Classification of normal and abnormal activity in SCADA system using multi-kernel SVM

SCADA systems or supervision, control and data acquisition systems for its acronym in English, can be defined in simple terms as networks of controllers and computers that are created in order to remotely control and monitor all types of industrial processes In this paper we propose a feature extraction method that extracts the features of normal activity on SCADA, and abnormal activity in order to feed a classification system, the classification scheme that classifies the activity into normal and abnormal in accordance with the data provided by the feature extraction phase.