Fusion: Practice and Applications FPA 2692-4048 2770-0070 10.54216/FPA https://www.americaspg.com/journals/show/2447 2018 2018 Candidate of Economic Sciences, Associate Professor of Department of Economics and Management, Kazan Federal University, Elabuga Institute of KFU, Elabuga, Russia. Elvir Akhmetshin Candidate of Historical Sciences, Associate Professor of the Department of History and Socio-Cultural Service, Southwest State University, Kursk, Russia. Alexander Nemtsev Candidate of Economic Sciences, Associate Professor of Department of Management, Kuban State Agrarian University named after I.T. Trubilin, Krasnodar, Russia. Rustem Shichiyakh Candidate of Sociological Sciences, Associate Professor of Department of Economics and Management, Khorezm University, Urgench, Uzbekistan Denis Shakhov Candidate of Economic Sciences, Associate Professor of Department of Enterprise Economics, Regional and Personnel Management, Kuban State University, Krasnodar, Russia. Inna Dedkova Falling is among the most threatening event proficient by the ageing population. There is a necessity for the development of the fall detection (FD) system with the increasing ageing population. FD in an Internet of Things (IoT) platform has developed as a vital application with the rapidly increasing population of aging population and the essential for continuous health monitoring. Falls among the ageing can performance in serious injuries, decreased independence, and longer recovery periods. The FD approach can constructed on deep learning (DL) approaches, especially, Recurrent Neural Network (RNN) and Convolutional Neural Network (CNN) are capable in learning difficult patterns from the sensor data. The CNNs investigate the spatial features, but the RNNs approach the temporal dependencies, allowing accurate recognition of fall events. This study presents an Evolutionary Algorithm with Deep Learning based Fall Detection and Classification (EADL-FDC) methodology in the IoT platform. The projected EADL-FDC algorithm allows the DL approaches for the effective recognition and classification of falls for disabled and ageing people. In the presented EADL-FDC technique, the span-partial structure, and attention (SPA-Net) model is utilized for feature extraction purposes. In addition, the symbiotic organism search (SOS) approach was used for the parameter selection of the SPA-Net system. The deep belief network (DBN) model is applied to classify the fall events. Lastly, the moth flame optimization (MFO) algorithm can be utilized to finetune the hyperparameters related to the DBN algorithm. The stimulation analysis of the EADL-FDC method takes place on the fall detection dataset. The experimental outcome depicts the remarkable solution of the EADL-FDC technique over other existing DL methods. 2024 2024 132 145 10.54216/FPA.140211 https://www.americaspg.com/articleinfo/3/show/2447