Research of Interest

  1. Daniel Almirall, Charlotte DiStefano, Ya-Chih Chang, Stephanie Shire, Ann Kaiser, Xi Lu, Inbal Nahum-Shani, Rebecca Landa, Pamela Mathy and Connie Kasari. Longitudinal Effects of Adaptive Interventions With a Speech-Generating Device in Minimally Verbal Children With ASD. Journal of Clinical Child & Adolescent Psychology 0(0):1-15, March 2016. URL, DOI BibTeX

    @article{Almirall0,
    	title = "Longitudinal Effects of Adaptive Interventions With a Speech-Generating Device in Minimally Verbal Children With ASD",
    	author = "Daniel Almirall and Charlotte DiStefano and Ya-Chih Chang and Stephanie Shire and Ann Kaiser and Xi Lu and Inbal Nahum-Shani and Rebecca Landa and Pamela Mathy and Connie Kasari",
    	journal = "Journal of Clinical Child \& Adolescent Psychology",
    	year = 2016,
    	month = "March",
    	note = "PMID: 26954267",
    	number = 0,
    	pages = "1-15",
    	volume = 0,
    	__markedentry = "[:6]",
    	abstract = "There are limited data on the effects of adaptive social communication interventions with a speech-generating device in autism. This study is the first to compare growth in communications outcomes among three adaptive interventions in school-age children with autism spectrum disorder (ASD) who are minimally verbal. Sixty-one children, ages 5–8 years, participated in a sequential, multiple-assignment randomized trial (SMART). All children received a developmental behavioral communication intervention: joint attention, symbolic play, engagement and regulation (JASP) with enhanced milieu teaching (EMT). The SMART included three 2-stage, 24-week adaptive interventions with different provisions of a speech-generating device (SGD) in the context of JASP+EMT. The first adaptive intervention, with no SGD, initially assigned JASP+EMT alone, then intensified JASP+EMT for slow responders. In the second adaptive intervention, slow responders to JASP+EMT were assigned JASP+EMT+SGD. The third adaptive intervention initially assigned JASP+EMT+SGD; then intensified JASP+EMT+SGD for slow responders. Analyses examined between-group differences in change in outcomes from baseline to Week 36. Verbal outcomes included spontaneous communicative utterances and novel words. Nonlinguistic communication outcomes included initiating joint attention and behavior regulation, and play. The adaptive intervention beginning with JASP+EMT+SGD was estimated as superior. There were significant (p < .05) between-group differences in change in spontaneous communicative utterances and initiating joint attention. School-age children with ASD who are minimally verbal make significant gains in communication outcomes with an adaptive intervention beginning with JASP+EMT+SGD. Future research should explore mediators and moderators of the adaptive intervention effects and second-stage intervention options that further capitalize on early gains in treatment.",
    	doi = "10.1080/15374416.2016.1138407",
    	eprint = "http://dx.doi.org/10.1080/15374416.2016.1138407",
    	timestamp = "2016.03.31",
    	url = "http://dx.doi.org/10.1080/15374416.2016.1138407"
    }
    
  2. Bill Brantley. The Data Briefing: Mapping the Big Data Ecosystem of U.S. Agriculture. Digital.gov, February 2016. URL BibTeX

    @article{Brantley2016,
    	title = "The Data Briefing: Mapping the Big Data Ecosystem of U.S. Agriculture",
    	author = "Bill Brantley",
    	journal = "Digital.gov",
    	year = 2016,
    	month = "February",
    	note = "ePub",
    	timestamp = "2016.02.10",
    	url = "http://www.digitalgov.gov/2016/02/03/the-data-briefing-mapping-the-big-data-ecosystem-of-u-s-agriculture/?utm_medium=email&utm_source=govdelivery"
    }
    
  3. Ida Sim. Two Ways of Knowing: Big Data and Evidence-Based Medicine.. Annals of Internal Medicine, January 2016. URL, DOI BibTeX

    @article{Sim2016,
    	title = "Two Ways of Knowing: Big Data and Evidence-Based Medicine.",
    	author = "Ida Sim",
    	journal = "Annals of Internal Medicine",
    	year = 2016,
    	month = "January",
    	note = "ePub ahead of print",
    	doi = "10.7326/M15-2970",
    	timestamp = "2016.02.10",
    	url = "http://annals.org/article.aspx?articleid=2484291"
    }
    
  4. Dan L Longo and Jeffrey M Drazen. Data Sharing. New England Journal of Medicine 374(3):276-277, 2016. URL, DOI BibTeX

    @article{Longo2016,
    	title = "Data Sharing",
    	author = "Longo, Dan L. and Drazen, Jeffrey M.",
    	journal = "New England Journal of Medicine",
    	year = 2016,
    	note = "PMID: 26789876",
    	number = 3,
    	pages = "276-277",
    	volume = 374,
    	doi = "10.1056/NEJMe1516564",
    	eprint = "http://dx.doi.org/10.1056/NEJMe1516564",
    	timestamp = "2016.02.10",
    	url = "http://dx.doi.org/10.1056/NEJMe1516564"
    }
    
  5. PLOS Medicine Editors. Can Data Sharing Become the Path of Least Resistance?. PLOS Medicine, 2016. URL, DOI BibTeX

    @article{PLOS2016,
    	title = "Can Data Sharing Become the Path of Least Resistance?",
    	author = "PLOS Medicine Editors",
    	journal = "PLOS Medicine",
    	year = 2016,
    	note = "Published electronically 1/26/2016",
    	doi = "10.1371/journal.pmed.1001949",
    	timestamp = "2016.02.10",
    	url = "http://journals.plos.org/plosmedicine/article?id=10.1371/journal.pmed.1001949"
    }
    
  6. Dalmeet Singh Chawla. The unsung heroes of scientific software. Nature 529(7584), January 2016. URL BibTeX

    @article{Chawla2016,
    	title = "The unsung heroes of scientific software",
    	author = "Dalmeet Singh Chawla",
    	journal = "Nature",
    	year = 2016,
    	month = "January",
    	number = 7584,
    	volume = 529,
    	timestamp = "2016.02.10",
    	url = "http://www.nature.com/news/the-unsung-heroes-of-scientific-software-1.19100"
    }
    
  7. Sumeet Kumar, Le T Nguyen, Ming Zeng, Kate Liu and Joy Zhang. Sound Shredding: Privacy Preserved Audio Sensing. In Proceedings of the 16th International Workshop on Mobile Computing Systems and Applications. 2015, 135–140. URL, DOI BibTeX

    @inproceedings{Kumar:2015:SSP:2699343.2699366,
    	title = "Sound Shredding: Privacy Preserved Audio Sensing",
    	author = "Kumar, Sumeet and Nguyen, Le T. and Zeng, Ming and Liu, Kate and Zhang, Joy",
    	booktitle = "Proceedings of the 16th International Workshop on Mobile Computing Systems and Applications",
    	year = 2015,
    	address = "New York, NY, USA",
    	pages = "135--140",
    	publisher = "ACM",
    	series = "HotMobile '15",
    	abstract = "Sound provides valuable information about a mobile user’s activity and environment. With the increasing large market penetration of smart phones, recording sound from mobile phones’ microphones and processing the sound information either on mobile devices or in the cloud opens a window to a large variety of mobile applications that are context-aware and behavior-aware. On the other hand, sound sensing has the potential risk of compromising users’ privacy. Security attacks by malicious software running on smart phones can obtain in-band and out-of-band sound information to infer the content of users’ conversation. In this paper, we propose two simple yet highly effective methods called sound shredding and sound subsampling. Sound shredding mutates the raw sound frames randomly just like paper shredding and sound subsampling randomly drops sound frames without storing them. The resulting mutated sound recording makes it difficult to recover the text content of the original sound recording, yet we show that some acoustic features are preserved which retains the accuracy of context recognition.",
    	acmid = 2699366,
    	doi = "10.1145/2699343.2699366",
    	isbn = "978-1-4503-3391-7",
    	keywords = "context recognition, sound sensing, sound shredding, sound subsampling, user privacy",
    	location = "Santa Fe, New Mexico, USA",
    	numpages = 6,
    	url = "http://mlt.sv.cmu.edu/joy/publications/Sound-shredding-privacy-Hotmobile-CMU.pdf"
    }
    
  8. J Hernandez, Yin Li, J M Rehg and R W Picard. BioGlass: Physiological parameter estimation using a head-mounted wearable device. In Wireless Mobile Communication and Healthcare (Mobihealth), 2014 EAI 4th International Conference on. November 2014, 55-58. URL, DOI BibTeX

    @inproceedings{Hernandez2014,
    	title = "BioGlass: Physiological parameter estimation using a head-mounted wearable device",
    	author = "Hernandez, J. and Yin Li and Rehg, J.M. and Picard, R.W.",
    	booktitle = "Wireless Mobile Communication and Healthcare (Mobihealth), 2014 EAI 4th International Conference on",
    	year = 2014,
    	month = "Nov",
    	pages = "55-58",
    	abstract = "This work explores the feasibility of using sensors embedded in Google Glass, a head-mounted wearable device, to measure physiological signals of the wearer. In particular, we develop new methods to use Glass's accelerometer, gyroscope, and camera to extract pulse and respiratory rates of 12 participants during a controlled experiment. We show it is possible to achieve a mean absolute error of 0.83 beats per minute (STD: 2.02) for heart rate and 1.18 breaths per minute (STD: 2.04) for respiration rate when considering different combinations of sensors. These results included testing across sitting, supine, and standing still postures before and after physical exercise.",
    	doi = "10.1109/MOBIHEALTH.2014.7015908",
    	keywords = "acceleration measurement;accelerometers;biomechanics;body sensor networks;electrocardiography;feature extraction;gyroscopes;image sensors;intelligent sensors;medical signal processing;pneumodynamics;BioGlass;Glass accelerometer;ballistocardiogram;breaths;camera;embedded sensors;google glass;gyroscope;head-mounted wearable device;heart rate;mean absolute error;physical exercise;physiological parameter estimation;physiological signal measurement;pulse rate extraction;respiratory rate extraction;DVD;Decision support systems;Ballistocardiogram (BCG);accelererometer;blood volume pulse (BVP);camera;daily life monitoring;gyroscope;head-mounted wearable device;heart rate;respiration rate",
    	timestamp = "2016.01.15",
    	url = "http://web.media.mit.edu/~javierhr/files/14.Hernandez.Li.Rehg.Picard-MobiHealth.pdf"
    }
    
  9. Onur Yuruten, Jiyong Zhang and Pearl Pu. Decomposing Activities of Daily Living to Discover Routine Clusters. In Twenty-Eighth AAAI Conference on Artificial Intelligence. 2014. URL BibTeX

    @inproceedings{Yuerueten2014,
    	title = "Decomposing Activities of Daily Living to Discover Routine Clusters",
    	author = "Yuruten, Onur and Zhang, Jiyong and Pu, Pearl",
    	booktitle = "Twenty-Eighth AAAI Conference on Artificial Intelligence",
    	year = 2014,
    	abstract = "The modern sensor technology helps us collect time series data for activities of daily living (ADLs), which in turn can be used to infer broad patterns, such as common daily routines. Most of the existing approaches either rely on a model trained by a preselected and manually labeled set of activities, or perform micro-pattern analysis with manually selected length and number of micro-patterns. Since real life ADL datasets are massive, such approaches would be too costly to apply. Thus, there is a need to formulate unsupervised methods that can be applied to different time scales. We propose a novel approach to discover clusters of daily activity routines. We use a matrix decomposition method to isolate routines and deviations to obtain two different sets of clusters. We obtain the final memberships via the cross product of these sets. We validate our approach using two real-life ADL datasets and a well-known artificial dataset. Based on average silhouette width scores, our approach can capture strong structures in the underlying data. Furthermore, results show that our approach improves on the accuracy of the baseline algorithms by 12% with a statistical significance (p <0.05) using the Wilcoxon signed-rank comparison test.",
    	timestamp = "2016.01.15",
    	url = "http://www.aaai.org/ocs/index.php/AAAI/AAAI14/paper/view/8235/8579"
    }
    
  10. Yi Xu, Jan-Michael Frahm and Fabian Monrose. Watching the Watchers: Automatically Inferring TV Content From Outdoor Light Effusions. In Proceedings of the 2014 ACM SIGSAC Conference on Computer and Communications Security. 2014, 418–428. URL, DOI BibTeX

    @inproceedings{Xu:2014:WWA:2660267.2660358,
    	title = "Watching the Watchers: Automatically Inferring TV Content From Outdoor Light Effusions",
    	author = "Xu, Yi and Frahm, Jan-Michael and Monrose, Fabian",
    	booktitle = "Proceedings of the 2014 ACM SIGSAC Conference on Computer and Communications Security",
    	year = 2014,
    	address = "New York, NY, USA",
    	pages = "418--428",
    	publisher = "ACM",
    	series = "CCS '14",
    	abstract = "The flickering lights of content playing on TV screens in our living rooms are an all too familiar sight at night --- and one that many of us have paid little attention to with regards to the amount of information these diffusions may leak to an inquisitive outsider. In this paper, we introduce an attack that exploits the emanations of changes in light (e.g., as seen through the windows and recorded over 70 meters away) to reveal the programs we watch. Our empirical results show that the attack is surprisingly robust to a variety of noise signals that occur in real-world situations, and moreover, can successfully identify the content being watched among a reference library of tens of thousands of videos within several seconds. The robustness and efficiency of the attack can be attributed to the use of novel feature sets and an elegant online algorithm for performing index-based matches.",
    	acmid = 2660358,
    	doi = "10.1145/2660267.2660358",
    	isbn = "978-1-4503-2957-6",
    	keywords = "compromising emanation, visual eavesdropping",
    	location = "Scottsdale, Arizona, USA",
    	numpages = 11,
    	url = "http://doi.acm.org/10.1145/2660267.2660358"
    }
    
  11. Robert Templeman, Mohammed Korayem, David Crandall and Apu Kapadia. PlaceAvoider: Steering first-person cameras away from sensitive spaces. In Network and Distributed System Security Symposium (NDSS). 2014. URL BibTeX

    @inproceedings{Templeman2014,
    	title = "PlaceAvoider: Steering first-person cameras away from sensitive spaces",
    	author = "Templeman, Robert and Korayem, Mohammed and Crandall, David and Kapadia, Apu",
    	booktitle = "Network and Distributed System Security Symposium (NDSS)",
    	year = 2014,
    	abstract = "Cameras are now commonplace in our social and computing landscapes and embedded into consumer devices like smartphones and tablets. A new generation of wearable devices (such as Google Glass) will soon make ‘first-person’ cameras nearly ubiquitous, capturing vast amounts of imagery without deliberate human action. ‘Lifelogging’ devices and applications will record and share images from people’s daily lives with their social networks. These devices that automatically capture images in the background raise serious privacy concerns, since they are likely to capture deeply private information. Users of these devices need ways to identify and prevent the sharing of sensitive images. As a first step, we introduce PlaceAvoider, a technique for owners of first-person cameras to ‘blacklist’ sensitive spaces (like bathrooms and bedrooms). PlaceAvoider recognizes images captured in these spaces and flags them for review before the images are made available to applications. PlaceAvoider performs novel image analysis using both fine-grained image features (like specific objects) and coarse-grained, scene-level features (like colors and textures) to classify where a photo was taken. PlaceAvoider combines these features in a probabilistic framework that jointly labels streams of images in order to improve accuracy. We test the technique on five realistic firstperson image datasets and show it is robust to blurriness, motion, and occlusion.",
    	timestamp = "2016.01.15",
    	url = "http://www.cs.indiana.edu/~kapadia/papers/placeavoider-ndss14.pdf"
    }
    
