uActivity: A User-Specific Human Activity Recognition and Fall Detection for Elderly Care

Falls are a major concern among the elderly, as they can cause serious injuries and even death. Therefore, the development of an effective and reliable fall detection system for the elderly is a critical area of research that can significantly improve their safety and quality of life. This paper presents a user-centric Human Activity Recognition (uHAR) model that integrates machine learning algorithms and advanced sensor technology to analyze and classify the various activities and movements. The proposed model, called uActivity, aims to significantly improve the safety and well-being of elderly people, using a uHAR model that integrates multiple sensor data streams and machine learning algorithms. In the performance analysis of daily activity and fall classification, the uActivity algorithm demonstrates satisfactory results in accurately classifying activities and detecting falls among elderly individuals, achieving an accuracy of more than 99% in detecting falls. The proposed uHAR architecture with the uActivity algorithm can significantly improve the accuracy and reliability of fall detection and daily activity classification systems for elderly people.