Activity sensing in the wild

Published 6 April 2008

Sunny Consolvo, David W. McDonald, Tammy Toscos, Mike Y. Chen, Jon E. Froehlich, Beverly L. Harrison

Citations1,112

TL;DR

This work has developed a system, UbiFit Garden, which uses on-body sensing and activity inference and a personal, mobile display to encourage physical activity to address the growing rate of sedentary lifestyles.

Abstract

Recent advances in small inexpensive sensors, low-power processing, and activity modeling have enabled applications that use on-body sensing and machine learning to infer people's activities throughout everyday life. To address the growing rate of sedentary lifestyles, we have developed a system, UbiFit Garden, which uses these technologies and a personal, mobile display to encourage physical activity. We conducted a 3-week field trial in which 12 participants used the system and report findings focusing on their experiences with the sensing and activity inference. We discuss key implications for systems that use on-body sensing and activity inference to encourage physical activity.

Keywords

Computer ScienceEngineering

American PsychologistIn search of how people change: Applications to addictive behaviors.

8,587 Citations1992James O. Prochaska, Carlo C. DiClemente +1 more

View PDF

Lecture notes in computer scienceActivity Recognition from User-Annotated Acceleration Data

3,118 Citations2004Ling Bao, Stephen Intille

This is the first work to investigate performance of recognition algorithms with multiple, wire-free accelerometers on 20 activities using datasets annotated by the subjects themselves, and suggests that multiple accelerometers aid in recognition.

Lecture notes in computer scienceFish’n’Steps: Encouraging Physical Activity with an Interactive Computer Game

848 Citations2006James Jeng-Weei Lin, Lena Mamykina +3 more

A social computer game, Fish'n'Steps, which links a player's daily foot step count to the growth and activity of an animated virtual character, a fish in a fish tank, to promote an increase in physical activity.

Design requirements for technologies that encourage physical activity

788 Citations2006Sunny Consolvo, Katherine Everitt +2 more

Houston, a prototype mobile phone application for encouraging activity by sharing step count with friends is described and four design requirements for technologies that encourage physical activity are presented, derived from a three-week long in situ pilot study that was conducted with women who wanted to increase their physical activity.

MyExperience

487 Citations2007Jon E. Froehlich, Mike Y. Chen +3 more

This paper presents MyExperience, a system for capturing both objective and subjective in situ data on mobile computing activities, and presents several case studies of field deployments on people's personal phones to demonstrate how MyExperience can be used effectively to understand how people use and experience mobile technology.

Lecture notes in computer scienceA Practical Approach to Recognizing Physical Activities

461 Citations2006Jonathan Lester, Tanzeem Choudhury +1 more

This paper presents an approach to building a system that exhibits these properties and provides evidence based on data for 8 different activities collected from 12 different subjects, and indicates that the system has an accuracy rate of approximately 90% while meeting the requirements.

Exertion interfaces

353 Citations2003Florian Mueller, Stefan Agamanolis +1 more

The results suggest that an Exertion Interface, as compared to a traditional interface, offers increased opportunities for connecting people socially, especially when they have never met before.

Chick clique

288 Citations2006Tammy Toscos, Anne M. Faber +2 more

The intent of Chick Clique is to provide information at opportune times in order to modify the behaviors of girls and ultimately lead to improved health habits.

Lecture notes in computer scienceMobility Detection Using Everyday GSM Traces

277 Citations2006Timothy Sohn, Alex Varshavsky +8 more

This paper explores how coarse-grained GSM data from mobile phones can be used to recognize high-level properties of user mobility, and daily step count, and demonstrates that even without knowledge of observed cell tower locations, mobility modes that are useful for several application domains are recognized.

Acceptance and usability of a relational agent interface by urban older adults

141 Citations2005Timothy Bickmore, Lisa B. Caruso +1 more

Survey results indicate the eight subjects who completed the pilot study found the agent very easy to interact with, even though most of them had little or no previous experience using computers.