  12. David Sun, Pablo Paredes and John Canny. MouStress: Detecting Stress from Mouse Motion. In Proceedings of the SIGCHI Conference on Human Factors in Computing Systems. 2014, 61–70. URL, DOI BibTeX

    @inproceedings{Sun:2014:MDS:2556288.2557243,
    	title = "MouStress: Detecting Stress from Mouse Motion",
    	author = "Sun, David and Paredes, Pablo and Canny, John",
    	booktitle = "Proceedings of the SIGCHI Conference on Human Factors in Computing Systems",
    	year = 2014,
    	address = "New York, NY, USA",
    	pages = "61--70",
    	publisher = "ACM",
    	series = "CHI '14",
    	abstract = {Stress causes and exacerbates many physiological and mental health problems. Routine and unobtrusive monitoring of stress would enable a variety of treatments, from break-taking to calming exercises. It may also be a valuable tool for assessing effects (frustration, difficulty) of using interfaces or applications. Custom sensing hardware is a poor option, because of the need to buy/wear/use it continuously, even before stress-related problems are evident. Here we explore stress measurement from common computer mouse operations. We use a simple model of arm-hand dynamics that captures muscle stiffness during mouse movement. We show that the within-subject mouse-derived stress measure is quite strong, even compared to concurrent physiological sensor measurements. While our study used fixed mouse tasks, the stress signal was still strong even when averaged across widely varying task geometries. We argue that mouse sensing "in the wild" may be feasible, by analyzing frequently-performed operations of particular geometries.},
    	acmid = 2557243,
    	doi = "10.1145/2556288.2557243",
    	isbn = "978-1-4503-2473-1",
    	keywords = "affective interfaces, mouse interaction, stress modeling",
    	location = "Toronto, Ontario, Canada",
    	numpages = 10,
    	url = "http://doi.acm.org/10.1145/2556288.2557243"
    }
    
  13. Jacopo Staiano, Nuria Oliver, Bruno Lepri, Rodrigo Oliveira, Michele Caraviello and Nicu Sebe. Money Walks: A Human-centric Study on the Economics of Personal Mobile Data. In Proceedings of the 2014 ACM International Joint Conference on Pervasive and Ubiquitous Computing. 2014, 583–594. URL, DOI BibTeX

    @inproceedings{Staiano2014,
    	title = "Money Walks: A Human-centric Study on the Economics of Personal Mobile Data",
    	author = "Staiano, Jacopo and Oliver, Nuria and Lepri, Bruno and de Oliveira, Rodrigo and Caraviello, Michele and Sebe, Nicu",
    	booktitle = "Proceedings of the 2014 ACM International Joint Conference on Pervasive and Ubiquitous Computing",
    	year = 2014,
    	address = "New York, NY, USA",
    	pages = "583--594",
    	publisher = "ACM",
    	series = "UbiComp '14",
    	abstract = "In the context of a myriad of mobile apps which collect personally identifiable information (PII) and a prospective market place of personal data, we investigate a user-centric monetary valuation of mobile PII. During a 6-week long user study in a living lab deployment with 60 participants, we collected their daily valuations of 4 categories of mobile PII (communication, e.g. phonecalls made/received, applications, e.g. time spent on different apps, location and media, e.g. photos taken) at three levels of complexity (individual data points, aggregated statistics and processed, i.e. meaningful interpretations of the data). In order to obtain honest valuations, we employ a reverse second price auction mechanism. Our findings show that the most sensitive and valued category of personal information is location. We report statistically significant associations between actual mobile usage, personal dispositions, and bidding behavior. Finally, we outline key implications for the design of mobile services and future markets of personal data.",
    	acmid = 2632074,
    	doi = "10.1145/2632048.2632074",
    	isbn = "978-1-4503-2968-2",
    	keywords = "auction, economics, living lab, mobile computing, monetization, personal mobile data, privacy",
    	location = "Seattle, Washington",
    	numpages = 12,
    	timestamp = "2016.01.15",
    	url = "http://arxiv.org/pdf/1407.0566.pdf"
    }
    
  14. Hillol Sarker, Moushumi Sharmin, Amin Ahsan Ali, Md. Mahbubur Rahman, Rummana Bari, Syed Monowar Hossain and Santosh Kumar. Assessing the Availability of Users to Engage in Just-in-time Intervention in the Natural Environment. In Proceedings of the 2014 ACM International Joint Conference on Pervasive and Ubiquitous Computing. 2014, 909–920. URL, DOI BibTeX

    @inproceedings{Sarker2014,
    	title = "Assessing the Availability of Users to Engage in Just-in-time Intervention in the Natural Environment",
    	author = "Sarker, Hillol and Sharmin, Moushumi and Ali, Amin Ahsan and Rahman, Md. Mahbubur and Bari, Rummana and Hossain, Syed Monowar and Kumar, Santosh",
    	booktitle = "Proceedings of the 2014 ACM International Joint Conference on Pervasive and Ubiquitous Computing",
    	year = 2014,
    	address = "New York, NY, USA",
    	pages = "909--920",
    	publisher = "ACM",
    	series = "UbiComp '14",
    	abstract = "Wearable wireless sensors for health monitoring are enabling the design and delivery of just-in-time interventions (JITI). Critical to the success of JITI is to time its delivery so that the user is available to be engaged. We take a first step in modeling users’ availability by analyzing 2,064 hours of physiological sensor data and 2,717 self-reports collected from 30 participants in a week-long field study. We use delay in responding to a prompt to objectively measure availability. We compute 99 features and identify 30 as most discriminating to train a machine learning model for predicting availability. We find that location, affect, activity type, stress, time, and day of the week, play significant roles in predicting availability. We find that users are least available at work and during driving, and most available when walking outside. Our model finally achieves an accuracy of 74.7% in 10-fold cross-validation and 77.9% with leave-one-subject-out.",
    	acmid = 2636082,
    	doi = "10.1145/2632048.2636082",
    	isbn = "978-1-4503-2968-2",
    	keywords = "EMA, interruption, intervention, mobile application, mobile health, self-report",
    	location = "Seattle, Washington",
    	numpages = 12,
    	timestamp = "2016.01.15",
    	url = "http://doi.acm.org/10.1145/2632048.2636082"
    }
    
  15. Alireza Sahami Shirazi, Niels Henze, Tilman Dingler, Martin Pielot, Dominik Weber and Albrecht Schmidt. Large-scale Assessment of Mobile Notifications. In Proceedings of the SIGCHI Conference on Human Factors in Computing Systems. 2014, 3055–3064. URL, DOI BibTeX

    @inproceedings{SahamiShirazi:2014:LAM:2556288.2557189,
    	title = "Large-scale Assessment of Mobile Notifications",
    	author = "Sahami Shirazi, Alireza and Henze, Niels and Dingler, Tilman and Pielot, Martin and Weber, Dominik and Schmidt, Albrecht",
    	booktitle = "Proceedings of the SIGCHI Conference on Human Factors in Computing Systems",
    	year = 2014,
    	address = "New York, NY, USA",
    	pages = "3055--3064",
    	publisher = "ACM",
    	series = "CHI '14",
    	abstract = "Notifications are a core feature of mobile phones. They inform users about a variety of events. Users may take immediate action or ignore them depending on the importance of a notification as well as their current context. The nature of notifications is manifold, applications use them both sparsely and frequently. In this paper we present the first large-scale analysis of mobile notifications with a focus on users' subjective perceptions. We derive a holistic picture of notifications on mobile phones by collecting close to 200 million notifications from more than 40,000 users. Using a data-driven approach, we break down what users like and dislike about notifications. Our results reveal differences in importance of notifications and how users value notifications from messaging apps as well as notifications that include information about people and events. Based on these results we derive a number of findings about the nature of notifications and guidelines to effectively use them",
    	acmid = 2557189,
    	doi = "10.1145/2556288.2557189",
    	isbn = "978-1-4503-2473-1",
    	keywords = "apps, in the wild, large-scale, mobile hci, mobile phone, notification",
    	location = "Toronto, Ontario, Canada",
    	numpages = 10,
    	url = "http://doi.acm.org/10.1145/2556288.2557189"
    }
    
  16. Tauhidur Rahman, Alexander T Adams, Mi Zhang, Erin Cherry, Bobby Zhou, Huaishu Peng and Tanzeem Choudhury. BodyBeat: A Mobile System for Sensing Non-speech Body Sounds. In Proceedings of the 12th Annual International Conference on Mobile Systems, Applications, and Services. 2014, 2–13. URL, DOI BibTeX

    @inproceedings{Rahman2014,
    	title = "BodyBeat: A Mobile System for Sensing Non-speech Body Sounds",
    	author = "Rahman, Tauhidur and Adams, Alexander T. and Zhang, Mi and Cherry, Erin and Zhou, Bobby and Peng, Huaishu and Choudhury, Tanzeem",
    	booktitle = "Proceedings of the 12th Annual International Conference on Mobile Systems, Applications, and Services",
    	year = 2014,
    	address = "New York, NY, USA",
    	pages = "2--13",
    	publisher = "ACM",
    	series = "MobiSys '14",
    	abstract = "In this paper, we propose BodyBeat, a novel mobile sensing system for capturing and recognizing a diverse range of non-speech body sounds in real-life scenarios. Non-speech body sounds, such as sounds of food intake, breath, laughter, and cough contain invaluable information about our dietary behavior, respiratory physiology, and affect. The BodyBeat mobile sensing system consists of a custom-built piezoelectric microphone and a distributed computational framework that utilizes an ARM microcontroller and an Android smartphone. The custom-built microphone is designed to capture subtle body vibrations directly from the body surface without being perturbed by external sounds. The microphone is attached to a 3D printed neckpiece with a suspension mechanism. The ARM embedded system and the Android smartphone process the acoustic signal from the microphone and identify non-speech body sounds. We have extensively evaluated the BodyBeat mobile sensing system. Our results show that BodyBeat outperforms other existing solutions in capturing and recognizing different types of important non-speech body sounds.",
    	acmid = 2594386,
    	doi = "10.1145/2594368.2594386",
    	isbn = "978-1-4503-2793-0",
    	keywords = "acoustic signal processing, embedded systems, mobile sensing, non-speech body sound",
    	location = "Bretton Woods, New Hampshire, USA",
    	numpages = 12,
    	timestamp = "2016.01.15",
    	url = "http://doi.acm.org/10.1145/2594368.2594386"
    }
    
  17. Elizabeth L Murnane and Scott Counts. Unraveling Abstinence and Relapse: Smoking Cessation Reflected in Social Media. In Proceedings of the 32Nd Annual ACM Conference on Human Factors in Computing Systems. 2014, 1345–1354. URL, DOI BibTeX

    @inproceedings{Murnane2014,
    	title = "Unraveling Abstinence and Relapse: Smoking Cessation Reflected in Social Media",
    	author = "Murnane, Elizabeth L. and Counts, Scott",
    	booktitle = "Proceedings of the 32Nd Annual ACM Conference on Human Factors in Computing Systems",
    	year = 2014,
    	address = "New York, NY, USA",
    	pages = "1345--1354",
    	publisher = "ACM",
    	series = "CHI '14",
    	abstract = "Analysis of smokers' posts and behaviors on Twitter reveals factors impacting abstinence and relapse during cessation attempts. Combining automatic and crowdsourced techniques, we detect users trying to quit smoking and analyze tweet and network data from a sample of 653 individuals over a two-year window of quitting. Guided by theory and practice, we derive behavioral, social, and emotional measures to compare users who abstain and relapse. We also examine the cessation process, demonstrating that Twitter can help chronicle how some people go about quitting. Among other results, we show that those who fail in their smoking cessation are far heavier posters and use relatively less positive language, while those who succeed are more social in both network ties and in directed communication. We conclude with insights on how intelligent intervention systems can harness these signals to provide tailored behavior change support.",
    	acmid = 2557145,
    	doi = "10.1145/2556288.2557145",
    	isbn = "978-1-4503-2473-1",
    	keywords = "behavior, cessation, health, smoking, social media, twitter",
    	location = "Toronto, Ontario, Canada",
    	numpages = 10,
    	timestamp = "2016.01.15",
    	url = "http://dl.acm.org/citation.cfm?id=2557145"
    }
    
  18. Yan Michalevsky, Dan Boneh and Gabi Nakibly. Gyrophone: Recognizing Speech from Gyroscope Signals. In Proceedings of the 23rd USENIX Conference on Security Symposium. 2014, 1053–1067. URL BibTeX

    @inproceedings{Michalevsky2014,
    	title = "Gyrophone: Recognizing Speech from Gyroscope Signals",
    	author = "Michalevsky, Yan and Boneh, Dan and Nakibly, Gabi",
    	booktitle = "Proceedings of the 23rd USENIX Conference on Security Symposium",
    	year = 2014,
    	address = "Berkeley, CA, USA",
    	pages = "1053--1067",
    	publisher = "USENIX Association",
    	series = "SEC'14",
    	abstract = "We show that the MEMS gyroscopes found on modern smart phones are sufficiently sensitive to measure acoustic signals in the vicinity of the phone. The resulting signals contain only very low-frequency information (<200Hz). Nevertheless we show, using signal processing and machine learning, that this information is sufficient to identify speaker information and even parse speech. Since iOS and Android require no special permissions to access the gyro, our results show that apps and active web content that cannot access the microphone can nevertheless eavesdrop on speech in the vicinity of the phone.",
    	acmid = 2671292,
    	comment = "http://dl.acm.org/citation.cfm?id=2671225.2671292",
    	isbn = "978-1-931971-15-7",
    	location = "San Diego, CA",
    	numpages = 15,
    	timestamp = "2016.01.15",
    	url = "http://crypto.stanford.edu/gyrophone/files/gyromic.pdf"
    }
    
  19. Addison Mayberry, Pan Hu, Benjamin Marlin, Christopher Salthouse and Deepak Ganesan. iShadow: Design of a Wearable, Real-time Mobile Gaze Tracker. In Proceedings of the 12th Annual International Conference on Mobile Systems, Applications, and Services. 2014, 82–94. URL, DOI BibTeX

