Mansour, Fatma SulemanIbrahim, Abdullahi Abdu2022-12-272022-12-272022Mansour, F. S., Ibrahim, A. A. (2022). A new framework for defect detection using hybird machine learning techniques. In 2022 International Symposium on Multidisciplinary Studies and Innovative Technologies (ISMSIT) (pp. 66-68). IEEE.9781665470131https://hdl.handle.net/20.500.12939/3156In this study, some logs obtained with the Firewall Device are classified using multiclass support vector machine (SVM) classifier optimized by grid search algorithm. The presented method was compared with various data mining techniques. In addition, these learning algorithms were compared using four measures: Accuracy, Precision, Recall, and F-measure. In this paper, we propose the use of an automatic ICA-SVM to solve the defect problem in the computer network. It is the first automatic ICA to be used to reduce the size of input data. Then, the output of the ICA is connected to classifiers. SVM categorizes the attributes into three attacks (normal and abnormal). The proposed system showed results with an accuracy of 99.21% compared to some studies.eninfo:eu-repo/semantics/closedAccessComputer SecurityDefect DetectionICASVMConference Object66682-s2.0-85142806496N/A