Research ProjectsOngoing work…

Enabling Population-Scale Physical Activity Measurement on Common Mobile Phones

This is a study with Stanford School of Medicine to create novel health monitoring tools for mobile phones. We have created small, wireless, wearable sensors called Wockets intended to be worn 24/7 and provide information on the type, duration, intensity, and location of physical activity. The system operates in real-time, making new interventions based on activity possible. Learn more….

Collaborator(s): Stanford Medical School, MIT
Supported by: NIH/NHLIB (NIH Genes and Environment Initiative)

Development of a Time Use Intervention Using Mobile Phones to Promote Physical Activity in Youth

We have several projects to explore the use of experience sampling on mobile phones for physical activity data gathering in children and adults using traditional electronic ecological momentary assessment (EMA), also known as experience sampling. This work is leading to insights on the validity of electronic EMA in children to gather information about the context in which they engage in physical activity or sedentary behavior. Learn more…

Collaborator(s): University of Southern California Medical School
Supported by: Robert Wood Johnson Foundation

Development of Longitudinal Home Activity Datasets as a Shared Resource

In this project we are developing portable sensor tools that can be used in typical homes to collect data for computer science and health research, as well as to generate shared datasets on home activity from actual homes to be used as a community resource to accelerate research. Data collected from many months of use is being put online, and we are adding tools to the toolkit for future data collection sessions. Learn more…

Collaborator(s): MIT
Supported by: National Science Foundation

Peer and Family Effects on Urban, African-American Children’s Sleep

In this study we are using Wockets sensors (and some audio processing extensions on the mobile phone) to investigate the role of two social factors in the duration and timing of sleep in 11-12 year old African-American children: (1) the influence of child peers, and (2) the level of family organization/structure as reflected in the presence of sleep-related rules, daily routines, and parenting practices. The study’s central hypothesis is that increased peer pressure and decreased level of family organization lead to delayed timing of sleep and decreased sleep duration. Learn more…

Collaborator(s): Case Western Reserve University, Harvard Medical School
Supported by: National Institutes of Health

Encouraging GEI Activity Monitor Adoption: Demonstrating Device Equivalency

In this work we are using custom-designed mechanical shakers and pattern recognition algorithms to demonstrate how phones can be used to produce output nearly equivalent to existing physical activity monitors. We have done some pilot work and are looking for students interested in signal processing who would like to continue with this project.

Collaborator(s): Stanford Medical School
Supported by: NIH Genes and Environment Initiative

Cellphone Intervention Trial for You (CITY)

This is a five-year study to develop and evaluate (in a randomized clinical trial) sensor-enabled mobile phone technology to assist young adults aged 18-35 with long-term weight loss and weight management for two years. The application includes many strategies known to help with weight loss and weight management, and we are able to track the usage of the application and the various components carefully. Read more…

Collaborator(s): Duke Medical School
Supported by: NIH/NHLBI

Optimizing Hospital Workflow and Quality through Patient Engagement

The Hospital Buddy is a computer agent that provides continual health counseling and companionship during a patient’s hospital stay via a bedside touchscreen computer equipped with sensors (RFID tags on staff, accelerometer on patient, acoustics) that can detect certain events occurring in the hospital room. The mHealth group is developing sleep processing algorithms using Wocket accelerometers that will feed into the relational agent (being developed by Dr. Bickmore’s group). Read more…

Collaborator(s): Boston Medical Center
Supported by: CIMIT

Development of Optimal Monitor Placement and Accelerometer Algorithms for Personal Contaminant Sensor Platforms with a Focus on Children’s Activities

In this project with RTI International, Stanford School of Medicine, UC San Diego, LDEO/Columbia, and Battelle/PNNL we are studying the use of accelerometry-based motion monitoring to improve a wearable, personal contaminant sensing in children. In particular, we are interested in whether knowledge of physical activity can improve estimates of exposure based on overall breathing volume. We have plenty of data to analyze from this project for interested students. Learn more…

Collaborator(s): RTI, Stanford Medical School, UCSD, LDEO/Columbia, and Battelle/PNNL
Supported by: NIH Genes and Environment Initiative

Using Mobile Phones to Reduce Missing Data in Youth Activity Monitoring Studies

The overall objective of this project is to develop new software for common mobile phones that can both reduce and explain missing data collected during objective and EMA activity monitoring studies with free living adolescents. This technology will supplement objective monitors already used today, with minimal additional cost. The idea is to use automatic clustering of the day to simplify self-report labeling and drive engaging little games that help teens “fill in gaps” in the data at the end of each day. Learn more…

Collaborator(s): University of Southern California Medical School
Supported by: National Institutes of Health

Generating a Free, High-Quality Food Product Database using Games with a Purpose

The specific aim of this project is to use a “games with a purpose” approach as a proof-of-concept to construct a UPC and nutrient database. Unfortunately, free and high-quality food product databases are not available at this time for research and commercial development. We have created the prototype of a game developed explicitely to acquire this information. Learn more…

Supported by: NIH/NCI

Telemetric Assessment of Movement Stereotypy in Children with ASD

A study with the Groden Center, a school for autistic children, and the University of Rhode Island to explore the use of wireless accelerometers for automatic detection of autistic stereotypies. Prof. Goodwin and Intille are looking for students interested in pattern recognition who wish to continue with the this work.

Collaborator(s): Groden Center, University of Rhode Island
Supported by: National Alliance for Autism

Automatic Detection of Smoking Behavior

The goal of this pilot project is to develop and evaluate real-time pattern recognition algorithms that run on mobile phones and process data from miniature, wearable motion sensors (accelerometers) to detect patterns of smoking behaviors in free-living individuals. By computing features on wrist and arm motion and orientation and looking for patterns over many minutes it may be possible to detect smoking events as they happen.

Collaborator(s): M.D. Anderson Cancer Research Center
Supported by: M.D. Anderson Cancer Research Center

End-User-Driven Training of Activity Recognition Algorithms

We are interested in exploring the complex relationship between pattern recognition algorithms and user interfaces when the pattern recognition systems are used in the real world. Some of the best pattern recognition algorithms will not work unless the users understand what they are doing to some extent, which creates new algorithmic challenges.

Supported by: Intel

Active Transportation

We are exploring an idea that would use mobile technology to encourage active transportation in urban areas by making it easier for people to commute to and from work by bicycle. We are definitely looking for people interested in cycling who want to help out with this one, which is in the early stages.

Comments are closed