    @inproceedings{Mayberry:2014:IDW:2594368.2594388,
    	title = "iShadow: Design of a Wearable, Real-time Mobile Gaze Tracker",
    	author = "Mayberry, Addison and Hu, Pan and Marlin, Benjamin and Salthouse, Christopher and Ganesan, Deepak",
    	booktitle = "Proceedings of the 12th Annual International Conference on Mobile Systems, Applications, and Services",
    	year = 2014,
    	address = "New York, NY, USA",
    	pages = "82--94",
    	publisher = "ACM",
    	series = "MobiSys '14",
    	abstract = "Continuous, real-time tracking of eye gaze is valuable in a variety of scenarios including hands-free interaction with the physical world, detection of unsafe behaviors, leveraging visual context for advertising, life logging, and others. While eye tracking is commonly used in clinical trials and user studies, it has not bridged the gap to everyday consumer use. The challenge is that a real-time eye tracker is a power-hungry and computation-intensive device which requires continuous sensing of the eye using an imager running at many tens of frames per second, and continuous processing of the image stream using sophisticated gaze estimation algorithms. Our key contribution is the design of an eye tracker that dramatically reduces the sensing and computation needs for eye tracking, thereby achieving orders of magnitude reductions in power consumption and form-factor. The key idea is that eye images are extremely redundant, therefore we can estimate gaze by using a small subset of carefully chosen pixels per frame. We instantiate this idea in a prototype hardware platform equipped with a low-power image sensor that provides random access to pixel values, a low-power ARM Cortex M3 microcontroller, and a bluetooth radio to communicate with a mobile phone. The sparse pixel-based gaze estimation algorithm is a multi-layer neural network learned using a state-ofthe-art sparsity-inducing regularization function that minimizes the gaze prediction error while simultaneously minimizing the number of pixels used. Our results show that we can operate at roughly 70mW of power, while continuously estimating eye gaze at the rate of 30 Hz with errors of roughly 3 degrees.",
    	acmid = 2594388,
    	doi = "10.1145/2594368.2594388",
    	isbn = "978-1-4503-2793-0",
    	keywords = "eye tracking, lifelog, neural network",
    	location = "Bretton Woods, New Hampshire, USA",
    	numpages = 13,
    	url = "http://doi.acm.org/10.1145/2594368.2594388"
    }
    
  20. Todd Kulesza, Saleema Amershi, Rich Caruana, Danyel Fisher and Denis Charles. Structured Labeling for Facilitating Concept Evolution in Machine Learning. In Proceedings of the 32Nd Annual ACM Conference on Human Factors in Computing Systems. 2014, 3075–3084. URL, DOI BibTeX

    @inproceedings{Kulesza2014,
    	title = "Structured Labeling for Facilitating Concept Evolution in Machine Learning",
    	author = "Kulesza, Todd and Amershi, Saleema and Caruana, Rich and Fisher, Danyel and Charles, Denis",
    	booktitle = "Proceedings of the 32Nd Annual ACM Conference on Human Factors in Computing Systems",
    	year = 2014,
    	address = "New York, NY, USA",
    	pages = "3075--3084",
    	publisher = "ACM",
    	series = "CHI '14",
    	abstract = "Labeling data is a seemingly simple task required for training many machine learning systems, but is actually fraught with problems. This paper introduces the notion of concept evolution, the changing nature of a person’s underlying concept (the abstract notion of the target class a person is labeling for, e.g., spam email, travel related web pages) which can result in inconsistent labels and thus be detrimental to machine learning. We introduce two structured labeling solutions, a novel technique we propose for helping people define and refine their concept in a consistent manner as they label. Through a series of five experiments, including a controlled lab study, we illustrate the impact and dynamics of concept evolution in practice and show that structured labeling helps people label more consistently in the presence of concept evolution than traditional labeling.",
    	acmid = 2557238,
    	doi = "10.1145/2556288.2557238",
    	isbn = "978-1-4503-2473-1",
    	keywords = "concept evolution, interactive machine learning",
    	location = "Toronto, Ontario, Canada",
    	numpages = 10,
    	timestamp = "2016.01.15",
    	url = "http://doi.acm.org/10.1145/2556288.2557238"
    }
    
  21. Roberto Hoyle, Robert Templeman, Steven Armes, Denise Anthony, David Crandall and Apu Kapadia. Privacy Behaviors of Lifeloggers Using Wearable Cameras. In Proceedings of the 2014 ACM International Joint Conference on Pervasive and Ubiquitous Computing. 2014, 571–582. URL, DOI BibTeX

    @inproceedings{Hoyle2014,
    	title = "Privacy Behaviors of Lifeloggers Using Wearable Cameras",
    	author = "Hoyle, Roberto and Templeman, Robert and Armes, Steven and Anthony, Denise and Crandall, David and Kapadia, Apu",
    	booktitle = "Proceedings of the 2014 ACM International Joint Conference on Pervasive and Ubiquitous Computing",
    	year = 2014,
    	address = "New York, NY, USA",
    	pages = "571--582",
    	publisher = "ACM",
    	series = "UbiComp '14",
    	abstract = "A number of wearable ‘lifelogging’ camera devices have been released recently, allowing consumers to capture images and other sensor data continuously from a first-person perspective. Unlike traditional cameras that are used deliberately and sporadically, lifelogging devices are always ‘on’ and automatically capturing images. Such features may challenge users’ (and bystanders’) expectations about privacy and control of image gathering and dissemination. While lifelogging cameras are growing in popularity, little is known about privacy perceptions of these devices or what kinds of privacy challenges they are likely to create. To explore how people manage privacy in the context of lifelogging cameras, as well as which kinds of first-person images people consider ‘sensitive,’ we conducted an in situ user study (N = 36) in which participants wore a lifelogging device for a week, answered questionnaires about the collected images, and participated in an exit interview. Our findings indicate that: 1) some people may prefer to manage privacy through in situ physical control of image collection in order to avoid later burdensome review of all collected images; 2) a combination of factors including time, location, and the objects and people appearing in the photo determines its ‘sensitivity;’ and 3) people are concerned about the privacy of bystanders, despite reporting almost no opposition or concerns expressed by bystanders over the course of the study.",
    	acmid = 2632079,
    	doi = "10.1145/2632048.2632079",
    	isbn = "978-1-4503-2968-2",
    	keywords = "lifelogging, privacy, wearable cameras",
    	location = "Seattle, Washington",
    	numpages = 12,
    	timestamp = "2016.01.15",
    	url = "http://www.cs.indiana.edu/~kapadia/papers/hoyle-ubicomp14.pdf"
    }
    
  22. Fanglin Chen, Rui Wang, Xia Zhou and Andrew T Campbell. My Smartphone Knows I Am Hungry. In Proceedings of the 2014 Workshop on Physical Analytics. 2014, 9–14. URL, DOI BibTeX

    @inproceedings{Chen2014,
    	title = "My Smartphone Knows I Am Hungry",
    	author = "Chen, Fanglin and Wang, Rui and Zhou, Xia and Campbell, Andrew T.",
    	booktitle = "Proceedings of the 2014 Workshop on Physical Analytics",
    	year = 2014,
    	address = "New York, NY, USA",
    	pages = "9--14",
    	publisher = "ACM",
    	series = "WPA '14",
    	abstract = "Can a smartphone learn our eating habits without the user being in the loop? Clearly, the phone could use checkins based on location to infer that if you are in a cafe, for example, there is a good possibility you might eat or drink something. In this paper, we use inferred behavioral data and location history to predict if you are going to eat or not in the near future. These predictors could serve as a basis for future eating trackers that work unobtrusively in the background of your phone rather than relying on burdensome user input. We report on a simple model that predicts the food purchases of a group of undergraduate college students (N=25) using inferred behavioral and location data from smartphones. The 10-week study uses the dining related purchase records from student college cards as ground-truth to validate our prediction model. Initial results show that we can predict food and drink purchases with an accuracy of 74% using three weeks of training data.",
    	acmid = 2611270,
    	doi = "10.1145/2611264.2611270",
    	isbn = "978-1-4503-2825-8",
    	keywords = "food purchase, human behavior dynamics, smartphone sensing.",
    	location = "Bretton Woods, New Hampshire, USA",
    	numpages = 6,
    	timestamp = "2016.01.15",
    	url = "http://doi.acm.org/10.1145/2611264.2611270"
    }
    
  23. Ricardo Cachucho, Marvin Meeng, Ugo Vespier, Siegfried Nijssen and Arno Knobbe. Mining Multivariate Time Series with Mixed Sampling Rates. In Proceedings of the 2014 ACM International Joint Conference on Pervasive and Ubiquitous Computing. 2014, 413–423. URL, DOI BibTeX

    @inproceedings{Cachucho2014,
    	title = "Mining Multivariate Time Series with Mixed Sampling Rates",
    	author = "Cachucho, Ricardo and Meeng, Marvin and Vespier, Ugo and Nijssen, Siegfried and Knobbe, Arno",
    	booktitle = "Proceedings of the 2014 ACM International Joint Conference on Pervasive and Ubiquitous Computing",
    	year = 2014,
    	address = "New York, NY, USA",
    	pages = "413--423",
    	publisher = "ACM",
    	series = "UbiComp '14",
    	acmid = 2632061,
    	doi = "10.1145/2632048.2632061",
    	isbn = "978-1-4503-2968-2",
    	keywords = "aggregation, feature construction, mixed sampling rates, multivariate time series, sensor data",
    	location = "Seattle, Washington",
    	numpages = 11,
    	timestamp = "2016.01.15",
    	url = "http://liacs.leidenuniv.nl/~degouveiadacostare/Publ/ubicomp2014.pdf"
    }
    
  24. Ali Borji and Laurent Itti. Defending Yarbus: Eye movements reveal observers' task. Journal of Vision 14(3):29, 2014. URL, DOI BibTeX

    @article{Borji2014,
    	title = "Defending Yarbus: Eye movements reveal observers' task",
    	author = "Borji, Ali and Itti, Laurent",
    	journal = "Journal of Vision",
    	year = 2014,
    	number = 3,
    	pages = 29,
    	volume = 14,
    	doi = "10.1167/14.3.29",
    	eprint = "/data/Journals/JOV/932817/i1534-7362-14-3-29.pdf",
    	timestamp = "2016.01.15",
    	url = "http://jov.arvojournals.org/article.aspx?articleid=2122021"
    }
    
  25. Otto F Barak, Aleksandar Klasnja, JELENA POPADIC GACESA and NIKOLA G GRUJIC. Gender differences in parasympathetic reactivation during recovery from Wingate anaerobic test. Periodicum biologorum 116(1):53–58, 2014. URL BibTeX

    @article{Barak2014,
    	title = "Gender differences in parasympathetic reactivation during recovery from Wingate anaerobic test",
    	author = "Barak, Otto F and Klasnja, Aleksandar and POPADIC GACESA, JELENA and GRUJIC, NIKOLA G",
    	journal = "Periodicum biologorum",
    	year = 2014,
    	number = 1,
    	pages = "53--58",
    	volume = 116,
    	publisher = "Hrvatsko prirodoslovno dru{\v{s}}tvo",
    	timestamp = "2016.01.15",
    	url = "http://hrcak.srce.hr/125465?lang=en"
    }
    
  26. Y Ayzenberg and R W Picard. FEEL: A System for Frequent Event and Electrodermal Activity Labeling. Biomedical and Health Informatics, IEEE Journal of 18(1):266-277, January 2014. URL, DOI BibTeX

    @article{Ayzenberg2014,
    	title = "FEEL: A System for Frequent Event and Electrodermal Activity Labeling",
    	author = "Ayzenberg, Y. and Picard, R.W.",
    	journal = "Biomedical and Health Informatics, IEEE Journal of",
    	year = 2014,
    	month = "Jan",
    	number = 1,
    	pages = "266-277",
    	volume = 18,
    	abstract = "The wide availability of low-cost wearable biophysiological sensors enables us to measure how the environment and our experiences impact our physiology. This creates a challenge: in order to interpret the longitudinal data, we require the matching contextual information as well. Collecting continuous biophysiological data makes it unfeasible to rely solely on our memory for contextual information. In this paper, we first present an architecture and implementation of a system for the acquisition, processing, and visualization of biophysiological signals and contextual information. Next, we present the results of a user study: users wore electrodermal activity wrist sensors that measured their autonomic arousal. These users uploaded the sensor data at the end of each day. At first, they annotated their events at the end of each day; then, after a two-day break, they annotated the data from two days earlier. One group of users had access to both the signal and the contextual information collected by the mobile phone and the other group could only access the biophysiological signal. At the end of the study, the users filled in a system usability scale and user experience surveys. Our results show that the system enables the users to annotate biophysiological signals at a greater effectiveness than the current state of the art while also providing very good usability.",
    	doi = "10.1109/JBHI.2013.2278213",
    	issn = "2168-2194",
    	keywords = "bioelectric potentials;body sensor networks;data visualisation;medical signal detection;medical signal processing;mobile radio;skin;FEEL;biophysiological data;biophysiological signal annotation;biophysiological signals;contextual information;electrodermal activity labeling;electrodermal activity wrist sensors;low-cost wearable biophysiological sensors;mobile phone;physiology;Calendars;Context;Mobile handsets;Monitoring;Physiology;Sensors;Servers;Context;mobile computing;pervasive computing;wearable sensors",
    	timestamp = "2016.01.15",
    	url = "http://affect.media.mit.edu/pdfs/14.Ayzenberg-Picard-IEEE-JBHI.pdf"
    }
    
  27. S Salman, Zheyu Wang, A Kiourti, E Topsakal and J L Volakis. A non-invasive lung monitoring sensor with integrated body-area network. In Microwave Workshop Series on RF and Wireless Technologies for Biomedical and Healthcare Applications (IMWS-BIO), 2013 IEEE MTT-S International. December 2013, 1-3. URL, DOI BibTeX

    @inproceedings{Salman2013,
    	title = "A non-invasive lung monitoring sensor with integrated body-area network",
    	author = "Salman, S. and Zheyu Wang and Kiourti, A. and Topsakal, E. and Volakis, J.L.",
    	booktitle = "Microwave Workshop Series on RF and Wireless Technologies for Biomedical and Healthcare Applications (IMWS-BIO), 2013 IEEE MTT-S International",
    	year = 2013,
    	month = "Dec",
    	pages = "1-3",
    	abstract = "This paper discusses the design and testing of a new robust system for in-situ continuous monitoring of the lung's condition. The system is composed of a body worn medical sensor with an accompanying wireless body area network (BAN) for remote health monitoring. The lung sensor consists of 17 electrodes, and operates at 40MHz. It aims to approximate the dielectric constant of the underlying lung tissue independent of variations in the outer layers (skin, fat, muscle and bone). Concurrently, the wireless BAN is used to transmit the measured dielectric constant to a mobile device via Bluetooth for continuous remote healthcare monitoring. In this paper, we present the design and experimental validation of the proposed lung sensor integrated with wireless BAN data link.",
    	doi = "10.1109/IMWS-BIO.2013.6756243",
    	keywords = "Bluetooth;bioelectric phenomena;biomedical electrodes;body area networks;body sensor networks;bone;health care;lung;medical computing;muscle;patient monitoring;permittivity;skin;Bluetooth;body worn medical sensor;bone;dielectric constant;electrodes;fat;healthcare monitoring;integrated body-area network;lung tissue;mobile device;muscle;noninvasive lung monitoring sensor;remote healthcare monitoring;skin;wireless BAN data link;wireless body area network;Biomedical measurement;Dielectric constant;Dielectric measurement;Lungs;Monitoring;Wireless communication;Wireless sensor networks;BAN;Biomedical sensor;healthcare monitoring;wearable sensor",
    	timestamp = "2016.01.15",
    	url = "http://ieeexplore.ieee.org/xpl/freeabs_all.jsp?arnumber=6756243&abstractAccess=no&userType=inst"
    }
    
