Human Activity Recognition Using Multichannel Convolutional Neural Network

TL;DR

This paper introduces a two-channel CNN model for human activity recognition that leverages frequency and power features, achieving over 95% accuracy on the UCI HAR dataset, advancing AI's ability to interpret human actions.

Contribution

It proposes a novel two-channel CNN approach utilizing frequency and power features for improved human activity recognition accuracy.

Findings

Achieved 95.25% classification accuracy on UCI HAR dataset.

Demonstrated effectiveness of frequency and power features in HAR.

Provided a framework for future biomedical signal-based activity recognition.

Abstract

Human Activity Recognition (HAR) simply refers to the capacity of a machine to perceive human actions. HAR is a prominent application of advanced Machine Learning and Artificial Intelligence techniques that utilize computer vision to understand the semantic meanings of heterogeneous human actions. This paper describes a supervised learning method that can distinguish human actions based on data collected from practical human movements. The primary challenge while working with HAR is to overcome the difficulties that come with the cyclostationary nature of the activity signals. This study proposes a HAR classification model based on a two-channel Convolutional Neural Network (CNN) that makes use of the frequency and power features of the collected human action signals. The model was tested on the UCI HAR dataset, which resulted in a 95.25% classification accuracy. This approach will help to conduct further researches on the recognition of human activities based on their biomedical signals.