AUTHOR=Deeptha R. , Ramkumar K. , Venkateswaran Sri , Hassan Mohammad Mehedi , Hassan Md. Rafiul , Noori Farzan M. , Uddin Md. Zia TITLE=Enhancing human activity recognition for the elderly and individuals with disabilities through optimized Internet-of-Things and artificial intelligence integration with advanced neural networks JOURNAL=Frontiers in Neuroinformatics VOLUME=Volume 18 - 2024 YEAR=2024 URL=https://www.frontiersin.org/journals/neuroinformatics/articles/10.3389/fninf.2024.1454583 DOI=10.3389/fninf.2024.1454583 ISSN=1662-5196 ABSTRACT=Individuals who are elderly or disabled may receive substantial support from Human Activity Recognition (HAR) systems, which have recently advanced to a new level by the reason of robust integration of the Internet of Things (IoT) and Artificial Intelligence (AI). The blending of IoT and AI methodologies into HAR systems has the potential to enable these populations to lead more autonomous and comfortable lives. HAR systems are equipped with various sensors, including motion capture sensors, microcontrollers, and transceivers, which supply data to assorted AI and machine learning (ML) algorithms for subsequent analysis. Despite the substantial advantages of this integration, current frameworks encounter significant challenges related to computational overhead, which arises from the complexity of AI and ML algorithms. This paper introduces a novel ensemble of Gated Recurrent Networks (GRN) and Deep Extreme Feedforward Neural Networks (DEFNN), with hyperparameters optimized through the Artificial Water Drop Optimization (AWDO) algorithm. This framework leverages GRN for effective feature extraction, subsequently utilized by DEFNN for the accurate classification of HAR data. Additionally, AWDO is employed within DEFNN to adjust hyper-parameters, thereby mitigating computational overhead and enhancing detection efficiency. To verify the proposed methodology, extensive experiments were conducted using real-time datasets gathered from IoT testbeds, which employ NodeMCU units interfaced with Wi-Fi transceivers. The Framework efficiency was assessed by utilizing metrics for instance accuracy is 99.5%, precision-98%, recall 97%, specificity achieves 98%, and F1-score is 98.2%, which were then benchmarked against other contemporary deep learning-based HAR systems. The experimental outcomes indicate that our model achieves near-perfect accuracy, surpassing alternative learning-based HAR systems. Moreover, our model demonstrates reduced computational demands compared to preceding algorithms, suggesting that the proposed framework may offer superior efficacy and compatibility for deployment in HAR systems designed for elderly or disabled individuals.