Abstract
Wireless Sensor Networks form the backbone of modern cyber physical systems used in applications such as environmental monitoring, healthcare monitoring, industrial automation, and smart infrastructure. In this paper a lightweight and interpretable anomaly detection framework based on a first order Markov chain model is proposed. The method discretizes continuous sensor readings into finite states and models the temporal dynamics of sensor transitions through a transition probability matrix. Anomalies are detected when observed transitions occur with probabilities below a computed threshold, allowing for real time detection without labeled data or intensive computation. The framework is validated on the Intel Berkeley Research Lab dataset, and comparative analysis with Z score, Hidden Markov Model, and autoencoder based methods shows a balanced trade-off between accuracy, interpretability, and computational efficiency.
Cite this work
Download BibTeX · Download RIS · This record describes a preprint.
@article{mishra2025anomaly,
title = {An Efficient Anomaly Detection Framework for Wireless Sensor Networks Using Markov Process},
author = {Mishra, Rahul and Jha, Sudhanshu Kumar and Osama, Omar Faruq and Bhusal, Bishnu and Sudhakaran, Sneha and Kshetri, Naresh},
journal = {arXiv preprint arXiv:2511.00481},
year = {2025},
month = nov,
eprint = {2511.00481},
archiveprefix = {arXiv},
primaryclass = {cs.CR},
url = {https://arxiv.org/abs/2511.00481}
}