Classifying Human Activities with Inertial Sensors: A Machine Learning Approach

TL;DR

This paper reviews and compares various machine learning and deep learning methods for classifying human activities using inertial sensor data from smartphones, highlighting advantages over traditional computer vision techniques.

Contribution

It provides an analysis of different ML and DL approaches for HAR with inertial sensors, identifying the most effective methods for this application.

Findings

Sensor-based HAR overcomes privacy issues of vision-based methods

Deep learning approaches improve activity classification accuracy

Inertial sensors offer cost-effective and mobile solutions for HAR

Abstract

Human Activity Recognition (HAR) is an ongoing research topic. It has applications in medical support, sports, fitness, social networking, human-computer interfaces, senior care, entertainment, surveillance, and the list goes on. Traditionally, computer vision methods were employed for HAR, which has numerous problems such as secrecy or privacy, the influence of environmental factors, less mobility, higher running costs, occlusion, and so on. A new trend in the use of sensors, especially inertial sensors, has lately emerged. There are several advantages of employing sensor data as an alternative to traditional computer vision algorithms. Many of the limitations of computer vision algorithms have been documented in the literature, including research on Deep Neural Network (DNN) and Machine Learning (ML) approaches for activity categorization utilizing sensor data. We examined and analyzed different Machine Learning and Deep Learning approaches for Human Activity Recognition using inertial sensor data of smartphones. In order to identify which approach is best suited for this application.