학술논문

A Multi-Criteria Intelligence AID Methodology and IoT Based Data Protection Using Machine Learning
Document Type
Conference
Source
2023 Eighth International Conference on Science Technology Engineering and Mathematics (ICONSTEM) Science Technology Engineering and Mathematics (ICONSTEM), 2023 Eighth International Conference on. :1-5 Apr, 2023
Subject
Aerospace
Communication, Networking and Broadcast Technologies
Components, Circuits, Devices and Systems
Computing and Processing
Engineered Materials, Dielectrics and Plasmas
Fields, Waves and Electromagnetics
Nuclear Engineering
Photonics and Electrooptics
Power, Energy and Industry Applications
Robotics and Control Systems
Signal Processing and Analysis
Transportation
Surveys
Computers
Machine learning algorithms
Numerical analysis
Federated learning
Data protection
Data models
federated learning
differential learning
machine learning
distributed learning
cryptographic methods
Language
Abstract
IoT-powered devices have become one of the key companions of humans in recent times. Almost every sector of the modern market is heavily reliant on IoT-powered devices such as smartphones, computers and other smart gadgets. This has resulted in the massive availability of digital data containing the personal information of the users. This has caused a massive issue regarding data privacy on IoT-powered devices in recent times. This has resulted in the application of ML-based technologies for fostering better data protection. The concerned study has focused on the role of the different ML-powered technologies such as federated learning and differential learning models. Thai entre study has also focused on numerical analysis of the issues associated with the mentioned models during data protection. It has also provided survey data regarding different FL-based algorithms such as LM, NN, NM, DT and CM. This study has analyzed the issues and strengths of ML-based data protection on local and global data sets.