Automated Disabled People Fall Detection Using Cuckoo Search with Mobile Networks

Abstract

Falls are the most common concern among older adults or disabled people who use scooters and wheelchairs. The early detection of disabled persons' falls is required to increase the living rate of an individual or provide support to them whenever required. In recent times, the arrival of the Internet of Things (IoT), smartphones, Artificial Intelligence (AI), wearables and so on make it easy to design fall detection mechanisms for smart homecare. The current study develops an Automated Disabled People Fall Detection using Cuckoo Search Optimization with Mobile Networks (ADPFD-CSOMN) model. The proposed model's major aim is to detect and distinguish fall events from non-fall events automatically. To attain this, the presented ADPFD-CSOMN technique incorporates the design of the MobileNet model for the feature extraction process. Next, the CSO-based hyperparameter tuning process is executed for the MobileNet model, which shows the paper's novelty. Finally, the Radial Basis Function (RBF) classification model recognises and classifies the instances as either fall or non-fall. In order to validate the betterment of the proposed ADPFD-CSOMN model, a comprehensive experimental analysis was conducted. The results confirmed the enhanced fall classification outcomes of the ADPFD-CSOMN model over other approaches with an accuracy of 99.17%.