An incremental learning on cloud computed decentralised IoT devices. (4th November 2022)

• Record Type: Journal Article
• Authors: Salunkhe, Satish S.; Tandon, Aditya; Arun, M.; Shaik, Nazeer; Nandikolla, Supriya; Ramkumar, D.; Narayanan, S. Lakshmi
• Is Part Of: International journal of engineering systems modelling and simulation. Volume 14:Number 1(2023)
• Page Start: 1
• Page End: 7
• Publication Date: 2022-11-04
• Subjects: incremental learning technique -- cloud computing -- decentralised IoT devices -- internet of things -- IoT; Engineering systems -- Computer simulation -- Periodicals; Engineering systems -- Mathematical models -- Periodicals; 620.0042
• Languages: English
• ISSNs: 1755-9758

Abstract

It is essential that IoT devices can constantly gather new ideas from streams of data independent of catastrophic forgetfulness. Although merely repeating all prior training samples can solve catastrophic forgetting issues, this method faces privacy problems, memory resources, as well as requires a lot of computational, making it unsuitable for limited-resources IoT devices. In this study, the proposed incremental learning for cloud computed decentralised IoT devices are developed and comprises of constant upgraded information and task resolution model. A neural network is trained and utilised to overcome this problem despite frequent disconnectivity or resource outages without losing a lot of progress using cloud computing. Several research experts have frequent disconnectivity issues regarding cloud computing frameworks because of the platform's free membership. Identical difficulties can be seen when working on a localised computer, where the machine will run out of resources or power at times, forcing the researchers to retrain the systems.