Activity Classification Using Realistic Data From Wearable Sensors

TLDR

Automatic classification of everyday activities can promote health‑enhancing physical activity and healthier lifestyles. The study aims to determine how to recognize everyday activities, identify useful sensors, and specify the required signal processing and classification methods. A realistic data library of 31 h of annotated 35‑channel sensor recordings from 16 participants performing activities in everyday settings was collected. Custom and automatically generated decision trees achieved 82–86% overall accuracy, while an artificial neural network reached 82% overall, with per‑subject accuracies ranging from 22% to 97% across classifiers.

Abstract

Automatic classification of everyday activities can be used for promotion of health-enhancing physical activities and a healthier lifestyle. In this paper, methods used for classification of everyday activities like walking, running, and cycling are described. The aim of the study was to find out how to recognize activities, which sensors are useful and what kind of signal processing and classification is required. A large and realistic data library of sensor data was collected. Sixteen test persons took part in the data collection, resulting in approximately 31 h of annotated, 35-channel data recorded in an everyday environment. The test persons carried a set of wearable sensors while performing several activities during the 2-h measurement session. Classification results of three classifiers are shown: custom decision tree, automatically generated decision tree, and artificial neural network. The classification accuracies using leave-one-subject-out cross validation range from 58 to 97% for custom decision tree classifier, from 56 to 97% for automatically generated decision tree, and from 22 to 96% for artificial neural network. Total classification accuracy is 82% for custom decision tree classifier, 86% for automatically generated decision tree, and 82% for artificial neural network