Utilization of Deep Learning Models for Safe Human-Friendly Computing in Cloud, Fog, and Mobile Edge Networks

Deep learning (DL) involves a multi-level layer model that uses the output from one layer as input to another. Unsupervised learning automatically learns handy features and conveys low-level traits as advanced structures. Supervised learning uses labeled data to optimize/adjust parameters for the whole network with better learning ability. DL development is rooted in rapidly applying massive tagged data to mitigate training problems and providing great computing power to train wide-ranging neural networks viz. high-performance GPU systems. DL models can be an efficient answer to the most intricate engineering puzzles. In unison, human-centered computing (HCC) in fog arrangements and mobile edge networks (MENs) is a stern concern nowadays. Thus, it is anticipated that the DL-grounded development solutions will play an important role in human-centered computing in fog and MENs. DL models for HCC in fog and mobile edge networks strive to afford investigators worldwide devising and sharing advanced solutions in fog and MENs while keeping (i) HCC information revelation and privacy control, (ii) secure HCC protocols, (iii) adequate modeling with security in mind, (iv) multimedia and streaming data safe, private, and manageable, (v) gaining novel HCC insights, (vi) handling associated concepts and applications, (vii) novel algorithms for learning and exploring the HCC behavior, and (viii) dynamic processes coordination.