  28. K Zolfaghar, N Meadem, A Teredesai, S B Roy, Si-Chi Chin and B Muckian. Big data solutions for predicting risk-of-readmission for congestive heart failure patients. In Big Data, 2013 IEEE International Conference on. October 2013, 64-71. URL, DOI BibTeX

    @inproceedings{Zolfaghar2013a,
    	title = "Big data solutions for predicting risk-of-readmission for congestive heart failure patients",
    	author = "Zolfaghar, K. and Meadem, N. and Teredesai, A. and Roy, S.B. and Si-Chi Chin and Muckian, B.",
    	booktitle = "Big Data, 2013 IEEE International Conference on",
    	year = 2013,
    	month = "Oct",
    	pages = "64-71",
    	abstract = "Developing holistic predictive modeling solutions for risk prediction is extremely challenging in healthcare informatics. Risk prediction involves integration of clinical factors with socio-demographic factors, health conditions, disease parameters, hospital care quality parameters, and a variety of variables specific to each health care provider making the task increasingly complex. Unsurprisingly, many of such factors need to be extracted independently from different sources, and integrated back to improve the quality of predictive modeling. Such sources are typically voluminous, diverse, and vary significantly over the time. Therefore, distributed and parallel computing tools collectively termed big data have to be developed. In this work, we study big data driven solutions to predict the 30-day risk of readmission for congestive heart failure (CHF) incidents. First, we extract useful factors from National Inpatient Dataset (NIS) and augment it with our patient dataset from Multicare Health System (MHS). Then, we develop scalable data mining models to predict risk of readmission using the integrated dataset. We demonstrate the effectiveness and efficiency of the open-source predictive modeling framework we used, describe the results from various modeling algorithms we tested, and compare the performance against baseline non-distributed, non-parallel, non-integrated small data results previously published to demonstrate comparable accuracy over millions of records.",
    	doi = "10.1109/BigData.2013.6691760",
    	keywords = "Big Data;cardiology;data mining;diseases;health care;hospitals;parallel processing;public domain software;Big data solutions;CHF;MHS;Multicare Health System;NIS;National Inpatient Dataset;clinical factors;congestive heart failure patient;data mining models;disease parameters;distributed computing tool;health care provider;health conditions;healthcare informatics;holistic predictive modeling solutions;hospital care quality parameters;open-source predictive modeling framework;parallel computing tool;risk-of-readmission prediction;socio-demographic factors;Data handling;Data storage systems;Diseases;Heart;Information management;Predictive models;Healthcare;Knowledge-Discovery;Risk Prediction",
    	timestamp = "2016.01.15",
    	url = "http://cwds.uw.edu/sites/default/files/publications/Big%20Data%20Solutions%20for%20Predicting%20Risk-of-Readmission%20for%20Congestive%20Heart%20Failure.pdf"
    }
    
  29. Chenren Xu, Sugang Li, Gang Liu, Yanyong Zhang, Emiliano Miluzzo, Yih-Farn Chen, Jun Li and Bernhard Firner. Crowd++: Unsupervised Speaker Count with Smartphones. In Proceedings of the 2013 ACM International Joint Conference on Pervasive and Ubiquitous Computing. 2013, 43–52. URL, DOI BibTeX

    @inproceedings{Xu2013,
    	title = "Crowd++: Unsupervised Speaker Count with Smartphones",
    	author = "Xu, Chenren and Li, Sugang and Liu, Gang and Zhang, Yanyong and Miluzzo, Emiliano and Chen, Yih-Farn and Li, Jun and Firner, Bernhard",
    	booktitle = "Proceedings of the 2013 ACM International Joint Conference on Pervasive and Ubiquitous Computing",
    	year = 2013,
    	address = "New York, NY, USA",
    	pages = "43--52",
    	publisher = "ACM",
    	series = "UbiComp '13",
    	abstract = "Smartphones are excellent mobile sensing platforms, with the microphone in particular being exercised in several audio inference applications. We take smartphone audio inference a step further and demonstrate for the first time that it’s possible to accurately estimate the number of people talking in a certain place – with an average error distance of 1.5 speakers – through unsupervised machine learning analysis on audio segments captured by the smartphones. Inference occurs transparently to the user and no human intervention is needed to derive the classification model. Our results are based on the design, implementation, and evaluation of a system called Crowd++, involving 120 participants in 6 very different environments. We show that no dedicated external hardware or cumbersome supervised learning approaches are needed but only off-the-shelf smartphones used in a transparent manner. We believe our findings have profound implications in many research fields, including social sensing and personal wellbeing assessment.",
    	acmid = 2493435,
    	doi = "10.1145/2493432.2493435",
    	isbn = "978-1-4503-1770-2",
    	keywords = "audio inference, smartphone sensing, speaker count",
    	location = "Zurich, Switzerland",
    	numpages = 10,
    	timestamp = "2016.01.15",
    	url = "http://doi.acm.org/10.1145/2493432.2493435"
    }
    
  30. Taiji Suzuki and Masashi Sugiyama. Sufficient dimension reduction via squared-loss mutual information estimation. Neural computation 25(3):725–758, 2013. BibTeX

    @article{Suzuki2013,
    	title = "Sufficient dimension reduction via squared-loss mutual information estimation",
    	author = "Suzuki, Taiji and Sugiyama, Masashi",
    	journal = "Neural computation",
    	year = 2013,
    	number = 3,
    	pages = "725--758",
    	volume = 25,
    	abstract = "The goal of sufficient dimension reduction in supervised learning is to find the lowdimensional subspace of input features that is ‘sufficient’ for predicting output values. In this paper, we propose a novel sufficient dimension reduction method using a squaredloss variant of mutual information as a dependency measure. We utilize an analytic approximator of squared-loss mutual information based on density ratio estimation, which is shown to possess suitable convergence properties. We then develop a natural gradient algorithm for sufficient subspace search. Numerical experiments show that the proposed method compares favorably with existing dimension reduction approaches.",
    	publisher = "MIT Press",
    	timestamp = "2016.01.15"
    }
    
  31. Bryson Padasdao, Ehsaneh Shahhaidar, Christopher Stickley and Olga Boric-Lubecke. Electromagnetic Biosensing of Respiratory Rate. Sensors Journal, IEEE 13(11):4204–4211, 2013. BibTeX

    @article{Padasdao2013,
    	title = "Electromagnetic Biosensing of Respiratory Rate",
    	author = "Padasdao, Bryson and Shahhaidar, Ehsaneh and Stickley, Christopher and Boric-Lubecke, Olga",
    	journal = "Sensors Journal, IEEE",
    	year = 2013,
    	number = 11,
    	pages = "4204--4211",
    	volume = 13,
    	abstract = "Continuous monitoring of respiratory rate is crucial in forecasting health crises and other major physiological instabilities. Current respiratory monitoring methods limit the mobility of the patient or require constant battery replacement. Wireless, wearable technology can collect continuous physiological data without immobilizing or inconveniencing patients, and human energy harvesting can be used to power these wearable sensors. In this paper, we explore this zero-net energy biosensor concept through simultaneous sensing and harvesting of respiratory effort. An off-the-shelf dc brushed motor is modified into a chest belt, and tested on a mechanical chest simulator as well as on 20 human subjects, using a spirometer as a reference. The electromagnetic biosensor is used to successfully harvest 7–70 µW from human subjects. On the mechanical chest, respiratory rate is detected with a mean absolute error of 0.00027 breaths/min with a standard deviation of 0.00019 breaths/min. For human subjects, respiratory rate is detected with a mean difference of 0.36 breaths/min with a standard deviation of 2.83 breaths/min (sitting), 0.23 breaths/min with a standard deviation of 2.64 breaths/min (standing), and 0.48 breaths/min with a standard deviation of 3.06 breaths/min (walking).",
    	publisher = "IEEE",
    	timestamp = "2016.01.15"
    }
    
  32. Bing Hu, Yanping Chen and Eamonn J Keogh. Time Series Classification under More Realistic Assumptions.. In SDM. 2013, 578–586. URL, DOI BibTeX

    @inproceedings{Hu2013,
    	title = "Time Series Classification under More Realistic Assumptions.",
    	author = "Hu, Bing and Chen, Yanping and Keogh, Eamonn J",
    	booktitle = "SDM",
    	year = 2013,
    	pages = "578--586",
    	abstract = "Most literature on time series classification assumes that the beginning and ending points of the pattern of interest can be correctly identified, both during the training phase and later deployment. In this work, we argue that this assumption is unjustified, and this has in many cases led to unwarranted optimism about the performance of the proposed algorithms. As we shall show, the task of correctly extracting individual gait cycles, heartbeats, gestures, behaviors, etc., is generally much more difficult than the task of actually classifying those patterns. We propose to mitigate this problem by introducing an alignment-free time series classification framework. The framework requires only very weakly annotated data, such as “in this ten minutes of data, we see mostly normal heartbeats…,” and by generalizing the classic machine learning idea of data editing to streaming/continuous data, allows us to build robust, fast and accurate classifiers. We demonstrate on several diverse real-world problems that beyond removing unwarranted assumptions and requiring essentially no human intervention, our framework is both significantly faster and significantly more accurate than current state-of-the-art approaches.",
    	doi = "http://dx.doi.org/10.1137/1.9781611972832.64",
    	timestamp = "2016.01.15",
    	url = "http://dx.doi.org/10.1137/1.9781611972832.64"
    }
    
  33. Heng-Tze Cheng, Feng-Tso Sun, Martin Griss, Paul Davis, Jianguo Li and Di You. NuActiv: Recognizing Unseen New Activities Using Semantic Attribute-based Learning. In Proceeding of the 11th Annual International Conference on Mobile Systems, Applications, and Services. 2013, 361–374. URL, DOI BibTeX

    @inproceedings{Cheng2013,
    	title = "NuActiv: Recognizing Unseen New Activities Using Semantic Attribute-based Learning",
    	author = "Cheng, Heng-Tze and Sun, Feng-Tso and Griss, Martin and Davis, Paul and Li, Jianguo and You, Di",
    	booktitle = "Proceeding of the 11th Annual International Conference on Mobile Systems, Applications, and Services",
    	year = 2013,
    	address = "New York, NY, USA",
    	pages = "361--374",
    	publisher = "ACM",
    	series = "MobiSys '13",
    	abstract = "We study the problem of how to recognize a new human activity when we have never seen any training example of that activity before. Recognizing human activities is an essential element for user-centric and context-aware applications. Previous studies showed promising results using various machine learning algorithms. However, most existing methods can only recognize the activities that were previously seen in the training data. A previously unseen activity class cannot be recognized if there were no training samples in the dataset. Even if all of the activities can be enumerated in advance, labeled samples are often time consuming and expensive to get, as they require huge effort from human annotators or experts. In this paper, we present NuActiv, an activity recognition system that can recognize a human activity even when there are no training data for that activity class. Firstly, we designed a new representation of activities using semantic attributes, where each attribute is a human readable term that describes a basic element or an inherent characteristic of an activity. Secondly, based on this representation, a twolayer zero-shot learning algorithm is developed for activity recognition. Finally, to reinforce recognition accuracy using minimal user feedback, we developed an active learning lgorithm for activity recognition. Our approach is evaluated on two datasets, including a 10-exercise-activity dataset we collected, and a public dataset of 34 daily life activities. Experimental results show that using semantic attribute-based learning, NuActiv can generalize knowledge to recognize unseen new activities. Our approach achieved up to 79% accuracy in unseen activity recognition",
    	acmid = 2464438,
    	doi = "10.1145/2462456.2464438",
    	isbn = "978-1-4503-1672-9",
    	keywords = "active learning, activity recognition, context-aware computing, machine learning, mobile sensing, semantic attributes, wearable computing, zero-shot learning",
    	location = "Taipei, Taiwan",
    	numpages = 14,
    	timestamp = "2016.01.15",
    	url = "http://users.ece.cmu.edu/~hengtzec/papers/MobiSys13_NuActiv_Cheng_CMU.pdf"
    }
    
  34. Jinwook Oh, Gyeonghoon Kim, Injoon Hong, Junyoung Park, Seungjin Lee, Joo-young Kim, Jeong-Ho Woo and Hoi-Jun Yoo. Low-Power, Real-Time Object-Recognition Processors for Mobile Vision Systems. Micro, IEEE 32(6):38-50, November 2012. DOI BibTeX

    @article{Oh2012,
    	title = "Low-Power, Real-Time Object-Recognition Processors for Mobile Vision Systems",
    	author = "Jinwook Oh and Gyeonghoon Kim and Injoon Hong and Junyoung Park and Seungjin Lee and Joo-young Kim and Jeong-Ho Woo and Hoi-Jun Yoo",
    	journal = "Micro, IEEE",
    	year = 2012,
    	month = "Nov",
    	number = 6,
    	pages = "38-50",
    	volume = 32,
    	abstract = "A new low-power object-recognition processor achieves real-time robust recognition, satisfying modern mobile vision systems' requirements. The authors introduce an attention-based object-recognition algorithm for energy efficiency, a heterogeneous multicore architecture for data- and thread-level parallelism, and a network on a chip for high on-chip bandwidth. The fabricated chip achieves 30 frames/second throughput and an average 320 mW power consumption on test 720p video sequences, yielding 640 GOPS/W and 10.5 NJ/pixel energy efficiency.",
    	doi = "10.1109/MM.2012.90",
    	issn = "0272-1732",
    	keywords = "computer vision;energy conservation;image sequences;low-power electronics;multiprocessing systems;network-on-chip;object recognition;parallel architectures;power aware computing;real-time systems;video signal processing;attention-based object recognition algorithm;data-level parallelism;energy efficiency;heterogeneous multicore architecture;low-power real-time object recognition processors;mobile vision systems;network on a chip;on-chip bandwidth;power 320 mW;real-time robust recognition;thread-level parallelism;video sequences;Decision support systems;Low power electronics;Multicore processing;Network-on-a-chip;Object recognition;Robustness;SIFT;attention;attention-based object recognition;heterogeneous multicore;multicore processor;network-on-chip;object recognition;object-recognition pipeline;scale invariant feature transform",
    	timestamp = "2016.01.15"
    }
    
  35. Byung-hoon Ko, Takhyung Lee, Changmok Choi, Youn-ho Kim, Gunguk Park, KyoungHo Kang, Sang Kon Bae and Kunsoo Shin. Motion artifact reduction in electrocardiogram using adaptive filtering based on half cell potential monitoring. In Engineering in Medicine and Biology Society (EMBC), 2012 Annual International Conference of the IEEE. August 2012, 1590-1593. DOI BibTeX

