Abstract—Numerous context-aware methods have been lately advanced to deliver physiological data on each person’s health and wellbeing. There are delays in the data transfer to cloud when patient’s health status is being tracked. Numerous Internet of Things sensors generated to observer, track, and sense the actions of elderly in order to avoid types of delays. To overcome this drawback, this paper proposes a Context-Aware Architecture fostered dual interactive Wasserstein generative adversarial network enhanced by Archimedes optimization algorithm with Internet of Things (IoT) (CaA-DuInWGAN-AmOA-IoT-HCS). In order to store, handle large amounts of cumulative sensor data, offers four-module architecture made an IoTM, a Data Pre-processing Module (DPM), Context-Aware Module (CAM), Decision-Making Module (DMM). An IoT in this context consists of a physical or large hardware ecological unit likes sensors, actuators. Contrarily, context-aware computational approach utilizes minimal software ecological unit immediately translate situation into a successful outcome through a variety of IoT devices. Sensors make up the initial module (Internet of Things Magazine, i.e., IoTM), whereas data collecting, storage, and redundancy phases are included in the DPM phase. Fog layer and cloud layer are two distinct kinds of layers that make up the third phase, or the CAM. Context-aware learning phase listed in addition to this. Back-propagation neural network and adaptive grasshopper optimization process perform feature extraction and classification in the last phase, also known as the DM-P phase, in order to produce the best optimal solution. As a result, an alarm or notification is provided to the doctor about the patient’s health with a very quick reaction time, high level of accuracy, and high rate of scalability. The performance of proposed approach CaA-DuInWGAN-AmOA-IoT-HCS reaches 20.15%, 19.76%, and 22.56% for higher accuracy and 21.25%, 19.66%, and 23.76% for higher specificity compared with existing techniques like health care monitoring in context-aware IoT utilizing particle swarm optimization based artificial neural network (ANN-PSO-HCM-CaA-IoT) health care monitoring in context-aware IoT utilizing back-propagation neural network based adaptive grasshopper optimization algorithm (BPNN-AGOA-HCM-CaA-IoT), economic data analytic AI method on IoT edge devices for health monitoring of agriculture machines (EDA-AI-IoT-HMAM), respectively.
 
Keywords—Context-Aware Module (CAM), context-aware architecture fostered dual interactive Wasserstein generative adversarial network, data pre-processing module, decision-making module, Internet of Things (IoT)


Copyright © 2024 by the authors. This is an open access article distributed under the Creative Commons Attribution License (CC BY-NC-ND 4.0), which permits use, distribution and reproduction in any medium, provided that the article is properly cited, the use is non-commercial and no modifications or adaptations are made.