Anomaly Detection Case Study Tutorial

The case study part of the tutorial will feature a hands-on session on applying machine learning techniques, such as neural network based Kohonen Self Organizing Maps (SOM), and the use of visual analytics for the exploration of anomalous behavior in wireless networks. The anomalies are indicators of vulnerabilities in the network. From an operations perspective it is important to detect the anomalies and correct the problem (based on knowing the root cause) in a timely manner. The case study is significant since communications traffic on wireless networks generates large volumes of metadata with hundreds of fields including error codes in the form of logs on a continuous basis across the various servers involved in a communication session.