Mashfiqui Rabbi

PhD Candidate
Information Science
Cornell University

Some words about me

I am a PhD student in the Information Science Department at Cornell University. I work in the people aware computing lab under Professor Tanzeem Choudhury.

I have a keen interest in building mobile systems that can reason about its user's well-being and subsequently influence the user's behavior for healthier life. My systems does so by first understanding a user's behavior from phone logs. Then my systems use machine leanring to suggest actions that relate to user's behavior so that they are acheievable.

I have more details below in my projects section. Please check them out.

My Projects


Modern fitness devices and apps can keep track of fine-grained personal health information. However, nearly all of them just provide step counts or visualizes the whole data. None of the tecnlogies do anything significant with the data to promote healthier lifestyle. MyBehavior changes all of that and it is world's first automated health feedback agent. It can understand a user's dietary intake and physical activity routine, and tell users what to do for a healthier lifestyle.

Check out paper from JMIR and Ubicomp 2015 for more details of the project.

See how MyBehavior app works


MyPersonalCoach is similar to the MyBehavior project, with an important addon - MyBehavior suggestions are pushed in the right time and context to a smartwatch to make user's active.

The suggestions in the right moment promote two kinds of action (i) repetition of same action to promote habit building (ii) novel or opportunisitic action to make user's active instantly.


FoodNinja is a fun mobile game to learn about daily foods. A user simply compares two foods and decide which food is more calorie intensive. Such simple comparison cognitively engages the users to actively think about food. We hypothesize that thinking about foods in the game may later influence the user to make better food choices in real life.


My research work involves a lot of system building that involves sesning, machine learning and signal processing. Often much of these codes are reusable for other research projects. SAINT is my effort to put all these codes together in an open-source project. Much of SAINT works are in progress. We have a workable prototype that can recognize activity, speech, common user locations and stress. If you want early access to SAINT then please send me an email.


BeWell is an old work, but I am still very proud to be once involved in BeWell. The BeWell app continuously tracks user behaviors along three key health dimensions without requiring any user input. Classification algorithms run directly on the phone to automatically infer the user's sleep duration, physical activity, and social interaction . BeWell also promotes improved behavioral patterns via persuasive feedback as part of an animated aquatic ecosystem rendered as an ambient display on the smartphone's wallpaper screen.

Check out the BeWell video.

My Publications

Refereed conference and journal publications

  1. Mashfiqui Rabbi, Jean Costa, Fabian Okeke, Max Schachere, Mi Zhang, and Tanzeem Choudhury. An Intelligent Crowd-worker Selection Approach for Reliable Content Labeling of Food Images. The Proceedings of Wireless Health 2015.

  2. Mashfiqui Rabbi, Min Hane Aung, Mi Zhang and Tanzeem Choudhury. MyBehavior: Automatic Personalized Health Feedback from User Behavior and Preference using Smartphones. The 2015 ACM International Joint Conference on Pervasive and Ubiquitous Computing (Ubicomp 2015).

  3. Mashfiqui Rabbi, Angela Pfammatter, Mi Zhang, Bonnie Spring, and Tanzeem Choudhury. Automated Personalized Feedback for Physical Activity and Dietary Behavior Change With Mobile Phones: A Randomized Controlled Trial on Adults. JMIR mHealth uHealth 2015;3(2):e42 [Impact factor 4.7]

  4. Phil Adams, Mashfiqui Rabbi, Tauhidur Rahman, Mark Matthews, Amy Voida, Geri Gay, Tanzeem Choudhury, and, Stephen Voida. Towards Personal Stress Informatics: Comparing Minimally Invasive Techniques for Measuring Daily Stress in the Wild. International Conference on Pervasive Computing Technologies for Healthcare, 2014.

  5. Nicholas D. Lane, Mu Lin, Mashfiqui Rabbi, Xiaochao Yang, Hong Lu, Giuseppe Cardone, Shahid Ali, Ethan Berke, Andrew T. Campbell, Tanzeem Choudhury Bewell: Sensing sleep, physical activities and social interactions to promote wellbeing. Mobile Networks and Applications 19, no. 3 (2014): 345-359.

