Low sampling rate for physical activity recognition

Abstract

The monitoring of physical activity by acceleration sensors is very common. Smartphones and it's accessories (Smartwatch, wrist bands) are equipped with sensors and provide enough calculation power for data processing. Body worn mobile devices are recognizing various types of physical activities. The current concept consists of a very high sampling rate, the higher the sampling rate, the better the accuracy of classification. This strategy reduces the battery lifetime, especially for devices with limited physical dimensions, e.g. Smartwatches. Since sampling rate is a relevant factor for energy consumption, this work is analyzing the possibilities and performance of a very low sampling rate for physical activity recognition on Smartwatches. This work proposes the new concept of extremely low sampling rate for physical activity recognition.