Internet of Things-driven Human Activity Recognition of Elderly and Disabled People Using Arithmetic Optimization Algorithm with LSTM Autoencoder

Abstract

In recent times, mobile communications and Internet of Things (IoT) techniques have been technologically advanced to gather environmental and human data for many applications and intelligent services. Remote monitoring of disabled and older people living in smart homes is very difficult. Human activity recognition (HAR) is an active research area for classifying human movement and application in many regions like rehabilitation, healthcare systems, medical diagnosis, surveillance from smart homes, and elderly care. HAR data are gathered in wearable devices that contain many kinds of sensors or with the mobile sensor aid. Lately, deep learning (DL) algorithm has shown remarkable performance in classifying human activity on HAR information. This paper presents a new Arithmetic Optimization Algorithm with LSTM Autoencoder (AOA-LSTMAE) for HAR technique in the IoT environment. In the presented AOA-LSTMAE technique, the major intention is to recognize several types of human activities in the IoT environment. To accomplish this, the AOA-LSTMAE technique mainly derives the P-ResNet model for feature extraction. In addition, the AOA-LSTMAE technique utilizes the LSTMAE classification model for the recognition of different activities. For improving the recognition efficacy of the LSTMAE model, AOA is used as a hyperparameter optimization system. The simulation validation of the AOA-LSTMAE technique is tested on benchmark activity recognition data. The simulation results of the AOA-LSTMAE technique and compared methods stated the improvement of the proposed model with an accuracy of 99.12% over other recent algorithms.