Human Activity Recognition using Smartphone

TL;DR

This paper presents a smartphone-based human activity recognition system utilizing accelerometer data, multiple classification algorithms, and active learning to improve accuracy and reduce labeling effort.

Contribution

It introduces a robust activity recognition framework using only smartphone accelerometer data, combining passive and active learning methods for improved performance and efficiency.

Findings

Passive learning classification rate of 84.4%

Robust to different phone positions and poses

Active learning reduces labeling effort

Abstract

Human activity recognition has wide applications in medical research and human survey system. In this project, we design a robust activity recognition system based on a smartphone. The system uses a 3-dimentional smartphone accelerometer as the only sensor to collect time series signals, from which 31 features are generated in both time and frequency domain. Activities are classified using 4 different passive learning methods, i.e., quadratic classifier, k-nearest neighbor algorithm, support vector machine, and artificial neural networks. Dimensionality reduction is performed through both feature extraction and subset selection. Besides passive learning, we also apply active learning algorithms to reduce data labeling expense. Experiment results show that the classification rate of passive learning reaches 84.4% and it is robust to common positions and poses of cellphone. The results of active learning on real data demonstrate a reduction of labeling labor to achieve comparable performance with passive learning.