    @inproceedings{6346248,
    	title = "Motion artifact reduction in electrocardiogram using adaptive filtering based on half cell potential monitoring",
    	author = "Byung-hoon Ko and Takhyung Lee and Changmok Choi and Youn-ho Kim and Gunguk Park and KyoungHo Kang and Sang Kon Bae and Kunsoo Shin",
    	booktitle = "Engineering in Medicine and Biology Society (EMBC), 2012 Annual International Conference of the IEEE",
    	year = 2012,
    	month = "Aug",
    	pages = "1590-1593",
    	abstract = "The electrocardiogram (ECG) is the main measurement parameter for effectively diagnosing chronic disease and guiding cardio-fitness therapy. ECGs contaminated by noise or artifacts disrupt the normal functioning of the automatic analysis algorithm. The objective of this study is to evaluate a method of measuring the HCP variation in motion artifacts through direct monitoring. The proposed wearable sensing device has two channels. One channel is used to measure the ECG through a differential amplifier. The other is for monitoring motion artifacts using the modified electrode and the same differential amplifier. Noise reduction was performed using adaptive filtering, based on a reference signal highly correlated with it. Direct measurement of HCP variations can eliminate the need for additional sensors.",
    	doi = "10.1109/EMBC.2012.6346248",
    	issn = "1557-170X",
    	keywords = "adaptive filters;bioelectric potentials;biomedical electrodes;differential amplifiers;diseases;electrocardiography;filtering theory;medical signal processing;patient diagnosis;patient treatment;signal denoising;ECG;adaptive filtering;automatic analysis algorithm;cardio-fitness therapy;chronic disease diagnosis;differential amplifier;electrocardiogram;half cell potential monitoring;measurement parameter;modified electrode;motion artifact reduction;noise contamination;wearable sensing device;Adaptive filters;Biomedical monitoring;Electric potential;Electrocardiography;Electrodes;Monitoring;Sensors;Algorithms;Artifacts;Computer Simulation;Electrocardiography, Ambulatory;Electrodes;Humans;Movement;Signal Processing, Computer-Assisted;Signal-To-Noise Ratio"
    }
    
  36. Ning Yang, Xingli Zhao and Hong Zhang. A non-contact health monitoring model based on the Internet of things. In Natural Computation (ICNC), 2012 Eighth International Conference on. May 2012, 506-510. URL, DOI BibTeX

    @inproceedings{Yang2012,
    	title = "A non-contact health monitoring model based on the Internet of things",
    	author = "Ning Yang and Xingli Zhao and Hong Zhang",
    	booktitle = "Natural Computation (ICNC), 2012 Eighth International Conference on",
    	year = 2012,
    	month = "May",
    	pages = "506-510",
    	abstract = "The Internet of things uses in various fields, which is of great convenience to people's lives. Health monitoring can provide users with convenient and reliable health services, which are of low cost. The current health monitoring systems depend on the instruments. Based on the Internet of things, a system called NCHMS is proposed, which is monitoring the health status with no contact. This article elaborates on the structures and functions of NCHMS, improves the expression classification space for health monitoring, and gives a detailed expression recognition algorithm. The experimental data from the simulated experiments can tell that the system have considerable feasibility and practicality.",
    	doi = "10.1109/ICNC.2012.6234771",
    	issn = "2157-9555",
    	keywords = "medical computing;patient monitoring;Internet of things;NCHMS;expression classification space;expression recognition algorithm;health monitoring;health services;health status;instruments;noncontact health monitoring model;Computational modeling;Databases;Educational institutions;Face recognition;Internet;Monitoring;Servers;expression recognition;health monitoring;non-contact;the Internet of things",
    	timestamp = "2016.01.15",
    	url = "http://download.springer.com/static/pdf/831/chp%253A10.1007%252F978-3-642-30732-4_1.pdf?auth66=1422392308_d6afa52798b0717a8f1848483166faf5&ext=.pdf"
    }
    
  37. K Tollmar, F Bentley and C Viedma. Mobile Health Mashups: Making sense of multiple streams of wellbeing and contextual data for presentation on a mobile device. In Pervasive Computing Technologies for Healthcare (PervasiveHealth), 2012 6th International Conference on. May 2012, 65-72. URL, DOI BibTeX

    @inproceedings{Tollmar2012,
    	title = "Mobile Health Mashups: Making sense of multiple streams of wellbeing and contextual data for presentation on a mobile device",
    	author = "Tollmar, K. and Bentley, F. and Viedma, C.",
    	booktitle = "Pervasive Computing Technologies for Healthcare (PervasiveHealth), 2012 6th International Conference on",
    	year = 2012,
    	month = "May",
    	pages = "65-72",
    	abstract = "In this paper we present the Mobile Health Mashups system, a mobile service that collects data from a variety of health and wellbeing sensors and presents significant correlations across sensors in a mobile widget as well as on a mobile web application. We found that long-term correlation data provided users with new insights about systematic wellness trends that they could not make using only the time series graphs provided by the sensor manufacturers. We describe the Mobile Health Mashups system with a focus on analyzing and detailing the technical solution, such as: integration of sensors, how to create correlations between various data sets, and the presentation of the statistical data as feeds and graphs. We will also describe the iterative design process that involved a 2-month field trial, the outcome of this trial, and implications for design of mobile data mashup systems.",
    	doi = "10.4108/icst.pervasivehealth.2012.248698",
    	keywords = "graph theory;health care;mobile computing;time series;iterative design process;mobile Web application;mobile device;mobile health mashups system;multiple streams;statistical data;time series graphs;wellbeing sensors;Androids;Browsers;Calendars;Humanoid robots;Manuals;Mashups;Mobile communication;Data Visualization;Health;Mash-up;Mobile;Well-being",
    	timestamp = "2016.01.15",
    	url = "http://web.mit.edu/bentley/www/papers/mashupsPH.pdf"
    }
    
  38. Matei Zaharia, Mosharaf Chowdhury, Tathagata Das, Ankur Dave, Justin Ma, Murphy McCauly, Michael J Franklin, Scott Shenker and Ion Stoica. Resilient Distributed Datasets: A Fault-Tolerant Abstraction for In-Memory Cluster Computing. In Presented as part of the 9th USENIX Symposium on Networked Systems Design and Implementation (NSDI 12). 2012, 15–28. URL BibTeX

    @inproceedings{Zaharia2012,
    	title = "Resilient Distributed Datasets: A Fault-Tolerant Abstraction for In-Memory Cluster Computing",
    	author = "Matei Zaharia and Mosharaf Chowdhury and Tathagata Das and Ankur Dave and Justin Ma and Murphy McCauly and Michael J. Franklin and Scott Shenker and Ion Stoica",
    	booktitle = "Presented as part of the 9th USENIX Symposium on Networked Systems Design and Implementation (NSDI 12)",
    	year = 2012,
    	address = "San Jose, CA",
    	pages = "15--28",
    	publisher = "USENIX",
    	abstract = "We present Resilient Distributed Datasets (RDDs), a distributed memory abstraction that lets programmers perform in-memory computations on large clusters in a fault-tolerant manner. RDDs are motivated by two types of applications that current computing frameworks handle inefficiently: iterative algorithms and interactive data mining tools. In both cases, keeping data in memory can improve performance by an order of magnitude. To achieve fault tolerance efficiently, RDDs provide a restricted form of shared memory, based on coarsegrained transformations rather than fine-grained updates to shared state. However, we show that RDDs are expressive enough to capture a wide class of computations, including recent specialized programming models for iterative jobs, such as Pregel, and new applications that these models do not capture. We have implemented RDDs in a system called Spark, which we evaluate through a variety of user applications and benchmarks.",
    	isbn = "978-931971-92-8",
    	timestamp = "2016.01.15",
    	url = "https://www.usenix.org/conference/nsdi12/technical-sessions/presentation/zaharia"
    }
    
  39. Po-He Tseng, Ian G M Cameron, Giovanna Pari, James N Reynolds, Douglas P Munoz and Laurent Itti. High-throughput classification of clinical populations from natural viewing eye movements. Journal of Neurology 260(1):275–284, 2012. URL, DOI BibTeX

    @article{Tseng2012,
    	title = "High-throughput classification of clinical populations from natural viewing eye movements",
    	author = "Tseng, Po-He and Cameron, Ian G. M. and Pari, Giovanna and Reynolds, James N. and Munoz, Douglas P. and Itti, Laurent",
    	journal = "Journal of Neurology",
    	year = 2012,
    	number = 1,
    	pages = "275--284",
    	volume = 260,
    	abstract = "Many high-prevalence neurological disorders involve dysfunctions of oculomotor control and attention, including attention deficit hyperactivity disorder (ADHD), fetal alcohol spectrum disorder (FASD), and Parkinson's disease (PD). Previous studies have examined these deficits with clinical neurological evaluation, structured behavioral tasks, and neuroimaging. Yet, time and monetary costs prevent deploying these evaluations to large at-risk populations, which is critically important for earlier detection and better treatment. We devised a high-throughput, low-cost method where participants simply watched television while we recorded their eye movements. We combined eye-tracking data from patients and controls with a computational model of visual attention to extract 224 quantitative features. Using machine learning in a workflow inspired by microarray analysis, we identified critical features that differentiate patients from control subjects. With eye movement traces recorded from only 15 min of videos, we classified PD versus age-matched controls with 89.6 \% accuracy (chance 63.2 \%), and ADHD versus FASD versus control children with 77.3 \% accuracy (chance 40.4 \%). Our technique provides new quantitative insights into which aspects of attention and gaze control are affected by specific disorders. There is considerable promise in using this approach as a potential screening tool that is easily deployed, low-cost, and high-throughput for clinical disorders, especially in young children and elderly populations who may be less compliant to traditional evaluation tests.",
    	doi = "10.1007/s00415-012-6631-2",
    	issn = "1432-1459",
    	url = "http://dx.doi.org/10.1007/s00415-012-6631-2"
    }
    
  40. Michaela Götz, Suman Nath and Johannes Gehrke. MaskIt: Privately Releasing User Context Streams for Personalized Mobile Applications. In Proceedings of the 2012 ACM SIGMOD International Conference on Management of Data. 2012, 289–300. URL, DOI BibTeX

    @inproceedings{Goetz2012,
    	title = "MaskIt: Privately Releasing User Context Streams for Personalized Mobile Applications",
    	author = {G\"{o}tz, Michaela and Nath, Suman and Gehrke, Johannes},
    	booktitle = "Proceedings of the 2012 ACM SIGMOD International Conference on Management of Data",
    	year = 2012,
    	address = "New York, NY, USA",
    	pages = "289--300",
    	publisher = "ACM",
    	series = "SIGMOD '12",
    	abstract = "The rise of smartphones equipped with various sensors has enabled personalization of various applications based on user contexts extracted from sensor readings. At the same time it has raised serious concerns about the privacy of user contexts. In this paper, we present MASKIT, a technique to filter a user context stream that provably preserves privacy. The filtered context stream can be released to applications or be used to answer queries from applications. Privacy is defined with respect to a set of sensitive contexts specified by the user. MASKIT limits what adversaries can learn from the filtered stream about the user being in a sensitive context – even if the adversaries are powerful and have knowledge about the filtering system and temporal correlations in the context stream. At the heart of MASKIT is a privacy check deciding whether to release or suppress the current user context. We present two novel privacy checks and explain how to choose the check with the higher utility for a user. Our experiments on real smartphone context traces of 91 users demonstrate the utility of MASKIT.",
    	acmid = 2213870,
    	doi = "10.1145/2213836.2213870",
    	isbn = "978-1-4503-1247-9",
    	keywords = "data privacy, mobile applications",
    	location = "Scottsdale, Arizona, USA",
    	numpages = 12,
    	timestamp = "2016.01.15",
    	url = "http://doi.acm.org/10.1145/2213836.2213870"
    }
    
  41. Karen P Tang, Jason I Hong and Daniel P Siewiorek. Understanding How Visual Representations of Location Feeds Affect End-user Privacy Concerns. In Proceedings of the 13th International Conference on Ubiquitous Computing. 2011, 207–216. URL, DOI BibTeX

    @inproceedings{Tang:2011:UVR:2030112.2030141,
    	title = "Understanding How Visual Representations of Location Feeds Affect End-user Privacy Concerns",
    	author = "Tang, Karen P. and Hong, Jason I. and Siewiorek, Daniel P.",
    	booktitle = "Proceedings of the 13th International Conference on Ubiquitous Computing",
    	year = 2011,
    	address = "New York, NY, USA",
    	pages = "207--216",
    	publisher = "ACM",
    	series = "UbiComp '11",
    	abstract = "While past work has looked extensively at how to design privacy configuration UIs for sharing current location, there has not yet been work done to examine how visual representations of historical locations can influence enduser privacy. We present results for a study examining three visualization types (text-, map-, and time-based) for social sharing of past locations. Our results reveal that there are important design implications for location sharing applications, as certain visual elements led to more privacy concerns and inaccurate perceptions of privacy control.",
    	acmid = 2030141,
    	doi = "10.1145/2030112.2030141",
    	isbn = "978-1-4503-0630-0",
    	keywords = "location, location sharing, privacy concerns, visualization",
    	location = "Beijing, China",
    	numpages = 10,
    	url = "http://doi.acm.org/10.1145/2030112.2030141"
    }
    
  42. Andrew Raij, Animikh Ghosh, Santosh Kumar and Mani Srivastava. Privacy Risks Emerging from the Adoption of Innocuous Wearable Sensors in the Mobile Environment. In Proceedings of the SIGCHI Conference on Human Factors in Computing Systems. 2011, 11–20. URL, DOI BibTeX

    @inproceedings{Raij2011,
    	title = "Privacy Risks Emerging from the Adoption of Innocuous Wearable Sensors in the Mobile Environment",
    	author = "Raij, Andrew and Ghosh, Animikh and Kumar, Santosh and Srivastava, Mani",
    	booktitle = "Proceedings of the SIGCHI Conference on Human Factors in Computing Systems",
    	year = 2011,
    	address = "New York, NY, USA",
    	pages = "11--20",
    	publisher = "ACM",
    	series = "CHI '11",
    	abstract = "Wearable sensors are revolutionizing healthcare and science by enabling capture of physiological, psychological, and behavioral measurements in natural environments. However, these seemingly innocuous measurements can be used to infer potentially private behaviors such as stress, conversation, smoking, drinking, illicit drug usage, and others. We conducted a study to assess how concerned people are about disclosure of a variety of behaviors and contexts that are embedded in wearable sensor data. Our results show participants are most concerned about disclosures of conversation episodes and stress — inferences that are not yet widely publicized. These concerns are mediated by temporal and physical context associated with the data and the participant’s personal stake in the data. Our results provide key guidance on the extent to which people understand the potential for harm and data characteristics researchers should focus on to reduce the perceived harm from such datasets.",
    	acmid = 1978945,
    	doi = "10.1145/1978942.1978945",
    	isbn = "978-1-4503-0228-9",
    	keywords = "information disclosure, mobile health, privacy, user study, wearable sensors",
    	location = "Vancouver, BC, Canada",
    	numpages = 10,
    	timestamp = "2016.01.15",
    	url = "http://doi.acm.org/10.1145/1978942.1978945"
    }
    
