An Intelligent Fault Detection Approach Based on Machine Learning in Wireless Sensor Networks
- Version
- Download 17
- File Size 352.53 KB
- File Count 1
- Create Date 27 February 2025
- Last Updated 5 March 2025
An Intelligent Fault Detection Approach Based on Machine Learning in Wireless Sensor Networks
Jangam Bhargavi1, Gonepally Adithya Kumar2, Pusala Arun Kumar3, Singarapu Charan Teja4
Assistant Professor of Department of CSE(AI&ML) of ACE Engineering College 1 Students of Department CSE(AI&ML) of ACE Engineering College 2,3,4
Abstract
Wireless Sensor Networks (WSNs) play a crucial role in applications such as environmental monitoring, healthcare, and industrial automation. However, faults in sensor nodes due to energy depletion, hardware failures, or communication errors impact network efficiency and reliability. This paper surveys various approaches to fault detection in WSNs, emphasizing machine learning techniques such as K-Nearest Neighbors (KNN), Logistic Regression, and Random Forest. These methods enhance fault detection accuracy by analyzing sensor data patterns and classifying faulty nodes in real time. We also discuss existing techniques, their limitations, and the advantages of integrating machine learning for adaptive fault detection. Our analysis highlights the need for hybrid approaches that combine multiple algorithms to improve detection precision and minimize false positives.
Keyword: Fault Detection, Wireless Sensor Networks, Machine Learning, KNN Classifier, Logistic Regression, Random Forest.
Download