Workshop on Physical Analytics (June 16, 2014)

Workshop Program


9:00-9:10: Opening Remarks, Venkat Padmanabhan (Microsoft Research India) and Deborah Estrin (Cornell Tech)

Session 1: Health and Wellness

9:10-9:50: Physical Analytics to Model Health Behaviors, Anmol Madan ( [Keynote Talk]

9:50-10:10: On11: An Activity Recommendation Application to Mitigate Sedentary Lifestyle, Qian He (Worcester Polytechnic Institute), Emmanuel Agu (Worcester Polytechnic Institute)

10:10-10:30: My smartphone knows I am hungry, Fanglin Chen (Dartmouth College); Rui Wang (Dartmouth College); Xia Zhou (Dartmouth College); Andrew Campbell (Dartmouth College)

10:30-11:00: Coffee Break

11:00-11:25: Using Smartphones to Sense, Assess, and Improve Well-Being, Tanzeem Choudhury (Cornell University) [Invited Talk]

11:25-11:45: Discussion, Moderator: Deborah Estrin (Cornell Tech)

Session 2: Human and Social Sensing

11:45-12:10: Life-logging, Thing-logging and the Internet of Things, Jim Gemmell (Trov) [Invited Talk]

12:10-12:30: Social Physicalytics: Challenges & Opportunities for Fusing Mobile and Online Sensing, Archan Misra (Singapore Management University); Kasthuri Jayarajah (Singapore Management Univ.); Shriguru Nayak (Singapore Management University); Philips Prasetyo (Singapore Management University); Ee-Peng Lim (Singapore Management University)

12:30-1:30: Lunch

1:30-1:50: The Case for Human-Centric Personal Analytics, Youngki Lee (Singapore Management University); Rajesh Balan (Singapore Management University)

1:50-2:10: GlimpseData: Towards Continuous Vision-Based Personal Analytics, Seungyeop Han (University of Washington); Rajalakshmi Nandakumar (University of Washington); Matthai Philipose (Microsoft Research); Arvind Krishnamurthy (University of Washington); David Wetherall (University of Washington)

2:10-2:30: Discussion, Moderator: Ramón Cáceres (AT&T Research, USA)

Session 3: Wireless Tracking

2:30-2:55: Wi-Fi Analytics for Business Intelligence, Pravin Bhagwat (AirTight Networks) [Invited Talk]

3:00-3:30: Coffee Break

3:30-3:50: Analysing the privacy policies of Wi-Fi trackers, Levent Demir (Inria); Mathieu Cunche (University of Lyon); Cedric Lauradoux (Inria)

3:50-4:35: Tracking People and Monitoring their Vital Signs Using Body Radio Reflections, Dina Katabi (MIT) [Keynote Talk]
4:35-4:55: Discussion, Moderator: Archan Misra (Singapore Management University)


5:00-5:30: Open Mic Session, Moderator: Venkat Padmanabhan (Microsoft Research India)

Keynote and Invited Talk Details

Keynote talk

Tracking People and Monitoring their Vital Signs Using Body Radio Reflections, Dina Katabi (MIT)

Abstract: Wireless signals are typically used for data communication between an RF transmitter and an RF receiver. Recent advances in wireless technologies, however, have demonstrated that a person’s motion can modulate the wireless signal, enabling the transfer of information from a human to an RF transceiver, even when the person does not carry a transmitter. This leads to new wireless systems in which a user communicate directly with remote devices using gestures. It also allows for using wireless signals to learn about the environment. For example, one may track objects and people as they move around, purely based on how their motion modulates the wireless signal. This could lead to new video games and virtual reality applications that work in non-line-of-sight and across rooms. It can also be used for health-care monitoring in hospitals or at home, and for intrusion detection or search-and-rescue operations.
In this talk, I will present sensing technologies that pinpoint people’s locations based purely on RF reflections off their bodies. They can further track a person’s breathing and heartbeat remotely, without requiring any body contact. They operate by transmitting a low-power wireless signal and monitoring its reflections. They use these reflections to track body motion as well as minute movements associated with breathing and heartbeat (e.g., the chest movements caused by the inhale-exhale process). We envision that such technologies can enable truly smart homes that learn people’s habits and monitor their vital signs to adapt the environment and actively contribute to their inhabitants’ well-being.

