Satisfying the expectations of quality living is essential for smart healthcare. Therefore, the determination of health afflictions in real-time has been considered as one of the most necessary parts of medical or assistive-care domain. In this article, a novel fog analytic-assisted deep learning-enabled physical stance-based irregularity recognition framework is presented to enhance personal living satisfaction of an individual. To increase the utility of the proposed framework for assistive-care, an attempt has been made to record predicted activity scores on cloud by following the continuous time series policy to provide future health references to authorized medical specialist. Furthermore, a smart two-phased decision generation mechanism is proposed to intimate medical specialist and caretakers about the current physical status of an individual in real-time. The generation of the alert is directly proportional to the predicted physical irregularity and the scale of health severity. The experimental results highlight the advantages of fog analytics that helps to increase the recognition rate up to 46.45% for 40 FPS and 45.72% for 30 FPS against cloud-based monitoring solutions. The calculated outcomes justify the superiority of the proposed fog analytics monitoring solution over the conventional cloud-based monitoring solutions by achieving high activity prediction accuracy and less latency rate in decision making.
Keywords: Abnormality recognition; Deep learning; Fog analytics; Latency reduction; Smart monitoring; Video processing.
Copyright © 2020 Elsevier Inc. All rights reserved.