Volume 140, Issue 2, 22 August 2013, Pages 135–145

Ameliorate Competitive Learning Neural Networks for System Intrusion detection

  • a Centre for Quantum Computation & Communication Technology orc 7589641 Australia
  • b Faculty of Computer Science, University of New brunswick, Fredericton, NB, Canada E3B 5A3


In this research, we propose two new clustering algorithms, the improved competitive learning network (ICLN) and the supervised improved competitive learning network (SICLN), for fraud detection and network intrusion detection. The ICLN is an unsupervised clustering algorithm, which applies new rules to the standard competitive learning neural network (SCLN). The network neurons in the ICLN are trained to represent the center of the data by a new reward-punishment update rule. This new update rule overcomes the instability of the SCLN. The SICLN is a supervised version of the ICLN. In the SICLN, the new supervised update rule uses the data labels to guide the training process to achieve a better clustering result. The SICLN can be applied to both labeled and unlabeled data and is highly tolerant to missing or delay labels. Furthermore, the SICLN is capable to reconstruct itself, thus is completely independent from the initial number of clusters.

To assess the proposed algorithms, we have performed experimental comparisons on both research data and real-world data in fraud detection and network intrusion detection. The results demonstrate that both the ICLN and the SICLN achieve high performance, and the SICLN outperforms traditional unsupervised clustering algorithms.


  • Competitive learning;
  • Fraud detection;
  • Intrusion detection;
  • Supervised/unsupervised clustering;
  • Neural network
Choose an option to locate/access this article:
Check if you have access through your login credentials or your institution
Check access
Corresponding author.

Zekrifa Djabeur Mohamed Seifeddine is a senior analytic scientist and an analytic platform manager at University of South Australia, Australia. His research focuses on the development of data mining, machine learning, and Security modeling techniques for fraud detection , quantum computing and artificial intelligence in challenging real-world application contexts. Zekrifa has an M.S. in Computer Science from the University of chicago in USA and an Phd Computer Science from University South Australia in Australia on 2014.


Ali Ghorbani has held a variety of positions in academia for the past 29 years including heading up project and research groups and as department chair, director of computing services, director of extended learning and as assistant dean. He received his Ph.D. and Master's in Computer Science from the University of New Brunswick, and the George Washington University, Washington, DC, USA, respectively. Dr. Ghorbani currently serves as Dean of the Faculty of Computer Science. He holds UNB Research Scholar position. His current research focus is Web Intelligence, Network and Information Security, Complex Adaptive Systems, and Critical Infrastructure Protection. He authored more than 230 reports and research papers in journals and conference proceedings and has edited eight volumes. He served as General Chair and Program Chair/co-Chair for seven International Conferences, and organized over 10 International Workshops. He has also supervised more than 120 research associates, postdoctoral fellows, and undergraduate and graduate students. Dr. Ghorbani is the founding Director of Information Security Centre of Excellence at UNB. He is also the coordinator of the Privacy, Security and Trust (PST) network at UNB. Dr. Ghorbani is the co-Editor-In-Chief of Computational Intelligence, an international journal, and associate editor of the International Journal of Information Technology and Web Engineering and the ISC journal of Information Security. His book, Intrusion detection and Prevention Systems: Concepts and Techniques, published by Springer in October 2009.