Power and size optimized multi-sensor context recognition platform

doi:10.1109/ISWC.2005.42

2024-10-22

PRE

Nagendra Bhargava Bharatula

Mathias Stäger

Paul Lukowicz

Gerhard Tröster

DOI：10.1109/ISWC.2005.42

原文链接

原文求助

摘要

En 中文

This paper presents a miniaturized low-power platform for real-time activity recognition. The wearable sensor system comprises of accelerometers, a microphone, a light sensor and signal processing units. The recognition is per,formed with low-power features and a decision tree classifier Power measurements show that our 4.15 x 2.75 cm(2), 9 gram platform consumes less than 3 m W and can perforin continuous classification and result transmission,for 129 hours on a small lithium-polymer battery.