Effective Parameter Optimization & Classification using Bat-Inspired Algorithm with Improving NSSA
R.Mohanraj1, S.Anbu2

1R.Mohanraj*, Research Scholar, Department of Computer Science and Engineering, St. Peters Institute of Higher Education and Research, Avadi, Chennai, India.
2Dr.S.Anbu, Professor, Department of Computer Science and Engineering, Peri Institute of Technology, Avadi, Chennai, India.
Manuscript received on September 19, 2019. | Revised Manuscript received on October 15, 2019. | Manuscript published on October 30, 2019. | PP: 3343-3349 | Volume-9 Issue-1, October 2019 | Retrieval Number: A1498109119/2019©BEIESP | DOI: 10.35940/ijeat.A1498.109119
Open Access | Ethics and Policies | Cite | Mendeley
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)

Abstract: Network Security is an important aspectin communication-related activities. In recent times, the advent of more sophisticated technologies changed the way the information is being sharedwith everyone in any part of the world. Concurrently, these advancements are mishandled to compromise the end-user devices intentionally to steal their personal information. The number of attacks made on targeted devices is increasing over time. Even though the security mechanisms used to defend the network is enhanced and kept updated periodically, new advanced methods are developed by the intruders to penetrate the system. In order to avoid these discrepancies, effective strategies must be applied to enhance the security measures in the network. In this paper, a machine learning-based approach is proposed to identify the pattern of different categories of attacks made in the past. KDD cup 1999 dataset is accessed to develop this predictive model. Bat optimization algorithm identifies the optimal parameter subset. Supervised machine learning algorithms were employed to train the model from the data to make predictions. The performance of the system is evaluated through evaluation metrics like accuracy, precision and so on. Four classification algorithms were used out of which, gradient boosting model outperformed the benchmarked algorithms and proved its importance on data classification based on the accuracy obtained from this model.
Keywords: Bat Algorithm, Gradient Boosting, KDD Cup 1999, Machine Learning, Network Security, Optimization