MACHINE LEARNING APPROACH FOR ANOMALY DETECTION IN WIRELESS SENSOR DATA

Wireless sensor nodes can experience faults during deployment either due to its hardware malfunctioning or software failure or even harsh environmental factors and battery failure. This results into presence of anomalies in their time-series collected data. So, these anomalies demand for reliable detection strategies to support in long term and/or in large scale WSN deployments. These data of physical variables are transmitted continuously to a repository for further processing of information as data stream. This paper presents a novel and distributed machine learning approach towards different anomalies detection based on incorporating the combined properties of wavelet and support vector machine (SVM). The time-series filtered data are passed through mother wavelets and several statistical features are extracted. Then features are classified using SVM to detect anomalies as short fault (SF) and noise fault (NF). The results obtained indicate that the proposed approach has excellent performance in fault detection and its classification of WS data.

[1]  V. Veeravalli,et al.  Asymptotically Optimal Quickest Change Detection in Distributed Sensor Systems , 2008 .

[2]  M. Potkonjak,et al.  On-line fault detection of sensor measurements , 2003, Proceedings of IEEE Sensors 2003 (IEEE Cat. No.03CH37498).

[3]  Gagandeep Kaur,et al.  Anomaly Detection in network traffic and role of wavelets , 2010, 2010 2nd International Conference on Computer Engineering and Technology.

[4]  Matt Welsh,et al.  Fidelity and yield in a volcano monitoring sensor network , 2006, OSDI '06.

[5]  V. Alarcón-Aquino,et al.  Anomaly detection in communication networks using wavelets , 2001 .

[6]  S. Osowski,et al.  Accurate fault location in the power transmission line using support vector machine approach , 2004, IEEE Transactions on Power Systems.

[7]  Sami Ekici,et al.  Classification of power system disturbances using support vector machines , 2009, Expert Syst. Appl..

[8]  Songlin Sun,et al.  Fault diagnosis of sensor by chaos particle swarm optimization algorithm and support vector machine , 2011, Expert systems with applications.

[9]  Yuan Yao,et al.  Online anomaly detection for sensor systems: A simple and efficient approach , 2010, Perform. Evaluation.

[10]  G. Panda,et al.  Fault Classification and Section Identification of an Advanced Series-Compensated Transmission Line Using Support Vector Machine , 2007, IEEE Transactions on Power Delivery.

[11]  Jiang Ting,et al.  Fault diagnosis of sensor by chaos particle swarm optimization algorithm and support vector machine , 2011 .

[12]  Supakit Siripanadorn,et al.  Anomaly detection in wireless sensor networks using self-organizing map and wavelets , 2010 .

[13]  Shyh-Jier Huang,et al.  Coiflet wavelet transform applied to inspect power system disturbance-generated signals , 2002 .

[14]  Vladimir Vapnik,et al.  Statistical learning theory , 1998 .

[15]  Nand Kishor,et al.  Disturbance detection in grid-connected distributed generation system using wavelet and S-transform , 2011 .

[16]  Charles X. Ling,et al.  Using AUC and accuracy in evaluating learning algorithms , 2005, IEEE Transactions on Knowledge and Data Engineering.

[17]  Deborah Estrin,et al.  Rapid Deployment with Confidence: Calibration and Fault Detection in Environmental Sensor Networks , 2006 .

[18]  Wei Hong,et al.  A macroscope in the redwoods , 2005, SenSys '05.

[19]  Ramesh Govindan,et al.  Sensor faults: Detection methods and prevalence in real-world datasets , 2010, TOSN.

[20]  Antonio Alfredo Ferreira Loureiro,et al.  Fault management in event-driven wireless sensor networks , 2004, MSWiM '04.

[21]  Yoon-Hwa Choi,et al.  Fault detection of wireless sensor networks , 2008, Comput. Commun..

[22]  Alexander S. Szalay,et al.  Model-Based Event Detection in Wireless Sensor Networks , 2009, ArXiv.

[23]  Stefano Chessa,et al.  Comparison-based system-level fault diagnosis in ad hoc networks , 2001, Proceedings 20th IEEE Symposium on Reliable Distributed Systems.