Physical Activity Recognition Based on a Parallel Approach for an Ensemble of Machine Learning and Deep Learning Classifiers

TL;DR

This paper presents a hybrid human activity recognition method combining machine learning and deep learning classifiers, achieving high accuracy and fast execution for wearable sensor data in healthcare applications.

Contribution

It introduces a parallel ensemble approach that improves accuracy and speed in HAR by combining feature engineering and feature learning techniques.

Findings

Achieved 90% average recognition accuracy in cross-validation.

Significantly reduced execution time through parallelization.

Outperformed individual classifiers in accuracy.

Abstract

Human activity recognition (HAR) by wearable sensor devices embedded in the Internet of things (IOT) can play a significant role in remote health monitoring and emergency notification, to provide healthcare of higher standards. The purpose of this study is to investigate a human activity recognition method of accrued decision accuracy and speed of execution to be applicable in healthcare. This method classifies wearable sensor acceleration time series data of human movement using efficient classifier combination of feature engineering-based and feature learning-based data representation. Leave-one-subject-out cross-validation of the method with data acquired from 44 subjects wearing a single waist-worn accelerometer on a smart textile, and engaged in a variety of 10 activities, yields an average recognition rate of 90%, performing significantly better than individual classifiers. The method easily accommodates functional and computational parallelization to bring execution time significantly down.