Novel hybrid firefly algorithm: an application to enhance XGBoost tuning for intrusion detection classification

Abstract

The research proposed in this article presents a novel improved version of the widely adopted firefly algorithm and its application for tuning and optimising XGBoost classifier hyper-parameters for network intrusion detection. One of the greatest issues in the domain of network intrusion detection systems are relatively high false positives and false negatives rates. In the proposed study, by using XGBoost classifier optimised with improved firefly algorithm, this challenge is addressed. Based on the established practice from the modern literature, the proposed improved firefly algorithm was first validated on 28 well-known CEC2013 benchmark instances a comparative analysis with the original firefly algorithm and other state-of-the-art metaheuristics was conducted. Afterwards, the devised method was adopted and tested for XGBoost hyper-parameters optimisation and the tuned classifier was tested on the widely used benchmarking NSL-KDD dataset and more recent USNW-NB15 dataset for network intrusion detection. Obtained experimental results prove that the proposed metaheuristics has significant potential in tackling machine learning hyper-parameters optimisation challenge and that it can be used for improving classification accuracy and average precision of network intrusion detection systems.

Artificial Neural Network Tuning by Improved Sine Cosine Algorithm for HealthCare 4.0

“…Therefore, the scientists have experimented with wide range of optimization algorithms on a variety of practical problems. Some of the most promising domains include medical diagnostics support [14,20,24,33,43], wireless sensor network tuning [4,9,12,48,57,66], stock price estimations [16], as well as intrusion detection and security domain [1,31,41,45,55,56,60,65] and plant classifying task [17].…”

Training a Logistic Regression Machine Learning Model for Spam Email Detection Using the Teaching-Learning-Based-Optimization Algorithm

“…A significant number of metaheuristics methods exist today, explained by the no free lunch theorem [57], stating that an universal solution to all optimization problems is not existing. Consequently, the researchers have implemented a large number of algorithms, and employed them on a wide range of real-world problems from different domains, such as medical diagnostics [15,21,25,37,47], wireless sensor networks [5,10,13,53,63,72], stock price forecasting [17], intrusion detection and other security applications [2,35,45,51,61,62,66,71] and plant classification problem [18]. Metaheuristics algorithms have been also employed to tune the cloud, edge and fog computing [3,6,16,24,52,65], feature selection [9,20,23,36,41,54,67], dropout regularization [12], a wide spectrum of COVID-19 challenges [26,64,[68][69][70], artificial neural networks optimization [4,7,8,…”

The XGBoost Approach Tuned by TLB Metaheuristics for Fraud Detection

“…The informatics field has benefited from the all of the above algorithm types as the improvements to real-world problems can be seen in practice some of which are: medical diagnosis applications [16,22,26,36,49,58], wireless sensor network optimizations [6,11,14,55,67,77], stock price predictions [18], as well as intrusion detection [2,34,45,65,66,70,74,76] and plant classifying task [19], cloud computing scheduling, edge and fog computing [4,7,17,25,54,69], feature selection [10,21,24,35,38,56,71], dropout regularization [13], COVID-19 detection and fake news detection [27, 68,72,73,75], tuning artificial neural networks [5,8,9,12,15,20,53,57], text clustering [23], cryptocurrency price prediction as well [46], and list goes on.…”