Identifying distinct features based on received samples for interference detection in wireless sensor network edge devices
Loading...
Files
Accepted version
Date
2020-04
Authors
O'Mahony, George D.
Harris, Philip J.
Murphy, Colin C.
Journal Title
Journal ISSN
Volume Title
Publisher
Institute of Electrical and Electronics Engineers, IEEE
Published Version
Abstract
Wireless Sensor Network (WSN) technologies have developed considerably over the past decade or so and, now, feasible solutions exist for various applications, both critical and otherwise. Often these solutions are achieved by using commercial off the shelf components combined with standardized open-access protocols. As deployments diverge into safety-critical areas, attack incentives intensify, leading to persistent malicious intrusion challenges, which are ever-changing as interference techniques evolve and dynamic hardware becomes increasingly accessible. Unique WSN security vulnerabilities, a fluctuating radio frequency (RF) spectrum and physical environment and spectrum co-existence escalate the problem. Thus, securing WSNs is a critical and demanding requirement, heightened by the burden of protecting sensitive transmitted information. This paper, by utilizing ZigBee and Monte Carlo simulations, aims to develop an initial framework for interference detection in WSNs. Initially, bit error location analysis motivates a feature-based detection strategy, relating to both subtle and crude forms of interference. The work expands to analyze Matlab simulated error-free and erroneous transmissions to investigate whether feature useful differences exist. A feature set, including the measured probability density function of, and statistics on, the in-phase and quadrature-phase samples is demonstrated and initially validated/feasibility tested using a designed support vector machine.
Description
Keywords
Detection , IEEE802.15.4 , Interference , IoT , Machine Learning , Security , Support Vector Machine , WSN and ZigBee
Citation
O’Mahony, G. D., Harris, P. J. and Murphy, C. C. (2020) 'Identifying Distinct Features based on Received Samples for Interference Detection in Wireless Sensor Network Edge Devices', 2020 Wireless Telecommunications Symposium (WTS), Washington, DC, USA, 22-24 April, (7 pp). doi: 10.1109/WTS48268.2020.9198724
Link to publisher’s version
Copyright
© 2020 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.