Publications: rConverse paper, accepted to ACM UbiComp 2018 (IMWUT), shows that speech can be detected from respiration with same accuracy as high-quality audio. 

Scientific Boards: NSF Engineering Research Center (ASSIST); NIH PRISMS Program; NIH Center for Technology and Behavioral Health (at Dartmouth).

Grants: Fall'17: An R01 and an R24 were awarded by NIH; Summer'17: A $13.8 million project from IARPA called mPerf to monitor and predict work performance using mobile sensors; Fall'16: A $4 million project (called mProv) from NSF (2016-21) to develop a metadata cyberinfrastructure to facilitate sharing of mobile sensor data for third party research; Fall'14: A $10.8 million project (called MD2K) from NIH (2014-18) to develop mobile sensor big data methods and tools to advance mobile health (mHealth).

Accolades: Holder of first Chair of Excellence in Computer Science (2015); Director of NIH Big Data Center of Excellence (2014); Distinguished Research Award (2013); Distinguished Research Award from College of Arts and Sciences (2012); Faudree Professorship (2011); Selected by the Popular Science magazine as one of America's  "Brilliant Ten" young scientists in 2010.

Recent Videos

• MD2K Webinar (1/2016) on Smoking Detection with puffMarker
• mHealth Training Institute Lectures (8/2015) - Wearable Wireless Sensors and Working with Other Disciplines
• NIH Webinar (5/2014) on Behavioral Assessment with Mobile Sensors
• Five minute introduction to AutoSense (prepared for White House release on 9/16/13)

Research Summary

Our current work (supported by NIH Center of Excellence for Mobile Sensor Data-to-Knowledge(MD2K)), several R01s and U01 from NIH, a contract from IARPA, and several grants from NSF seeks to define new frontiers in the newly emerging discipline of mobile health (mHealth). Our decade-long work has involved collecting mobile sensor data from 2,000+ human volunteers for 300,000+ hours in their natural environments as part of various scientific field studies. From these real-life sensor measurements, we have developed robust models to detect several important biomarkers from mobile sensor data. They incliude estimating stress and craving (from physiological sensor data), and detecting smoking (from smartwatch and respiration data), cocaine use (from heart rate data), and conversation (from respiration data). 

We are working on discovering patterns in time series of biomarkers to determine triggers for delivering just-in-time mobile interventions. See ACM UbiComp'14 work and ACM CHI'16 work. In addition, we have developed methods to ensure behavioral privacy. See ACM CHI'11 work and ACM UbiComp'16 work. 

Our research involves more than twenty faculty members from nineteen institutions (Cornell, Cornell Tech, Dartmouth, Georgia Tech, Harvard, Johns Hopkins, NIDA Intramural Research, Northwestern, Michigan, Ohio State, Rice, UCLA, UCSD, UCSF, UMass Amherst, UPenn, University of Minnesota, Utah, and West Virginia). Our collaborators span a variety of disciplines (e.g., Computer Science, Electrical Engineering, Mathematics, Statistics, Psychology, Behavioral Science, Cardiology, Physiology, Public Health, etc.), making our projects highly transdisciplinary.

Our prior work led the foundation for coverage and connectivity in wireless sensor networks. We introduced two new models of coverage, Barrier Coverage (for intrusion detection) and Trap Coverage (for scalable tracking with provable guarantees). With our esteemed Mathematician colleagues (Bela Bollobas and Paul Balister), we introduced an analytical technique for deriving reliable estimates for probabilistic events, obviating the need to insist on large network size to make probabilistic guarantess (as is traditionally done in making "with high probability" claims). We applied this technique to derive reliable estimates of density to achieve barrier coverage, full coverage, connectivity, and trap coverage, demonstrating its wide applicability. Our work on trap coverage explained the entire continuum between percolation and full coverage.

In an earlier systems work, we developed the AutoWitness burglar tracking system to help law enforcement agencies in recovering stolen assets. AutoWitness can detect burglary without an explicit report from the owner, instantly notify law enforcement agency, and most importantly, provide real-time updates on the current location of assets while en-route, maximizing the chances of timely recovery. 

Selected Recent Publications (Citations: 4,500+)

• R. Bari, R. J. Adams, M. Rahman, M. Parsons, E. Buder, and S. Kumar, "rConverse: Moment by Moment Conversation Detection Using A Mobile Respiration Sensor," In Proceedings of ACM IMWUT (to appear in ACM UbiComp 2018). (.pdf)

• S. M. Hossain, T. Hnat, N. Saleheen, N. J. Nasrin, J. Noor, B.-J. Ho, T. Condie, M. Srivastava, and S. Kumar, "mCerebrum: A Mobile Sensing Software Platform for Development and Validation of Digital Biomarkers and Interventions," ACM SenSys, 2017. (14 pages) (.pdf)

• N. Saleheen, S. Chakraborty, et. al., "mSieve: Differential Behavioral Privacy in Time Series of Mobile Sensor Data," ACM UbiComp, 2016. (12 pages) (.pdf)

• S. Chatterjee, K. Hovsepian, et. al. mCrave: Continuous Estimation of Craving During Smoking Cessation, ACM UbiComp, 2016.(12 pages) (.pdf)

