IMPLEMENTATION OF DEEP LEARNING MECHANISM IN BIG DATA USING HYBRID MVO WITH PSO

Abstract
This research paper has simulated the integration of Particle Swarm Optimization (PSO) and Multi-Verse Optimizer (MVO) in order to represent the benefits of the proposed work over traditional Deep Learning. Deep thinking and quick learning are significant for viable artificial intelligence. Several research works have reviewed the current constraints in specific famous learning techniques. PSO has been considered as computational mechanism that is capable of optimizing issues by trying to improve the solution in an iterative manner to provide better-quality result. It is observed that PSO is one of the widely used and very popular met heuristics in the current trend. Its successful application in various optimization problems is proof for the same. Yet, there are several issues associated to PSO. This research paper has resolved those issues by integrating PSO and MVO. MVO technique is considered as sociological as well as biological inspired mechanism. This technique basically depends on three main concepts in cosmology, namely white hole, black hole, and worm hole. For the determination of fast convergence rate, the abilities of MVO are utilized. MVO makes use of roulette wheel selection and therefore it is possible to manage handle continuous and discrete optimization problems. This research is aimed at providing the proposal of innovative and more efficient MSO integrated PSO based system. The proposed research is supposed to be an efficient and vast system that should be capable of being used in several fields.

Authors
Ankur Gupta, Dushyant Kaushik, Muskan Garg
Vaish College of Engineering, India

Keywords
Deep Learning, Optimization, ALO, PSO, MVO
Published By :
ICTACT
Published In :
ICTACT Journal on Soft Computing
( Volume: 10 , Issue: 4 )
Date of Publication :
July 2020
DOI :

Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.