  43. Christopher Olston and Benjamin Reed. Inspector Gadget: A Framework for Custom Monitoring and Debugging of Distributed Dataflows. In Proceedings of the 2011 ACM SIGMOD International Conference on Management of Data. 2011, 1221–1224. URL, DOI BibTeX

    @inproceedings{Olston2011,
    	title = "Inspector Gadget: A Framework for Custom Monitoring and Debugging of Distributed Dataflows",
    	author = "Olston, Christopher and Reed, Benjamin",
    	booktitle = "Proceedings of the 2011 ACM SIGMOD International Conference on Management of Data",
    	year = 2011,
    	address = "New York, NY, USA",
    	pages = "1221--1224",
    	publisher = "ACM",
    	series = "SIGMOD '11",
    	abstract = "We consider how to monitor and debug query processing dataflows, in distributed environments such as Pig/Hadoop. Our work is motivated by a series of informal user interviews, which revealed that monitoring and debugging needs are both pressing and diverse. In response to these interviews, we created a framework for custom dataflow instrumentation, called Inspector Gadget (IG). IG makes it easy to write a wide variety of monitoring and debugging behaviors, and attaches seamlessly to an existing, unmodified dataflow environment such as Pig. We have implemented a dozen user-requested tools in Inspector Gadget, each in just a few hundred lines of Java code. The performance overhead is modest in most cases. Our Pig-based implementation of IG, called Penny, is slated for public release in mid-2011, in conjunction with the upcoming Apache Pig v0.9 release",
    	acmid = 1989459,
    	doi = "10.1145/1989323.1989459",
    	isbn = "978-1-4503-0661-4",
    	keywords = "debugging, hadoop, instrumentation, query processing",
    	location = "Athens, Greece",
    	numpages = 4,
    	timestamp = "2016.01.15",
    	url = "http://doi.acm.org/10.1145/1989323.1989459"
    }
    
  44. Adrian Letchford, Junbin Gao and Lihong Zheng. Penalized Least Squares for Smoothing Financial Time Series. In Dianhui Wang and Mark Reynolds (eds.). AI 2011: Advances in Artificial Intelligence. Lecture Notes in Computer Science series, volume 7106, Springer Berlin Heidelberg, 2011, pages 72-81. URL, DOI BibTeX

    @incollection{Letchford2011,
    	title = "Penalized Least Squares for Smoothing Financial Time Series",
    	author = "Letchford, Adrian and Gao, Junbin and Zheng, Lihong",
    	booktitle = "AI 2011: Advances in Artificial Intelligence",
    	publisher = "Springer Berlin Heidelberg",
    	year = 2011,
    	editor = "Wang, Dianhui and Reynolds, Mark",
    	pages = "72-81",
    	series = "Lecture Notes in Computer Science",
    	volume = 7106,
    	abstract = "Modeling of financial time series data by methods of artificial intelligence is difficult because of the extremely noisy nature of the data. A common and simple form of filter to reduce the noise originated in signal processing, the finite impulse response (FIR) filter. There are several of these noise reduction methods used throughout the financial instrument trading community. The major issue with these filters is the delay between the filtered data and the noisy data. This delay only increases as more noise reduction is desired. In the present marketplace, where investors are competing for quality and timely information, this delay can be a hindrance. This paper proposes a new FIR filter derived with the aim of maximizing the level of noise reduction and minimizing the delay. The model is modified from the old problem of time series graduation by penalized least squares. Comparison between five different methods has been done and experiment results have shown that our method is significantly superior to the alternatives in both delay and smoothness over short and middle range delay periods.",
    	doi = "10.1007/978-3-642-25832-9_8",
    	isbn = "978-3-642-25831-2",
    	keywords = "Penalized least squares; Time series analysis; Financial analysis; Finite impulse response; Time series data mining",
    	language = "English",
    	timestamp = "2016.01.15",
    	url = "http://dx.doi.org/10.1007/978-3-642-25832-9_8"
    }
    
  45. Suzan Koknar-Tezel and Longin Jan Latecki. Improving SVM Classification on Imbalanced Time Series Data Sets with Ghost Points. Knowl. Inf. Syst. 28(1):1–23, 2011. URL, DOI BibTeX

    @article{Koknar-Tezel:2011:ISC:2003503.2003504,
    	title = "Improving SVM Classification on Imbalanced Time Series Data Sets with Ghost Points",
    	author = "Koknar-Tezel, Suzan and Latecki, Longin Jan",
    	journal = "Knowl. Inf. Syst.",
    	year = 2011,
    	month = "",
    	number = 1,
    	pages = "1--23",
    	volume = 28,
    	abstract = "Imbalanced data sets present a particular challenge to the data mining community. Often, it is the rare event that is of interest and the cost of misclassifying the rare event is higher than misclassifying the usual event. When the data is highly skewed toward the usual, it can be very difficult for a learning system to accurately detect the rare event. There have been many approaches in recent years for handling imbalanced data sets, from under-sampling the majority class to adding synthetic points to the minority class in feature space. However, distances between time series are known to be non-Euclidean and non-metric, since comparing time series requires warping in time. This fact makes it impossible to apply standard methods like SMOTE to insert synthetic data points in feature spaces. We present an innovative approach that augments the minority class by adding synthetic points in distance spaces. We then use Support Vector Machines for classification. Our experimental results on standard time series show that our synthetic points significantly improve the classification rate of the rare events, and in most cases also improves the overall accuracy of SVMs. We also show how adding our synthetic points can aid in the visualization of time series data sets.",
    	acmid = 2003504,
    	address = "New York, NY, USA",
    	doi = "10.1007/s10115-010-0310-3",
    	issn = "0219-1377",
    	issue_date = "July 2011",
    	keywords = "Support Vector Machines, Time series",
    	numpages = 23,
    	publisher = "Springer-Verlag New York, Inc.",
    	url = "http://link.springer.com/article/10.1007%2Fs10115-010-0310-3#/page-1"
    }
    
  46. Laetitia Comté, Stijn Vansteelandt, Richard A Rode and Bernard Vrijens. Estimation of HIV treatment-efficacy by combining structural nested mean models with pharmacokinetic models of antiretroviral drug exposure. Statistics and its interface 4(4):511–520, 2011. BibTeX

    @article{Comte2011,
    	title = "Estimation of HIV treatment-efficacy by combining structural nested mean models with pharmacokinetic models of antiretroviral drug exposure",
    	author = "Comt{\'e}, Laetitia and Vansteelandt, Stijn and Rode, Richard A and Vrijens, Bernard",
    	journal = "Statistics and its interface",
    	year = 2011,
    	number = 4,
    	pages = "511--520",
    	volume = 4,
    	abstract = "The aim of treating HIV-1-infected patients is to achieve and maintain suppression of viral load (VL). Achievement of this aim is thwarted by variable adherence to prescribed anti-retroviral drugs. Variable adherence to an antiretroviral regimen creates variability in the patient’s internal exposure to the drugs. Structural nested mean models (SNMMs) enabled us to estimate, during the initial phase of treatment, the relationship between variable internal exposure and VL, accounting for measured time-varying confounders and feedback relations using an antiretroviral regimen containing lopinavir/ritonavir (LPV/RTV, LPV/r). Our final SNMM predicts that the short term effect of treatment is modified by the most recent past VL, with higher initial VL’s being associated with larger treatment-induced reductions in VL for a given internal exposure to the drugs. Variation in internal exposure to LPV/r in the interquartile interval (P25%–P75%) only slightly affects the overall reduction in VL, supporting the conclusion that the relatively long duration of action of LPV/r lessens the impact on VL of the most frequently recurring intermittent lapses in dosing.",
    	publisher = "INT PRESS BOSTON, INC PO BOX 43502, SOMERVILLE, MA 02143 USA",
    	timestamp = "2016.01.15"
    }
    
  47. Siddharth Chandra, Deborah Scharf and Saul Shiffman. Within-day temporal patterns of smoking, withdrawal symptoms, and craving. Drug and Alcohol Dependence 117(2–3):118 - 125, 2011. URL, DOI BibTeX

    @article{Chandra2011118,
    	title = "Within-day temporal patterns of smoking, withdrawal symptoms, and craving",
    	author = "Siddharth Chandra and Deborah Scharf and Saul Shiffman",
    	journal = "Drug and Alcohol Dependence",
    	year = 2011,
    	number = "2–3",
    	pages = "118 - 125",
    	volume = 117,
    	abstract = "We examined the temporal relationships between smoking frequency and craving and withdrawal. 351 heavy smokers (≥15 cigarettes per day) used ecological momentary assessment and electronic diaries to track smoking, craving, negative affect, arousal, restlessness, and attention disturbance in real time over 16 days. The waking day was divided into 8 2-h “bins� during which cigarette counts and mean levels of craving and withdrawal were computed. Cross-sectional analyses showed no association between restlessness and smoking, and arousal and smoking, but craving (b = 0.65, p < 0.01) was positively associated, and negative affect (b = −0.20, p < 0.01), and attention disturbance (b = −0.24, p < 0.01) were inversely associated with smoking. In prospective lagged analyses, higher craving predicted more subsequent smoking and higher smoking predicted lower craving (p's < 0.01). Higher restlessness also predicted more subsequent smoking and higher smoking predicted lower restlessness (p's < 0.01). Higher negative affect did not predict later smoking, but more smoking preceded lower negative affect (p < 0.01). Neither attention disturbance nor arousal predicted, or were predicted by variations in smoking. In short, smoking exhibits time-lagged, reciprocal relationships with craving and restlessness, and a one-way predictive relationship with negative affect. Temporal patterns of craving and restlessness may aid in the design of smoking cessation interventions.",
    	doi = "http://dx.doi.org/10.1016/j.drugalcdep.2010.12.027",
    	issn = "0376-8716",
    	keywords = "Smoking",
    	url = "http://www.sciencedirect.com/science/article/pii/S0376871611000561"
    }
    
  48. Lide Zhang, B Tiwana, R P Dick, Zhiyun Qian, Z M Mao, Zhaoguang Wang and Lei Yang. Accurate online power estimation and automatic battery behavior based power model generation for smartphones. In Hardware/Software Codesign and System Synthesis (CODES+ISSS), 2010 IEEE/ACM/IFIP International Conference on. October 2010, 105-114. URL BibTeX

    @inproceedings{5751489,
    	title = "Accurate online power estimation and automatic battery behavior based power model generation for smartphones",
    	author = "Lide Zhang and Tiwana, B. and Dick, R.P. and Zhiyun Qian and Mao, Z.M. and Zhaoguang Wang and Lei Yang",
    	booktitle = "Hardware/Software Codesign and System Synthesis (CODES+ISSS), 2010 IEEE/ACM/IFIP International Conference on",
    	year = 2010,
    	month = "Oct",
    	organization = "IEEE",
    	pages = "105-114",
    	abstract = "This paper describes PowerBooter, an automated power model construction technique that uses built-in battery voltage sensors and knowledge of battery discharge behavior to monitor power consumption while explicitly controlling the power management and activity states of individual components. It requires no external measurement equipment. We also describe PowerTutor, a component power management and activity state introspection based tool that uses the model generated by PowerBooter for online power estimation. PowerBooter is intended to make it quick and easy for application developers and end users to generate power models for new smartphone variants, which each have different power consumption properties and therefore require different power models. PowerTutor is intended to ease the design and selection of power efficient software for embedded systems. Combined, PowerBooter and PowerTutor have the goal of opening power modeling and analysis for more smartphone variants and their users.",
    	keywords = "battery management systems;electric sensing devices;embedded systems;power consumption;power engineering computing;PowerBooter;automatic battery behavior;built-in battery voltage sensor;embedded system;online power estimation;power efficient software;power management;power model generation;smartphone variant;Batteries;Bluetooth;Brightness;Cameras;Global Positioning System;Ground penetrating radar;Monitoring;Power modeling;battery;mobile phones",
    	url = "http://ieeexplore.ieee.org/xpl/freeabs_all.jsp?arnumber=5751489"
    }
    
  49. B Longstaff, S Reddy and D Estrin. Improving activity classification for health applications on mobile devices using active and semi-supervised learning. In Pervasive Computing Technologies for Healthcare (PervasiveHealth), 2010 4th International Conference on-NO PERMISSIONS. March 2010, 1-7. DOI BibTeX

    @inproceedings{Longstaff2010,
    	title = "Improving activity classification for health applications on mobile devices using active and semi-supervised learning",
    	author = "Longstaff, B. and Reddy, S. and Estrin, D.",
    	booktitle = "Pervasive Computing Technologies for Healthcare (PervasiveHealth), 2010 4th International Conference on-NO PERMISSIONS",
    	year = 2010,
    	month = "March",
    	pages = "1-7",
    	abstract = "Mobile phones' increasing ubiquity has created many opportunities for personal context sensing. Personal activity is an important part of a user's context, and automatically recognizing it is vital for health and fitness monitoring applications. Recording a stream of activity data enables monitoring patients with chronic conditions affecting ambulation and motion, as well as those undergoing rehabilitation treatments. Modern mobile phones are powerful enough to perform activity classification in real time, but they typically use a static classifier that is trained in advance or require the user to manually add training data after the application is on his/her device. This paper investigates ways of automatically augmenting activity classifiers after they are deployed in an application. It compares active learning and three different semi-supervised learning methods, self-learning, En-Co-Training, and democratic co-learning, to determine which show promise for this purpose. The results show that active learning, En-Co-Training, and democratic co-learning perform well when the initial classifier's accuracy is low (75-80%). When the initial accuracy is already high (90%), these methods are no longer effective, but they do not hurt the accuracy either. Overall, active learning gave the highest improvement, but democratic co-learning was almost as good and does not require user interaction. Thus, democratic co-learning would be the best choice for most applications, since it would significantly increase the accuracy for initial classifiers that performed poorly.",
    	doi = "10.4108/ICST.PERVASIVEHEALTH2010.8851",
    	keywords = "learning (artificial intelligence);mobile computing;patient monitoring;patient rehabilitation;active learning;activity classification;democratic co-learning;en-co-training;health applications;mobile devices;patients monitoring;personal context sensing;rehabilitation treatments;semi supervised learning;Biomedical monitoring;Cardiac disease;Cardiovascular diseases;Machine learning algorithms;Mobile handsets;Patient monitoring;Semisupervised learning;Smart phones;Training data;User interfaces",
    	timestamp = "2016.01.15"
    }
    
  50. James Loughead, Riju Ray, Paul E Wileyto, Kosha Ruparel, Paul Sanborn, Steven Siegel, Ruben C Gur and Caryn Lerman. Effects of the?4?2 Partial Agonist Varenicline on Brain Activity and Working Memory in Abstinent Smokers. Biological Psychiatry 67(8):715 - 721, 2010. URL, DOI BibTeX

