Drift management in ML-based IoT device classification: A survey and evaluation
The fast-moving adaptation of the Internet of Things (IoT) and its devices has revolutionized the way we interact with the connecting things and perceive the world around us. Effective and efficient classification of these IoT devices is essential for network management, security, QoS and performanc...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English English |
| Published: |
Indonesian Society for Knowledge and Human Development
2024
|
| Subjects: | |
| Online Access: | https://umpir.ump.edu.my/id/eprint/40500/ |
| Summary: | The fast-moving adaptation of the Internet of Things (IoT) and its devices has revolutionized the way we interact with the connecting things and perceive the world around us. Effective and efficient classification of these IoT devices is essential for network management, security, QoS and performance optimization. However, the dynamic nature of IoT environments introduces a pervasive challenge for effective IoT device classification in the form of drift. Drift is characterized by shifts in device characteristics and behaviors over time, which poses a significant obstacle to accurately classifying IoT devices in various applications like smart homes, smart infrastructures, smart cities, etc. This survey explores the use of machine learning techniques to manage drift management in IoT device classification, encompassing drift prevention detection, drift adaptation, and drift mitigation. Additionally, we discuss the open issues and challenges of various Machine Learning (ML)-based models used to assess drift prevention, detection, adaptation techniques, and mitigation, along with future directions. By shedding light on the current landscape of drift management, this research survey aims to provide valuable insights regarding critical analysis for research gaps in drift management. |
|---|