Bio: Dina Katabi is a Professor in the Department of Electrical Engineering and Computer Science and the director of MIT’s research center, Wireless@MIT. Katabi's work focuses on wireless networks, mobile applications, network security, and distributed resource management. She received her Bachelor of Science from Damascus University in 1995 and her MS and PhD from MIT in 1999 and 2003. Katabi's doctoral dissertation won an ACM Honorable Mention award and a Sprowls award for academic excellence. She has received best paper awards from ACM SIGCOMM and Usenix NSDI. She was awarded an NSF CAREER award in 2005, the NBX Career Development chair and a Sloan Fellowship in 2006, the IEEE William R. Bennett prize in 2009, a Faculty Research Innovation Fellowship in 2011, and the ACM Grace Murray Hopper Award and a MacArtuher Foundation Fellowship in 2013. Her work on the sparse Fourier transform was selected by the MIT Technology Review as one of the top 10 Most Important Emerging Technologies.

Keynote talk

Physical Analytics to Model Health Behaviors, Anmol Madan (

Abstract: Mobile phones are a pervasive platform for opportunistic sensing of social and health related behaviors. In this talk, I discuss how sensor data from mobile phones can be used to model and predict health outcomes. The talk starts with a review of research at the MIT Media Lab, and then transitions into how has built a commercial platform to collect, annotate, analyze and drive healthcare interventions at scale, deployed with major US hospital systems and healthcare providers.
The three-part platform -- patient app, behavioral analytics engine, and provider dashboard -- applies this technolgy to give care providers a window into their patients' health between office visits. Our mobile app uses smartphone sensors to passively collect information about a patient’s daily patterns. Using this data, our machine learning models are able to detect at-risk patients significantly better than the standard of care. Any concerning changes in behavior are communicated to the provider through our simple, action-oriented web dashboard. is part of the care solutions at instituions such as Kaiser Permanente, Novant Health, UCSF, Duke Medical and Cincinnati Children's.

Bio: Anmol Madan is Co-Founder/CEO and Data Scientist at

Invited talk

Wi-Fi Analytics for Business Intelligence, Pravin Bhagwat (AirTight Networks)

Abstract: With a growing number of mobile consumers routinely carrying at least one Wi-Fi enabled smartphone or tablet and the popularity of Wi-Fi as a preferred network access medium, Wi-Fi analytics can provide major insights into consumer behavior to businesses across different industry verticals. The intelligence gained from these new insights can be leveraged to spawn new applications in the fields of business strategy (e.g., real world A/B testing), marketing (e.g., location-based services, customer engagement) and operations (e.g., staffcasting).
In this presentation I’ll provide several examples from live deployments of AirTight Wi-Fi Analytics. Using data from a case study, I’ll show how we found many unexpected uses of analytics reports based on: 1) the Wi-Fi devices that are detected by or associate with an AirTight AP; and 2) Wi-Fi users that opt into sharing personal information for an incentive.

Bio: Pravin Bhagwat is Founder and CTO of AirTight Networks.

Invited talk

Using Smartphones to Sense, Assess, and Improve Well-Being, Tanzeem Choudhury (Cornell University)

Abstract: The people-aware computing group at Cornell has been developing techniques to cheaply, accurately, and continuously collect data on daily human behavior, social interactions, and context. This data is subsequently leveraged to provide targeted, personalized and effective feedback to promote better mental and physical health in individuals. In this talk I will give an overview of our work on turning sensor-enabled mobile phones into well-being monitors and instruments for administering real-time/real-place interventions.

Bio: Tanzeem Choudhury is an Associate Professor in the Information Science department at Cornell University.

Invited talk

Life-logging, Thing-logging and the Internet of Things, Jim Gemmell (Trov)

Abstract: The same factors that allowed us predict the advent of life-logging point also to the rise of thing-logging – a precursor to the complete Internet of Things vision. Most objects will go through a progression of being logged, being tracked, and being a peripheral, before they become fully connected. Trends in wealth and technology will fuel this progression, but ultimately adoption will be driven by value to the consumer. Experience with life-logging and thing-logging gives us an idea of what that value proposition will be, and shows us some key technical challenges ahead.

Bio: Dr Jim Gemmell, PhD, is the CTO of Trōv and co-author of the book the book Your Life, Uploaded: The Digital Way To Better Memory, Health and Productivity. Previously, he spent 16 years at Microsoft Research as a Senior Researcher, with a broad range of study including life-logging, reliable multicast, multimedia, and entity matching. Jim led the creation of the Microsoft Digital Memories program that funded 14 universities and supplied them with the MyLifeBits life-logging software that he architected and co-developed. Jim also architected and led development of the entity resolution system used to power Xbox TV & Movies, as well as Bing's Movies, TV, Celebrities, and Events. He created the Bing flight status answer, and helped develop the Bing Twitter features. He also represented Microsoft at the IETF standard body and became a co-author of a number of networking standards. His reliable multicast work has been incorporated into Windows.