    @article{Loughead2010,
    	title = "Effects of the?4?2 Partial Agonist Varenicline on Brain Activity and Working Memory in Abstinent Smokers",
    	author = "James Loughead and Riju Ray and E. Paul Wileyto and Kosha Ruparel and Paul Sanborn and Steven Siegel and Ruben C. Gur and Caryn Lerman",
    	journal = "Biological Psychiatry",
    	year = 2010,
    	note = "Nicotine Effects on Dysphoric Mood",
    	number = 8,
    	pages = "715 - 721",
    	volume = 67,
    	abstract = "Background Cognitive alterations are a core symptom of nicotine withdrawal, contributing to smoking relapse. In rodents and humans, cognitive deficits can be reversed by treatment with the α4β2 nicotinic receptor partial agonist varenicline. This neuroimaging study examined the neural mechanisms that underlie these effects. Methods Twenty-two smokers completed 13 days of varenicline and placebo treatment in a double-blind crossover study with two functional magnetic resonance imaging sessions: after 3 days of abstinence while on varenicline and after 3 days of abstinence while on placebo (counterbalanced randomized order, 2-week washout). Blood oxygenation level-dependent (BOLD) data were acquired during performance of a visual N-back working memory task. Results In a region of interest analysis, significant effects of treatment on mean percent signal change (varenicline > placebo) were observed in the dorsal anterior cingulate/medial frontal cortex, left dorsolateral prefrontal cortex, and right dorsolateral prefrontal cortex. In a cross-region model, there was a significant interaction of treatment by memory load, indicating significant increases in \{BOLD\} signal for varenicline versus placebo at the 2-back and 3-back levels but not the 1-back level. Varenicline improved performance (correct response time) in highly dependent smokers with no effect among less dependent smokers. In highly dependent smokers, faster correct response time was associated with increased \{BOLD\} signal. Conclusions This study provides novel evidence that the α4β2 partial agonist varenicline increases working memory-related brain activity after 3 days of nicotine abstinence, particularly at high levels of task difficulty, with associated improvements in cognitive performance among highly dependent smokers.",
    	doi = "http://dx.doi.org/10.1016/j.biopsych.2010.01.016",
    	issn = "0006-3223",
    	keywords = "Addiction",
    	timestamp = "2016.01.15",
    	url = "http://www.sciencedirect.com/science/article/pii/S0006322310000582"
    }
    
  51. David H Epstein, Gina F Marrone, Stephen J Heishman, John Schmittner and Kenzie L Preston. Tobacco, cocaine, and heroin: Craving and use during daily life. Addictive Behaviors 35(4):318 - 324, 2010. URL, DOI BibTeX

    @article{Epstein2010,
    	title = "Tobacco, cocaine, and heroin: Craving and use during daily life",
    	author = "David H. Epstein and Gina F. Marrone and Stephen J. Heishman and John Schmittner and Kenzie L. Preston",
    	journal = "Addictive Behaviors",
    	year = 2010,
    	number = 4,
    	pages = "318 - 324",
    	volume = 35,
    	abstract = "Background Relationships among tobacco smoking, tobacco craving, and other drug use and craving may have treatment implications in polydrug-dependent individuals. Methods We conducted the first ecological momentary assessment (EMA) study to investigate how smoking is related to other drug use and craving during daily life. For up to 20 weeks, 106 methadone-maintained outpatients carried PalmPilots (PDAs). They reported their craving, mood, behaviors, environment, and cigarette-smoking status in 2 to 5 random-prompt entries/day and initiated \{PDA\} entries when they used cocaine or heroin or had a discrete episode of craving for cocaine or heroin. Results Smoking frequency increased linearly with random-prompt ratings of tobacco craving, cocaine craving, and craving for both cocaine and heroin. Smoking frequency was greater during discrete episodes of cocaine use and craving than during random-prompt reports of low craving for cocaine. This pattern was also significant for dual cocaine and heroin use and craving. Smoking and tobacco craving were each considerably reduced during periods of urine-verified abstinence from cocaine, and there was a (nonsignificant) tendency for morning smoking to be especially reduced during those periods. Conclusions This \{EMA\} study confirms that smoking and tobacco craving are strongly associated with the use of and craving for cocaine and heroin. Together with prior findings, our data suggest that tobacco and cocaine may each increase craving for (and likelihood of continued use of) themselves and each other. Treatment for tobacco dependence should probably be offered concurrently with (rather than only after) initiation of treatment for other substance-use disorders.",
    	doi = "http://dx.doi.org/10.1016/j.addbeh.2009.11.003",
    	issn = "0306-4603",
    	keywords = "Smoking",
    	timestamp = "2016.01.15",
    	url = "http://www.sciencedirect.com/science/article/pii/S0306460309003098"
    }
    
  52. Laura Balzano, Robert D Nowak and Benjamin Recht. Online Identification and Tracking of Subspaces from Highly Incomplete Information. CoRR abs/1006.4046, 2010. URL BibTeX

    @article{DBLP:journals/corr/abs-1006-4046,
    	title = "Online Identification and Tracking of Subspaces from Highly Incomplete Information",
    	author = "Laura Balzano and Robert D. Nowak and Benjamin Recht",
    	journal = "CoRR",
    	year = 2010,
    	volume = "abs/1006.4046",
    	abstract = "This work presents GROUSE (Grassmannian Rank-One Update Subspace Estimation), an efficient online algorithm for tracking subspaces from highly incomplete observations. GROUSE requires only basic linear algebraic manipulations at each iteration, and each subspace update can be performed in linear time in the dimension of the subspace. The algorithm is derived by analyzing incremental gradient descent on the Grassmannian manifold of subspaces. With a slight modification, GROUSE can also be used as an online incremental algorithm for the matrix completion problem of imputing missing entries of a low-rank matrix. GROUSE performs exceptionally well in practice both in tracking subspaces and as an online algorithm for matrix completion.",
    	bibsource = "dblp computer science bibliography, http://dblp.org",
    	biburl = "http://dblp.uni-trier.de/rec/bib/journals/corr/abs-1006-4046",
    	timestamp = "Thu, 07 May 2015 20:04:46 +0200",
    	url = "http://arxiv.org/abs/1006.4046"
    }
    
  53. Hong Lu, Wei Pan, Nicholas D Lane, Tanzeem Choudhury and Andrew T Campbell. SoundSense: Scalable Sound Sensing for People-centric Applications on Mobile Phones. In Proceedings of the 7th International Conference on Mobile Systems, Applications, and Services. 2009, 165–178. URL, DOI BibTeX

    @inproceedings{Lu2009,
    	title = "SoundSense: Scalable Sound Sensing for People-centric Applications on Mobile Phones",
    	author = "Lu, Hong and Pan, Wei and Lane, Nicholas D. and Choudhury, Tanzeem and Campbell, Andrew T.",
    	booktitle = "Proceedings of the 7th International Conference on Mobile Systems, Applications, and Services",
    	year = 2009,
    	address = "New York, NY, USA",
    	pages = "165--178",
    	publisher = "ACM",
    	series = "MobiSys '09",
    	abstract = "Top end mobile phones include a number of specialized (e.g., accelerometer, compass, GPS) and general purpose sensors (e.g., microphone, camera) that enable new people-centric sensing applications. Perhaps the most ubiquitous and unexploited sensor on mobile phones is the microphone – a powerful sensor that is capable of making sophisticated inferences about human activity, location, and social events from sound. In this paper, we exploit this untapped sensor not in the context of human communications but as an enabler of new sensing applications. We propose SoundSense, a scalable framework for modeling sound events on mobile phones. SoundSense is implemented on the Apple iPhone and represents the first general purpose sound sensing system specifically designed to work on resource limited phones. The architecture and algorithms are designed for scalability and SoundSense uses a combination of supervised and unsupervised learning techniques to classify both general sound types (e.g., music, voice) and discover novel sound events specific to individual users. The system runs solely on the mobile phone with no back-end interactions. Through implementation and evaluation of two proof of concept peoplecentric sensing applications, we demostrate that SoundSense is capable of recognizing meaningful sound events that occur in users’ everyday lives.",
    	acmid = 1555834,
    	doi = "10.1145/1555816.1555834",
    	isbn = "978-1-60558-566-6",
    	keywords = "audio processing, mobile phones, people centric sensing, sound classification, urban sensing",
    	location = "Krak\&\#243;w, Poland",
    	numpages = 14,
    	timestamp = "2016.01.15",
    	url = "http://pac.cs.cornell.edu/pubs/mobisys09_soundsense.pdf"
    }
    
  54. Sunny Consolvo, David W McDonald and James A Landay. Theory-driven Design Strategies for Technologies That Support Behavior Change in Everyday Life. In Proceedings of the SIGCHI Conference on Human Factors in Computing Systems. 2009, 405–414. URL, DOI BibTeX

    @inproceedings{Consolvo:2009:TDS:1518701.1518766,
    	title = "Theory-driven Design Strategies for Technologies That Support Behavior Change in Everyday Life",
    	author = "Consolvo, Sunny and McDonald, David W. and Landay, James A.",
    	booktitle = "Proceedings of the SIGCHI Conference on Human Factors in Computing Systems",
    	year = 2009,
    	address = "New York, NY, USA",
    	pages = "405--414",
    	publisher = "ACM",
    	series = "CHI '09",
    	abstract = "In this paper, we propose design strategies for persuasive technologies that help people who want to change their everyday behaviors. Our strategies use theory and prior work to substantially extend a set of existing design goals. Our extensions specifically account for social characteristics and other tactics that should be supported by persuasive technologies that target long-term discretionary use throughout everyday life. We used these strategies to design and build a system that encourages people to lead a physically active lifestyle. Results from two field studies of the system - a three-week trial and a three-month experiment - have shown that the system was successful at helping people maintain a more physically active lifestyle and validate the usefulness of the strategies.",
    	acmid = 1518766,
    	doi = "10.1145/1518701.1518766",
    	isbn = "978-1-60558-246-7",
    	keywords = "behavior change, design strategies, everyday life, lifestyle, mobile phone, persuasive technology, physical activity",
    	location = "Boston, MA, USA",
    	numpages = 10,
    	url = "http://doi.acm.org/10.1145/1518701.1518766"
    }
    
  55. David A Smith and Jason Eisner. Dependency Parsing by Belief Propagation. In Proceedings of the Conference on Empirical Methods in Natural Language Processing. 2008, 145–156. URL BibTeX

    @inproceedings{Smith:2008:DPB:1613715.1613737,
    	title = "Dependency Parsing by Belief Propagation",
    	author = "Smith, David A. and Eisner, Jason",
    	booktitle = "Proceedings of the Conference on Empirical Methods in Natural Language Processing",
    	year = 2008,
    	address = "Stroudsburg, PA, USA",
    	pages = "145--156",
    	publisher = "Association for Computational Linguistics",
    	series = "EMNLP '08",
    	abstract = "We formulate dependency parsing as a graphical model with the novel ingredient of global constraints. We show how to apply loopy belief propagation (BP), a simple and effective tool for approximate learning and inference. As a parsing algorithm, BP is both asymptotically and empirically efficient. Even with second-order features or latent variables, which would make exact parsing considerably slower or NP-hard, BP needs only O(n3) time with a small constant factor. Furthermore, such features significantly improve parse accuracy over exact first-order methods. Incorporating additional features would increase the runtime additively rather than multiplicatively.",
    	acmid = 1613737,
    	location = "Honolulu, Hawaii",
    	numpages = 12,
    	url = "http://dl.acm.org/citation.cfm?id=1613737"
    }
    
  56. Lin Liao, Dieter Fox and Henry Kautz. Hierarchical conditional random fields for GPS-based activity recognition. In Robotics Research. Springer, 2007, pages 487–506. URL BibTeX

    @incollection{Liao2007,
    	title = "Hierarchical conditional random fields for GPS-based activity recognition",
    	author = "Liao, Lin and Fox, Dieter and Kautz, Henry",
    	booktitle = "Robotics Research",
    	publisher = "Springer",
    	year = 2007,
    	pages = "487--506",
    	abstract = "Learning patterns of human behavior from sensor data is extremely important for high-level activity inference. We show how to extract a person’s activities and significant places from traces of GPS data. Our system uses hierarchically structured conditional random fields to generate a consistent model of a person’s activities and places. In contrast to existing techniques, our approach takes high-level context into account in order to detect the significant locations of a person. Our experiments show significant improvements over existing techniques. Furthermore, they indicate that our system is able to robustly estimate a person’s activities using a model that is trained from data collected by other persons.",
    	timestamp = "2016.01.15",
    	url = "http://mobilerobotics.cs.washington.edu/postscripts/places-isrr-05.pdf"
    }
    
  57. Zutao Zhang and Jiashu Zhang. A New Real-Time Eye Tracking for Driver Fatigue Detection. In ITS Telecommunications Proceedings, 2006 6th International Conference on. June 2006, 8-11. DOI BibTeX

    @inproceedings{4068517,
    	title = "A New Real-Time Eye Tracking for Driver Fatigue Detection",
    	author = "Zutao Zhang and Jiashu Zhang",
    	booktitle = "ITS Telecommunications Proceedings, 2006 6th International Conference on",
    	year = 2006,
    	month = "June",
    	pages = "8-11",
    	abstract = "Driver fatigue is one of the important factors that cause traffic accidents. The vision-based facial expression recognition technique is the most prospective method to detect driver fatigue. In this paper, we present a new driver fatigue detection based on unscented Kalman filter and eye tracking in this paper. The face is located using Haar algorithm firstly, which has good robustness in terms of head motions, variable lighting conditions, the change of hair and having glasses, etc. Secondly, the geometric properties and projection technique are used for eye location. Thirdly, we propose a new real time eye tracking method based on unscented Kalman Filter. Finally, driver fatigue can be detected whether the eyes are closed over 5 consecutive frames using vertical projection matching. The experimental results show validity of our method for driver fatigue detection under variable realistic conditions",
    	doi = "10.1109/ITST.2006.288748",
    	keywords = "Kalman filters;accident prevention;computer vision;eye;face recognition;feature extraction;image matching;image motion analysis;image texture;road accidents;tracking filters;Haar algorithm;driver fatigue detection;facial expression recognition technique;geometric properties;hair change;head motion;real-time eye tracking;traffic accident;unscented Kalman filter;variable lighting condition;vertical projection matching;vision-based technique;Change detection algorithms;Eyes;Face detection;Face recognition;Fatigue;Glass;Hair;Road accidents;Robustness;Target tracking"
    }
    
  58. Rogier A T Donders, Geert J M G Heijden, Theo Stijnen and Karel G M Moons. Review: A gentle introduction to imputation of missing values. Journal of Clinical Epidemiology 59(10):1087 - 1091, 2006. URL, DOI BibTeX

