A performance study of anomaly detection using entropy method

An experiment to study the entropy method for an anomaly detection system has been performed. The study has been conducted using real data generated from the distributed sensor networks at the Intel Berkeley Research Laboratory. The experimental results were compared with the elliptical method and has been analyzed in two dimensional data sets acquired from temperature and humidity sensors across 52 micro controllers. Using the binary classification to determine the upper and lower boundaries for each series of sensors, it has been shown that the entropy method are able to detect more number of out ranging sensor nodes than the elliptical methods. It can be argued that the better result was mainly due to the lack of elliptical approach which is requiring certain correlation between two sensor series, while in the entropy approach each sensor series is treated independently. This is very important in the current case where both sensor series are not correlated each other.

[1]  Sutharshan Rajasegarar,et al.  Anomaly detection by clustering ellipsoids in wireless sensor networks , 2009, 2009 International Conference on Intelligent Sensors, Sensor Networks and Information Processing (ISSNIP).

[2]  M. Palaniswami,et al.  Analysis of Anomalies in IBRL Data from a Wireless Sensor Network Deployment , 2007, 2007 International Conference on Sensor Technologies and Applications (SENSORCOMM 2007).

[3]  Chou-Yuan Lee,et al.  An intelligent algorithm with feature selection and decision rules applied to anomaly intrusion detection , 2012, Appl. Soft Comput..

[4]  Yanheng Liu,et al.  Dynamic entropy based DoS attack detection method , 2013, Comput. Electr. Eng..

[5]  Francisco Herrera,et al.  On the combination of genetic fuzzy systems and pairwise learning for improving detection rates on Intrusion Detection Systems , 2015, Expert Syst. Appl..

[6]  Zaenal Akbar,et al.  Exhaustive search-based model for hybrid sensor network , 2012, 2012 4th International Conference on Intelligent and Advanced Systems (ICIAS2012).

[7]  Laksana Tri Handoko,et al.  A simple statistical analysis approach for Intrusion Detection System , 2014, 2013 IEEE Conference on Systems, Process & Control (ICSPC).

[8]  Maorong Ge,et al.  Cost‐effective monitoring of ground motion related to earthquakes, landslides, or volcanic activity by joint use of a single‐frequency GPS and a MEMS accelerometer , 2013 .

[9]  Sang Joon Kim,et al.  A Mathematical Theory of Communication , 2006 .

[10]  Özgür Ulusoy,et al.  A framework for use of wireless sensor networks in forest fire detection and monitoring , 2012, Comput. Environ. Urban Syst..

[11]  Qian Quan,et al.  Entropy Based Method for Network Anomaly Detection , 2009, 2009 15th IEEE Pacific Rim International Symposium on Dependable Computing.

[12]  Marimuthu Palaniswami,et al.  Elliptical anomalies in wireless sensor networks , 2009, TOSN.

[13]  Alexandros G. Fragkiadakis,et al.  Anomaly-based intrusion detection of jamming attacks, local versus collaborative detection , 2015, Wirel. Commun. Mob. Comput..

[14]  Naixue Xiong,et al.  Anomaly secure detection methods by analyzing dynamic characteristics of the network traffic in cloud communications , 2014, Inf. Sci..

[15]  C. Kavitha,et al.  Processing Massive Data Streams to Achieve Anomaly Intrusion Prevention , 2012, 2012 Fourth International Conference on Computational Intelligence and Communication Networks.

[16]  Claude E. Shannon,et al.  The mathematical theory of communication , 1950 .

[17]  D. Hanto,et al.  Real-time inclinometer using accelerometer MEMS , 2011 .