From User-independent to Personal Human Activity Recognition Models Exploiting the Sensors of a Smartphone

TL;DR

This paper introduces a novel smartphone sensor-based method for creating personalized human activity recognition models that outperform traditional user-independent models in most cases, with promising potential for improved accuracy.

Contribution

The study presents a new approach combining sensor fusion and single sensor models to develop user-dependent activity recognition models unobtrusively using smartphone sensors.

Findings

Proposed method outperforms traditional models in 9 out of 10 cases.

Sensor fusion enhances data labeling accuracy.

Potential for improved personalized activity recognition.

Abstract

In this study, a novel method to obtain user-dependent human activity recognition models unobtrusively by exploiting the sensors of a smartphone is presented. The recognition consists of two models: sensor fusion-based user-independent model for data labeling and single sensor-based user-dependent model for final recognition. The functioning of the presented method is tested with human activity data set, including data from accelerometer and magnetometer, and with two classifiers. Comparison of the detection accuracies of the proposed method to traditional user-independent model shows that the presented method has potential, in nine cases out of ten it is better than the traditional method, but more experiments using different sensor combinations should be made to show the full potential of the method.