Incremental Learning Techniques for Online Human Activity Recognition

TL;DR

This paper presents an online human activity recognition system using incremental learning algorithms, achieving over 95% accuracy in real-time detection of physical activities through smartphone sensors.

Contribution

It introduces a real-time HAR system utilizing incremental learning algorithms and compares their performance with batch learning methods, highlighting the effectiveness of Incremental KNN and Naive Bayesian.

Findings

Incremental KNN and Naive Bayesian outperform other algorithms.

Achieved over 95% recognition accuracy in real-time.

System effectively processes accelerometer and gyroscope data for activity recognition.

Abstract

Unobtrusive and smart recognition of human activities using smartphones inertial sensors is an interesting topic in the field of artificial intelligence acquired tremendous popularity among researchers, especially in recent years. A considerable challenge that needs more attention is the real-time detection of physical activities, since for many real-world applications such as health monitoring and elderly care, it is required to recognize users' activities immediately to prevent severe damages to individuals' wellness. In this paper, we propose a human activity recognition (HAR) approach for the online prediction of physical movements, benefiting from the capabilities of incremental learning algorithms. We develop a HAR system containing monitoring software and a mobile application that collects accelerometer and gyroscope data and send them to a remote server via the Internet for classification and recognition operations. Six incremental learning algorithms are employed and evaluated in this work and compared with several batch learning algorithms commonly used for developing offline HAR systems. The Final results indicated that considering all performance evaluation metrics, Incremental K-Nearest Neighbors and Incremental Naive Bayesian outperformed other algorithms, exceeding a recognition accuracy of 95% in real-time.