• R. J. Adams, N. Saleheen, E. Thomaz, A. Parate, S. Kumar, and B. Marlin, "Hierarchican Span-Based Conditional Random Fields for Labeling and Segmenting Events in Wearable Sensor Data Streams," ICML, pp. 334-343, 2016. (.pdf)

• D. Kotz, C. A. Gunter, S. Kumar, and J. Weiner. Privacy and Security in Mobile Health: A Research Agenda," IEEE Computer, 49(6), pp. 22-30, 2016. (.pdf)

• H. Sarker, M. Tyburski, M. Rahman, et. al., "Finding Significant Stress Episodes in a Discontinuous Time Series of Rapidly Varying Mobile Sensor Data," ACM CHI, pp. 4489-4501, 2016. (.pdf)

• S. Kumar, G. D. Abowd, W. T. Abraham, et. al., "Center of excellence for mobile sensor Data-to-Knowledge (MD2K)," Journal of the American Medical Informatics Association, 22(6), pp. 1137-1142, 2015. (.pdf)

• N. Saleheen, A. A. Ali, et. al., "puffMarker: A Multi-sensor Approach for Pinpointing the Timing of First Lapse in Smoking Cessation," ACM UbiComp, pp. 999-1010, 2015. (.pdf)

• K. Hovsepian, M. al’Absi, E. Ertin, T. Kamarck, M. Nakajima, and S. Kumar, "cStress: Towards a Gold Standard for Continuous Stress Assessment in the Mobile Environment," ACM UbiComp, pp. 493-504, 2015. (.pdf)

• M. Sharmin, A. Raij, et. al., "Visualization of Time-Series Sensor Data to Inform the Design of Just-In-Time Adaptive Stress Interventions," ACM UbiComp, pp. 505-516, 2015.(.pdf)

• H. Sarker, M. Sharmin, et. al., "Assessing the Availability of Users to Engage in Just-in-Time Intervention in the Natural Environment," ACM UbiComp, pp.909-920, 2014. (.pdf)

• M. Hossain, A. Ali, et. al., "Identifying Drug (Cocaine) Intake Events from Acute Physiological Response in the Presence of Free-living Physical Activity," ACM/IEEE IPSN, pp. 71-82, 2014. (.pdf)

• M. Rahman, R. Bari, et. al. “Are We There Yet? Feasibility of ContinuousStress Assessment via Wireless Physiological Sensors,” ACM BCB, pp. 479-488, 2014. ( .pdf) 
  

• S. Vhaduri, A. Ali, M. Sharmin, K. Hovsepian, and S. Kumar. “Estimating Drivers’ Stress from GPS Traces,” Automotive UI, pp. 1-8, 2014. (.pdf)

• S. Kumar, W. Nilsen, et. al. “mHealth Evidence Workshop - Exploring Innovative Methods to Evaluate the Efficacy and Safety of Mobile Health,” American Journal of Preventive Medicine, 45(2):228-236, Oct 2013. (9 pages) 

• S. Kumar, W. Nilsen, M. Pavel, and M.B. Srivastava, "Mobile Health: Revolutionizing Healthcare Through Transdisciplinary Research," IEEE Computer, Cover Feature, 46(1): 28-35, Jan 2013. (8 pages) 

• A. Ali, M. Hossain, K. Hovsepian, M. Rahman, K. Plarre, and S. Kumar, "mPuff: Automated Detection of Cigarette Smoking Puffs from Respiration Measurements," ACM/IEEE IPSN, pp. 269-280, 2012. (.pdf, slides)

• E. Ertin, N. Stohs, S. Kumar, et. al. "AutoSense: Unobtrusively Wearable Sensor Suite for Inferencing of Onset, Causality, and Consequences of Stress in the Field," ACM SenSys, pp. 274-287, 2011. (.pdf) 
  

• M. Rahman, A. Ali, K. Plarre, M. al'Absi, E. Ertin, and S. Kumar, "mConverse: Inferring Conversation Episodes from Respiratory Measurements Collected in the Field," ACM Wireless Health, 2011. (10 pages) (.pdf)  Nominated for Best Paper Award

• M. Mustang, A. Raij, D. Ganesan, S. Kumar and S. Shiffman, "Exploring Micro-Incentive Strategies for Participant Compensation in High Burden Studies," ACM UbiComp, pp. 435-444, 2011. (.pdf) 

• K. Plarre, A. Raij, et. al., "Continuous Inference of Psychological Stress from Sensory Measurements Collected in the Natural Environment," ACM/IEEE IPSN, pp.97-108, 2011. (12 pages) (.pdf, slides) Nominated for Best Paper Award

• A. Raij, A. Ghosh, S. Kumar and M.B. Srivastava, "Privacy Risks Emerging from the Adoption of Inoccuous Wearable Sensors in the Mobile Environment," ACM CHI, pp. 11-20, 2011. (.pdf) (Acceptance Rate = 24%). 

• S. Guha, K. Plarre, D. Lissner, S. Mitra, B. Krishna, P. Dutta, and S. Kumar, "AutoWitness: Locating and Tracking Stolen Property While Tolerating GPS and Radio Outages," ACM SenSys, pp. 29-42, 2010. (.pdf, slides) Nominated for Best Paper Award

• List of All Publications