    @article{Donders2006,
    	title = "Review: A gentle introduction to imputation of missing values",
    	author = "A. Rogier T. Donders and Geert J.M.G. van der Heijden and Theo Stijnen and Karel G.M. Moons",
    	journal = "Journal of Clinical Epidemiology",
    	year = 2006,
    	number = 10,
    	pages = "1087 - 1091",
    	volume = 59,
    	abstract = "In most situations, simple techniques for handling missing data (such as complete case analysis, overall mean imputation, and the missing-indicator method) produce biased results, whereas imputation techniques yield valid results without complicating the analysis once the imputations are carried out. Imputation techniques are based on the idea that any subject in a study sample can be replaced by a new randomly chosen subject from the same source population. Imputation of missing data on a variable is replacing that missing by a value that is drawn from an estimate of the distribution of this variable. In single imputation, only one estimate is used. In multiple imputation, various estimates are used, reflecting the uncertainty in the estimation of this distribution. Under the general conditions of so-called missing at random and missing completely at random, both single and multiple imputations result in unbiased estimates of study associations. But single imputation results in too small estimated standard errors, whereas multiple imputation results in correctly estimated standard errors and confidence intervals. In this article we explain why all this is the case, and use a simple simulation study to demonstrate our explanations. We also explain and illustrate why two frequently used methods to handle missing data, i.e., overall mean imputation and the missing-indicator method, almost always result in biased estimates.",
    	doi = "http://dx.doi.org/10.1016/j.jclinepi.2006.01.014",
    	issn = "0895-4356",
    	keywords = "Missing data",
    	timestamp = "2016.01.15",
    	url = "http://www.sciencedirect.com/science/article/pii/S0895435606001971"
    }
    
  59. Nitin Kumar Venkata Nishanth Lolla Eamonn, Keogh Stefano Lonardi Chotirat Ann Ratanamahatana and Li Wei. Time-series bitmaps: a practical visualization tool for working with large time series databases. , 2005. URL BibTeX

    @article{Eamonn2005,
    	title = "Time-series bitmaps: a practical visualization tool for working with large time series databases",
    	author = "Eamonn, Nitin Kumar Venkata Nishanth Lolla and Ratanamahatana, Keogh Stefano Lonardi Chotirat Ann and Wei, Li",
    	year = 2005,
    	abstract = "The increasing interest in time series data mining in the last decade has resulted in the introduction of a variety of similarity measures, representations, and algorithms. Surprisingly, this massive research effort has had little impact on real world applications. Real world practitioners who work with time series on a daily basis rarely take advantage of the wealth of tools that the data mining community has made available. In this work, we attempt to address this problem by introducing a simple parameter-light tool that allows users to efficiently navigate through large collections of time series. Our system has the unique advantage that it can be embedded directly into any standard graphical user interfaces, such as Microsoft Windows, thus making deployment easier. Our approach extracts features from a time series of arbitrary length and uses information about the relative frequency of its features to color a bitmap in a principled way. By visualizing the similarities and differences within a collection of bitmaps, a user can quickly discover clusters, anomalies, and other regularities within their data collection. We demonstrate the utility of our approach with a set of comprehensive experiments on real datasets from a variety of domains.",
    	publisher = "SIAM",
    	timestamp = "2016.01.15",
    	url = "http://alumni.cs.ucr.edu/~nkumar/My_Papers/bitmap_SDM.pdf"
    }
    
  60. J W Fisher and T Darrell. Speaker association with signal-level audiovisual fusion. Multimedia, IEEE Transactions on 6(3):406-413, June 2004. URL, DOI BibTeX

    @article{Fisher2004,
    	title = "Speaker association with signal-level audiovisual fusion",
    	author = "Fisher, J.W. and Darrell, T.",
    	journal = "Multimedia, IEEE Transactions on",
    	year = 2004,
    	month = "June",
    	number = 3,
    	pages = "406-413",
    	volume = 6,
    	abstract = "Audio and visual signals arriving from a common source are detected using a signal-level fusion technique. A probabilistic multimodal generation model is introduced and used to derive an information theoretic measure of cross-modal correspondence. Nonparametric statistical density modeling techniques can characterize the mutual information between signals from different domains. By comparing the mutual information between different pairs of signals, it is possible to identify which person is speaking a given utterance and discount errant motion or audio from other utterances or nonspeech events.",
    	doi = "10.1109/TMM.2004.827503",
    	issn = "1520-9210",
    	keywords = "audio signal processing;image sequences;interactive systems;probability;speech recognition;statistical analysis;video signal processing;audio signals;cross-modal correspondence;discount errant motion;mutual information theoretic measure;nonparametric statistical density modeling techniques;nonspeech events;probabilistic multimodal generation model;signal-level audiovisual fusion;speaker data association;visual signals;Computer science;Databases;Fusion power generation;Microphones;Mutual information;Signal detection;Signal processing;Speech recognition;Telephone sets;Telephony;Audiovisual correspondence;multimodal data association;mutual information",
    	timestamp = "2016.01.15",
    	url = "http://people.csail.mit.edu/fisher/publications/papers/fisher04tmm.pdf"
    }
    
  61. Huanmei Wu, Gregory C Sharp, Betty Salzberg, David Kaeli, Hiroki Shirato and Steve B Jiang. A finite state model for respiratory motion analysis in image guided radiation therapy. Physics in Medicine and Biology 49(23):5357, 2004. URL BibTeX

    @article{Wu2004,
    	title = "A finite state model for respiratory motion analysis in image guided radiation therapy",
    	author = "Huanmei Wu and Gregory C Sharp and Betty Salzberg and David Kaeli and Hiroki Shirato and Steve B Jiang",
    	journal = "Physics in Medicine and Biology",
    	year = 2004,
    	number = 23,
    	pages = 5357,
    	volume = 49,
    	abstract = "Effective image guided radiation treatment of a moving tumour requires adequate information on respiratory motion characteristics. For margin expansion, beam tracking and respiratory gating, the tumour motion must be quantified for pretreatment planning and monitored on-line. We propose a finite state model for respiratory motion analysis that captures our natural understanding of breathing stages. In this model, a regular breathing cycle is represented by three line segments, exhale, end-of-exhale and inhale, while abnormal breathing is represented by an irregular breathing state. In addition, we describe an on-line implementation of this model in one dimension. We found this model can accurately characterize a wide variety of patient breathing patterns. This model was used to describe the respiratory motion for 23 patients with peak-to-peak motion greater than 7 mm. The average root mean square error over all patients was less than 1 mm and no patient has an error worse than 1.5 mm. Our model provides a convenient tool to quantify respiratory motion characteristics, such as patterns of frequency changes and amplitude changes, and can be applied to internal or external motion, including internal tumour position, abdominal surface, diaphragm, spirometry and other surrogates.",
    	timestamp = "2016.01.15",
    	url = "http://www.lugarenergycenter.org/~hw9/publications/Wu04PMB.pdf"
    }
    
  62. JamesM. Robins. Optimal Structural Nested Models for Optimal Sequential Decisions. In D Y Lin and P J Heagerty (eds.). Proceedings of the Second Seattle Symposium in Biostatistics. Lecture Notes in Statistics series, volume 179, Springer New York, 2004, pages 189-326. URL, DOI BibTeX

    @incollection{Robins2004,
    	title = "Optimal Structural Nested Models for Optimal Sequential Decisions",
    	author = "Robins, JamesM.",
    	booktitle = "Proceedings of the Second Seattle Symposium in Biostatistics",
    	publisher = "Springer New York",
    	year = 2004,
    	editor = "Lin, D.Y. and Heagerty, P.J.",
    	pages = "189-326",
    	series = "Lecture Notes in Statistics",
    	volume = 179,
    	abstract = "I describe two new methods for estimating the optimal treatment regime (equivalently, protocol, plan or strategy) from very high dimesional observational and experimental data: (i) g-estimation of an optimal double-regime structural nested mean model (drSNMM) and (ii) g-estimation of a standard single regime SNMM combined with sequential dynamic-programming (DP) regression. These methods are compared to certain regression methods found in the sequential decision and reinforcement learning literatures and to the regret modelling methods of Murphy (2003). I consider both Bayesian and frequentist inference. In particular, I propose a novel “Bayes-frequentist compromise” that combines honest subjective non- or semiparametric Bayesian inference with good frequentist behavior, even in cases where the model is so large and the likelihood function so complex that standard (uncompromised) Bayes procedures have poor frequentist performance.",
    	doi = "10.1007/978-1-4419-9076-1_11",
    	isbn = "978-0-387-20862-6",
    	language = "English",
    	timestamp = "2016.01.15",
    	url = "http://dx.doi.org/10.1007/978-1-4419-9076-1_11"
    }
    
  63. Jessica Lin, Eamonn Keogh, Stefano Lonardi, Jeffrey P Lankford and Donna M Nystrom. Visually Mining and Monitoring Massive Time Series. In Proceedings of the Tenth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. 2004, 460–469. URL, DOI BibTeX

    @inproceedings{Lin2004,
    	title = "Visually Mining and Monitoring Massive Time Series",
    	author = "Lin, Jessica and Keogh, Eamonn and Lonardi, Stefano and Lankford, Jeffrey P. and Nystrom, Donna M.",
    	booktitle = "Proceedings of the Tenth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining",
    	year = 2004,
    	address = "New York, NY, USA",
    	pages = "460--469",
    	publisher = "ACM",
    	series = "KDD '04",
    	abstract = "Moments before the launch of every space vehicle, engineering discipline specialists must make a critical go/no-go decision. The cost of a false positive, allowing a launch in spite of a fault, or a false negative, stopping a potentially successful launch, can be measured in the tens of millions of dollars, not including the cost in morale and other more intangible detriments. The Aerospace Corporation is responsible for providing engineering assessments critical to the go/no-go decision for every Department of Defense space vehicle. These assessments are made by constantly monitoring streaming telemetry data in the hours before launch. We will introduce VizTree, a novel time-series visualization tool to aid the Aerospace analysts who must make these engineering assessments. VizTree was developed at the University of California, Riverside and is unique in that the same tool is used for mining archival data and monitoring incoming live telemetry. The use of a single tool for both aspects of the task allows a natural and intuitive transfer of mined knowledge to the monitoring task. Our visualization approach works by transforming the time series into a symbolic representation, and encoding the data in a modified suffix tree in which the frequency and other properties of patterns are mapped onto colors and other visual properties. We demonstrate the utility of our system by comparing it with state-of-the-art batch algorithms on several real and synthetic datasets.",
    	acmid = 1014104,
    	doi = "10.1145/1014052.1014104",
    	isbn = "1-58113-888-1",
    	keywords = "anomaly detection, motif discovery, pattern discovery, time series, visualization",
    	location = "Seattle, WA, USA",
    	numpages = 10,
    	timestamp = "2016.01.15",
    	url = "http://cs.gmu.edu/~jessica/KDD04_VizTree.pdf"
    }
    
  64. M P Tarvainen, P O Ranta-aho and P A Karjalainen. An advanced detrending method with application to HRV analysis. Biomedical Engineering, IEEE Transactions on 49(2):172-175, February 2002. URL, DOI BibTeX

    @article{Tarvainen2002,
    	title = "An advanced detrending method with application to HRV analysis",
    	author = "Tarvainen, M.P. and Ranta-aho, P.O. and Karjalainen, P.A.",
    	journal = "Biomedical Engineering, IEEE Transactions on",
    	year = 2002,
    	month = "Feb",
    	number = 2,
    	pages = "172-175",
    	volume = 49,
    	abstract = "An advanced, simple to use, detrending method to be used before heart rate variability analysis (HRV) is presented. The method is based on smoothness priors approach and operates like a time-varying finite-impulse response high-pass filter. The effect of the detrending on time- and frequency-domain analysis of HRV is studied.",
    	doi = "10.1109/10.979357",
    	issn = "0018-9294",
    	keywords = "electrocardiography;frequency-domain analysis;least squares approximations;medical signal processing;signal sampling;smoothing methods;spectral analysis;time series;time-domain analysis;ECG sampling;RR interval data;advanced detrending method;autonomic nervous system activity;frequency-domain analysis;heart rate variability analysis;mean-squared differences;power spectrum estimate;regularized least squares solution;respiratory sinus arrhythmia quantification;signal detrending;smoothness priors approach;spectral analysis;time series;time-domain analysis;time-varying FIR high-pass filter;Autonomic nervous system;Detectors;Electrocardiography;Filters;Frequency domain analysis;Frequency estimation;Heart rate variability;Physics;Power distribution;Spectral analysis;Algorithms;Electrocardiography;Fourier Analysis;Heart Rate;Humans;Models, Cardiovascular;Nonlinear Dynamics;Signal Processing, Computer-Assisted;Stochastic Processes",
    	timestamp = "2016.01.15",
    	url = "http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=979357"
    }
    
  65. Thomas G Dietterich. Machine Learning for Sequential Data: A Review. In Proceedings of the Joint IAPR International Workshop on Structural, Syntactic, and Statistical Pattern Recognition. 2002, 15–30. URL BibTeX

    @inproceedings{Dietterich:2002:MLS:645890.671269,
    	title = "Machine Learning for Sequential Data: A Review",
    	author = "Dietterich, Thomas G.",
    	booktitle = "Proceedings of the Joint IAPR International Workshop on Structural, Syntactic, and Statistical Pattern Recognition",
    	year = 2002,
    	address = "London, UK, UK",
    	pages = "15--30",
    	publisher = "Springer-Verlag",
    	abstract = "Statistical learning problems in many fields involve sequential data. This paper formalizes the principal learning tasks and describes the methods that have been developed within the machine learning research community for addressing these problems. These methods include sliding window methods, recurrent sliding windows, hidden Markov models, conditional random fields, and graph transformer networks. The paper also discusses some open research issues.",
    	acmid = 671269,
    	isbn = "3-540-44011-9",
    	numpages = 16,
    	url = "http://dl.acm.org/citation.cfm?id=645890.671269"
    }
    
  66. JamesM. Robins. Causal Inference from Complex Longitudinal Data. In Maia Berkane (ed.). Latent Variable Modeling and Applications to Causality. Lecture Notes in Statistics series, volume 120, Springer New York, 1997, pages 69-117. URL, DOI BibTeX

    @incollection{Robins1997,
    	title = "Causal Inference from Complex Longitudinal Data",
    	author = "Robins, JamesM.",
    	booktitle = "Latent Variable Modeling and Applications to Causality",
    	publisher = "Springer New York",
    	year = 1997,
    	editor = "Berkane, Maia",
    	pages = "69-117",
    	series = "Lecture Notes in Statistics",
    	volume = 120,
    	doi = "10.1007/978-1-4612-1842-5_4",
    	isbn = "978-0-387-94917-8",
    	language = "English",
    	timestamp = "2016.01.15",
    	url = "http://dx.doi.org/10.1007/978-1-4612-1842-5_4"
    }
    
  67. Jeffrey M Drazen. Data Sharing and the Journal. New England Journal of Medicine 0(0):null, 0. URL, DOI BibTeX

    @article{Drazen0,
    	title = "Data Sharing and the Journal",
    	author = "Drazen, Jeffrey M.",
    	journal = "New England Journal of Medicine",
    	year = 0,
    	note = "PMID: 26808582",
    	number = 0,
    	pages = "null",
    	volume = 0,
    	__markedentry = "[:]",
    	doi = "10.1056/NEJMe1601087",
    	eprint = "http://dx.doi.org/10.1056/NEJMe1601087",
    	timestamp = "2016.02.10",
    	url = "http://dx.doi.org/10.1056/NEJMe1601087"
    }