Big Data Analytics for Improved Risk Management and Customer Segregation in Banking Applications
Volume-3 | Issue-3
Design of Deep Learning Algorithm for IoT Application by Image based Recognition
Volume-3 | Issue-3
Analysis of Serverless Computing Techniques in Cloud Software Framework
Volume-3 | Issue-3
Health Record Management System – A Web-based Application
Volume-3 | Issue-4
A Novel Signal Processing Based Driver Drowsiness Detection System
Volume-3 | Issue-3
IoT Based Monitoring and Control System using Sensors
Volume-3 | Issue-2
Secure Data Sharing Platform for Portable Social Networks with Power Saving Operation
Volume-3 | Issue-3
Review of Internet of Wearable Things and Healthcare based Computational Devices
Volume-3 | Issue-3
Stock Index Prediction with Financial News Sentiments and Technical Indicators
Volume-4 | Issue-3
Hybrid Framework on Automatic Detection and Recognition of Traffic Display board Signs
Volume-3 | Issue-3
Suspicious Human Activity Detection System
Volume-2 | Issue-4
ROBOT ASSISTED SENSING, CONTROL AND MANUFACTURE IN AUTOMOBILE INDUSTRY
Volume-1 | Issue-3
EFFICIENT RESOURCE ALLOCATION AND QOS ENHANCEMENTS OF IOT WITH FOG NETWORK
Volume-1 | Issue-2
Live Streaming Architectures for Video Data - A Review
Volume-2 | Issue-4
IoT Based Monitoring and Control System using Sensors
Volume-3 | Issue-2
Big Data Analytics for Improved Risk Management and Customer Segregation in Banking Applications
Volume-3 | Issue-3
A Novel Signal Processing Based Driver Drowsiness Detection System
Volume-3 | Issue-3
IoT BASED AIR AND SOUND POLLUTION MONITIORING SYSTEM USING MACHINE LEARNING ALGORITHMS
Volume-2 | Issue-1
Analysis of Serverless Computing Techniques in Cloud Software Framework
Volume-3 | Issue-3
Hybrid Intrusion Detection System for Internet of Things (IoT)
Volume-2 | Issue-4
Volume - 2 | Issue - 3 | september 2020
Published
08 July, 2020
For improving the mobile service quality and acceleration of content delivery, edge computing techniques have been providing optimal solution to bridge the device requirements and cloud capacity by network edges. The advancements of technologies like edge computing and mobile communication has contributed greatly towards these developments. The mobile edge system is enabled with Machine Learning techniques in order to improve the edge system intelligence, optimization of communication, caching and mobile edge computing. For this purpose, a smart framework is developed based on artificial intelligence enabling reduction of unwanted communication load of the system as well as enhancement of applications and optimization of the system dynamically. The models can be trained more accurately using the learning parameters that are exchanged between the edge nodes and the collaborating devices. The adaptivity and cognitive ability of the system is enhanced towards the mobile communication system despite the low learning overhead and helps in attaining a near optimal performance. The opportunities and challenges of smart systems in the near future are also discussed in this paper.
KeywordsArtificial Intelligence Energy management Mobile Communication Edge Computing Machine Learning
Full Article PDF Download Article PDF