RT Journal Article
JF IEEE Pervasive Computing
YR 2008
VO 7
IS
SP 32
TI The Mobile Sensing Platform: An Embedded Activity Recognition System
A1 James A. Landay,
A1 Predrag "Pedja" Klasnja,
A1 Tanzeem Choudhury,
A1 Gaetano Borriello,
A1 Anthony LaMarca,
A1 Bruce Hemingway,
A1 Jonathan Lester,
A1 Sunny Consolvo,
A1 Adam Rea,
A1 Jeffrey Hightower,
A1 Karl Koscher,
A1 Louis LeGrand,
A1 Ali Rahimi,
A1 Dirk Haehnel,
A1 Danny Wyatt,
A1 Beverly Harrison,
K1 activity recognition
K1 embedded systems
K1 machine learning
K1 wearable computers
AB The Mobile Sensing Platform (MSP) is a small-form-factor wearable device designed for embedded activity recognition. The MSP aims broadly to support context-aware ubiquitous computing applications. It incorporates multimodal sensing, data processing and inference, storage, all-day battery life, and wireless connectivity into a single 4 oz (115 g) wearable unit. Several design iterations and real-world deployments over the last four years have identified a set of core hardware and software requirements for a mobile inference system. This article presents findings and lessons learned in the course of designing, improving and using this system. This article is part of a special issue on activity-based computing.
PB IEEE Computer Society, [URL:http://www.computer.org]
SN 1536-1268
LA English
DO 10.1109/MPRV.2008.39
LK http://doi.ieeecomputersociety.org/10.1109/MPRV.2008.39