Outlier Detection for IoT Frameworks Using Isolation Forest

V. Lakshmi Chaitanya, M. Sharmila Devi, Gaddam Anju Sree, Dudekula Aisha Thabasum, Uppu Sravani, Gandham Sneha

2025

Abstract

"Outlier Detection for IoT Frameworks Using Isolation Forest" focuses on the importance of identifying abnormal data in IoT systems where a large amount of sensor data is transmitted through wireless networks. In IoT frameworks, anomaly detection is essential to ensure network security, error detection, and effective data management. In this area, there are several challenges, such as high-speed and large-scale data, limited IoT devices resources, changes in network conditions, and the complexity of separating effective outliers from malicious attacks and faulty sensors. To address these problems, a sophisticated machine learning model is used, for example, to identify in-depth anomalies in isolated forests and single-class SVMs, to group similar patterns and outliers with K-Means Clustering and DBSCAN, and to detect anomalies based on deep learning in complex high-dimensional IoT data. These methods scan sensor measurements, network traffic, and device operations to improve system safety and efficiency. This methodology is widely used, from smart city intrusion detection and industrial IoT fault prediction to network anomalies detection in health monitoring systems and traffic optimization in wireless smart transport networks. With these methods of machine learning, IoT systems can perform strong, secure, and intelligent operations in wireless areas, detect abnormalities earlier, and improve the overall performance of the system. In addition, the combination of federated learning and edge computing can improve the scalability and privacy of an abnormal detection system in order to better adapt to the distributed environment of an IoT network. This study complements existing literature on IoT security and data analysis and provides practical applications for real problems in wireless IoT systems.

Paper Citation

in Harvard Style

Chaitanya V., Devi M., Sree G., Thabasum D., Sravani U. and Sneha G. (2025). Outlier Detection for IoT Frameworks Using Isolation Forest. In Proceedings of the 1st International Conference on Research and Development in Information, Communication, and Computing Technologies - ICRDICCT`25; ISBN 978-989-758-777-1, SciTePress, pages 808-815. DOI: 10.5220/0013890300004919

in Bibtex Style

@conference{icrdicct`2525,
author={V. Chaitanya and M. Devi and Gaddam Sree and Dudekula Thabasum and Uppu Sravani and Gandham Sneha},
title={Outlier Detection for IoT Frameworks Using Isolation Forest},
booktitle={Proceedings of the 1st International Conference on Research and Development in Information, Communication, and Computing Technologies - ICRDICCT`25},
year={2025},
pages={808-815},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013890300004919},
isbn={978-989-758-777-1},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 1st International Conference on Research and Development in Information, Communication, and Computing Technologies - ICRDICCT`25
TI - Outlier Detection for IoT Frameworks Using Isolation Forest
SN - 978-989-758-777-1
AU - Chaitanya V.
AU - Devi M.
AU - Sree G.
AU - Thabasum D.
AU - Sravani U.
AU - Sneha G.
PY - 2025
SP - 808
EP - 815
DO - 10.5220/0013890300004919
PB - SciTePress