Human Activity Recognition Using Multichannel Convolutional Neural Network
This work addresses the challenge of recognizing human activities from biomedical signals, which is incremental as it applies a known CNN architecture to a specific dataset.
The paper tackled the problem of Human Activity Recognition (HAR) by proposing a two-channel Convolutional Neural Network (CNN) that uses frequency and power features of activity signals, achieving a classification accuracy of 95.25% on the UCI HAR dataset.
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.