Machine-Learning-Based Human Fall Detection Using Contact- and Noncontact-Based Sensors

Abstract

Automated human fall detection is an essential area of research due to its health implications in day-to-day life. Detecting and timely reporting of human falls may lead to saving human life. In this paper, fall detection has been targeted using machine-learning-based approaches from two perspectives regarding data sources, that is, contact-based and noncontact-based sensors. In both of these cases, various methods based on deep learning and machine learning techniques have been attempted, and their performances were compared. The approaches analyze data in fixed time windows and extract features in the time domain or spatial domain which obtain relative information between consecutive data samples. After experimentation, it was found that the proposed noncontact-based sensor techniques outperformed the contact-based sensor techniques by a margin of 1.82%. After this, it was also found that the noncontact-based sensor techniques outperformed the state of the art of noncontact-based sensor results by a margin of 3.15%. To better suit these techniques for real-world applications, embedded board implementation and privacy preservation of subject by using advanced methods such as compressive sensing and feature encoding need to be attempted.