  6. Mu Lin, Nicholas Lane, Mashfiqui Rabbi, Xiaochao Yang, Hong Lu, Giuseppe Cardone, Shahid Ali, Afsaneh Doryab, Ethan Berke, Andrew Campbell, and Tanzeem Choudhury. BeWell+: Multi-dimensional Wellbeing Monitoring with Community-guided User Feedback and Energy Optimization Appears in the Proceedings of Wireless Health 2012, October 2012.

  7. Hong Lu, Mashfiqui Rabbi, Gokul Chittaranjan, Denise Frauendorfer, Marianne Schmidt, Andrew Campbell, Daneil Gatica-Perez, and Tanzeem Choudhury. StressSense: Detecting Stress in Unconstrained Acoustic Environments using Smartphones. Appears in the Proceedings of Ubicomp 2012, September 2012.

  8. Mashfiqui Rabbi, Shahid Ali, Tanzeem Choudhury, and Ethan Berke. Passive and In-situ Assessment of Mental and Physical Well-being using Mobile Sensors. To appear in the Proceedings of Ubicomp 2011, September 2011. Beijing, China.

  9. Ethan Berke, Tanzeem Choudhury, Shahid Ali, and Mashfiqui Rabbi. Objective Sensing of Activity and Sociability: Mobile Sensing in the Community. Appears in the Annals of Family Medicine, Volume 9, Issue 4, Pages 344-350, July 2011. [commentary]

  10. Nicholas D. Lane, Mashfiqui Rabbi, Mu Lin, Xiaochao Yang, Afsaneh Doryab, Hong Lu, Shahid Ali, Tanzeem Choudhury, Andrew Campbell, and Ethan Berke, BeWell: A Smartphone Application to Monitor, Model and Promote Wellbeing, Pervasive Health 2011-- 5th International ICST Conference on Pervasive Computing Technologies for Healthcare, Dublin, 23-26 May 2011

  11. Andrew T. Campbell, Tanzeem Choudhury, Shaohan Hu, Hong Lu, Matthew Mukerjee, Mashfiqui Rabbi, and Rajeev Raizada. NeuroPhone: Brain-Mobile Phone Interface using a Wireless EEG Headset. Appears in the Proceedings of MobiHeld 2010.

  12. M Jawaherul Alam, Md Abul Hassan Samee, Mashfiqui Rabbi, and Md Saidur Rahman. Minimum-Layer Upward Drawings of Trees. J. Graph Algorithms and Applications 14, no. 2 (2010): 245-267.

  13. M Jawaherul Alam, Mashfiqui Rabbi, and Md Saidur Rahman. Upright Drawings of Planar Graphs on Three Layers. Journal of Applied Mathematics and Informatics, 28(56): 1347-1358, 2010

Lightly reviewed posters and workshop papers

  1. Mashfiqui Rabbi, Thiago Caetano, Jean Costa, Saeed Abdullah, Mi Zhang, and Tanzeem Choudhury. SAINT: A Scalable Sensing and Inference Toolkit. Hotmobile 2015 poster

  2. Mashfiqui Rabbi, Syed Ishtiaque Ahmed. Sensing stress network for social coping CSCW Interactive Poster Session, 2014

  3. Steven Voida, Mark Matthews, Saeed Abdullah, Mengxi C. Chi, Mattew Green, W. J. Jang, D. Hu, Jon Weinrich, P. Patil, Mashfiqui Rabbi, et al. Moodrhythm: tracking and supporting daily rhythms.In Proceedings of the 2013 ACM conference on Pervasive and ubiquitous computing adjunct publication, pages 67-70. ACM, 2013

  4. Stephen Voida, Tanzeem Choudhury, Geri Gay, Mark Matthews, Phil Adams, Mashfiqui Rabbi, JP Pollak, Mengxi Chi, Matthew Green, Andrew Campbell, Nic Lane, and Hong Lu. Personal Informatics Can Be Stressful: Collecting, Reflecting, and Embedding Stress Data in Personal Informatics. To Appear in the Proceeding of Personal Informatics Workshop, CHI.

  5. Mashfiqui Rabbi, Chien wen Yuan, and Kirsikka Kaipaien. An exploratory study to identify opportune moments in everyday life to promote healthy eating.Poster in ISBNPA, 2013