A support vector machine cost function in simulated annealing for network intrusion detection
| dc.contributor.author | Chowdhury, Md Nasimuzzaman | |
| dc.contributor.examiningcommittee | McLeod, Bob (Electrical and Computer Engineering) Mohammed, Noman (Computer Science) | en_US |
| dc.contributor.supervisor | Ferens, Ken (Electrical and Computer Engineering) | en_US |
| dc.date.accessioned | 2019-02-06T20:20:38Z | |
| dc.date.available | 2019-02-06T20:20:38Z | |
| dc.date.issued | 2019-01-15 | en_US |
| dc.date.submitted | 2019-01-15T18:31:41Z | en |
| dc.degree.discipline | Electrical and Computer Engineering | en_US |
| dc.degree.level | Master of Science (M.Sc.) | en_US |
| dc.description.abstract | This research proposes an intelligent computational approach for feature extraction merging Simulated Annealing (SA) and Support Vector Machine (SVM). The thesis aims to develop a methodology that can provide a reasonable solution for meaningful extraction of data features from a finite number of features/attributes set. Particularly, the proposed method can deal with large datasets efficiently. The proposed methodology is analyzed and validated using two different network intrusion dataset and the performance measures used are; detection accuracy, false positive and false negative rate, Receiver Operation Characteristics curve, Area Under Curve Value and F1 score. Subsequently, a comparative analysis of the proposed model with other machine learning techniques (i.e. general SVM and decision trees) based schemes have been performed to evaluate and benchmark the efficacy of the proposed methodology. The empirically validated results show that proposed SA-SVM based model outperforms the general SVM and decision tree-based detection schemes based on performance measures such as detection accuracy, false positive and false negative rates, Area Under Curve Value and F1 score. | en_US |
| dc.description.note | February 2019 | en_US |
| dc.identifier.citation | Md Nasimuzzaman Chowdhury and Ken Ferens , "Network Intrusion Detection Using Machine Learning," in International Conference on Security & Management, SAM’16, Las Vegas, USA, 2016. | en_US |
| dc.identifier.citation | Md Nasimuzzaman Chowdhury and Ken Ferens , "A Computational Approach for Detecting Intrusion in Communication Network Using Machine Learning," in International Conference on Advances on Applied Cognitive Computing ACC’17, Las Vegas, Nevada, USA, 2017 | en_US |
| dc.identifier.uri | http://hdl.handle.net/1993/33744 | |
| dc.language.iso | eng | en_US |
| dc.rights | open access | en_US |
| dc.subject | Network Intrusion, Machine Learning, Computational Intelligence, Feature Extraction | en_US |
| dc.title | A support vector machine cost function in simulated annealing for network intrusion detection | en_US |
| dc.type | master thesis | en_US |