Abstract—In the last decade a great technological advance in mobile technologies infrastructure was seen. The increase in the use of wireless local networks and the use of services from satellites is also noticed. The high utilization rate of mobile devices for various purposes makes clear the need to monitor wireless networks to ensure the integrity and confidentiality of the information transmitted. Therefore, it is necessary to quickly and efficiently identify the normal and abnormal traffic of these networks, so that the administrators can take action. This work aims, from a database of wireless networks, to classify this data in some classes of pre-established anomalies according to some defined criteria of the MAC layer, using supervised and unsupervised intelligent algorithms Multilayer Perceptron (MLP), K-Means and Self-Organizing Maps (SOM). For the analysis of the mentioned algorithms, the WEKA Data Mining software (Waikato Environment for Knowledge Analysis) is used. The algorithms have high success rate in the classification of the data, being indicated in the use of Intrusion Detection Systems for Wireless Networks.
 

Index Terms—Wireless networks, multilayer perceptron, K-means, self-organized map, weka

Cite: Daniel R. Canêdo and Alexandre R. S. Romariz, "Data Analysis of Wireless Networks Using Computational Intelligence," Journal of Communications, vol. 13, no. 11, pp. 618-626, 2018. Doi: 10.12720/jcm.13.11.618-626