Abstract: Sensor–equipped smartphones and wearable device are transforming the way of health monitoring. Big data generated by sensor, sensitive application like health monitoring and surveillance system cannot be transferred to and processed by cloud. Moreover, faster processing is required by several internet of things (IOT) application, but current cloud capability will be unable to process such application. The emergence fog computing provide solution by bringing computing resources such as routers much closer to user, also reduce propagation latency for application that require real time response compared to cloud domain. Despite the benefit offered by FC, there are some limitations of fog computing model which focus from a limited perspective on either accuracy of result or response time both not both.
Deep learning algorithms, with their ability to process large scale datasets, have recently started gaining tremendous attentions in the fog computing literatures. However, no comprehensive literature review exists on the applications of deep learning approaches to solve complex problems in fog computing and IoT healthcare. To fill this gap, we conducted a comprehensive literature survey on when deep learning meet fog computing and IoT healthcare. The survey shows that when deep learning algorithms meet fog computing architectures in IoT healthcare are increasingly becoming an interesting research area for solving complex problems. We introduce a new taxonomy of deep learning techniques in fog computing and IoT healthcare. The synthesis and analysis of the articles as well as their limitation are presented. A lot of challenges were identified in the literature and new future research directions to solve the identified challenges are presented.
Keywords: Deep learning, fog computing, Internet of Things (IoT), Cloud computing
Works Cited:
Abdulhafiz Sabo, Habib Shehu Jibrin, Muhammad Zia-Ul-Rahaman Abubakar, Jamilu UsmanWaziri " WHEN DEEP LEARNING MEETS FOG COMPUTING & IoT HEALTHCARE: A REVIEW", IJARCCE International Journal of Advanced Research in Computer and Communication Engineering, vol. 12, no. 9, pp. 32-41, 2023. Crossref https://doi.org/10.17148/IJARCCE.2023.12904
|
DOI:
10.17148/IJARCCE.2023.12904
