Please enable JavaScript.
Coggle requires JavaScript to display documents.
Research Question: How can machine learning be integrated with IoT…
Research Question: How can machine learning be integrated with IoT networks for real-time anomaly detection and response along with prevention to cyber threats?
Anomaly Detection
"Anomaly detection in IoT environment using machine learning." by Bilakanti and others. (2024)
Researchers explore machine learning techniques for identifying anomalous activities within IoT networks. Models include supervised and unsupervised algorithms for their suitability in detecting unusual patterns in IoT data.
"A hybrid approach for efficient feature selection in anomaly intrusion detection for IoT networks." by Ayad and others (2024)
The authors focus on finding the most relevant features from IoT data to enhance accuracy and proficiency of IDS.Through a hybrid approach, researchers aim to reduce computational cost and improve ability to detect intrusions.
"A Comprehensive Study of Anomaly Detection Schemes in IoT Networks Using Machine Learning Algorithms." by Diro and others. (2021)
This article assessed different algorithms, assessing effectiveness, strengths and limitations in identifying abnormal behavior in IoT environments.
"Anomaly detection framework for IoT-enabled appliances using machine learning." by Ahsan and others (2024)
This anomaly detection framework leverages machine learning to monitor IoT devices, identifying unusual behavior that could signify security threats or performance issues
-
Prevention
-
"Machine Learning-Based Detection and Prevention Systems for IoE" by Khatoon and Others (2023)
Key prevention strategies using machine learning techniques are discussed to enhance security of IoT such as Automated Response Mechanisms, real-time threat mitigation, adaptive learning, collaborative defense mechanisms, and behavioral analysis.
"Advanced Manufacturing with Machine Learning: Enhancing Predictive Maintenance, Quality Control, and Process Optimization" by Ani and others (2024)
The paper discusses how machine learning algorithms can analyze data from manufacturing equipment to predict potential failures before they occur. This approach allows for timely maintenance, reducing downtime and maintenance costs, and increasing overall equipment effectiveness.
-