A Comprehensive Analysis on Wearable Acceleration Sensors in Human Activity Recognition

TLDR

Sensor‑based motion recognition combines wearable sensors and machine learning to interpret low‑level data for real‑life context, yet the Human Activity Recognition problem remains debated because of diverse activities and tracking methods. The study aims to experimentally determine the best predictive model for HAR by creating a comprehensive accelerometer dataset that captures diverse heterogeneities. The authors built a large accelerometer dataset and performed an extensive comparison of 293 feature representations and classifiers, applying PCA to reduce dimensionality while preserving essential information. The experiments achieved an average accuracy of 96.44 % ± 1.62 % with 10‑fold cross‑validation and 79.92 % ± 9.68 % in subject‑independent tests, demonstrating that highly accurate HAR models can be built under realistic conditions.

Abstract

Sensor-based motion recognition integrates the emerging area of wearable sensors with novel machine learning techniques to make sense of low-level sensor data and provide rich contextual information in a real-life application. Although Human Activity Recognition (HAR) problem has been drawing the attention of researchers, it is still a subject of much debate due to the diverse nature of human activities and their tracking methods. Finding the best predictive model in this problem while considering different sources of heterogeneities can be very difficult to analyze theoretically, which stresses the need of an experimental study. Therefore, in this paper, we first create the most complete dataset, focusing on accelerometer sensors, with various sources of heterogeneities. We then conduct an extensive analysis on feature representations and classification techniques (the most comprehensive comparison yet with 293 classifiers) for activity recognition. Principal component analysis is applied to reduce the feature vector dimension while keeping essential information. The average classification accuracy of eight sensor positions is reported to be 96.44% ± 1.62% with 10-fold evaluation, whereas accuracy of 79.92% ± 9.68% is reached in the subject-independent evaluation. This study presents significant evidence that we can build predictive models for HAR problem under more realistic conditions, and still achieve highly accurate results.