Intrusion Detection Using Improved Drosophila Optimization Based Weighted Extreme Learning Machine

Abstract

With the rapid development of computer networks, network attacks and damages are becoming more and more frequent, and network intrusion detection has become a hot research topic. With the rapid development of artificial intelligence technology in recent years, more and more researchers apply artificial intelligence technology to network intrusion detection. Extreme Learning Machine (ELM) is a feedforward neural network training method. It randomly sets the initial weights of the feedforward neural network, and completes the network training by solving the least squares solution of the output weights. In this research, the weights evaluated during the machine learning process is optimized using Improved Fruit Fly algorithm. This improves the learning speed and generalization performance of Extreme Learning Machine. To evaluate the performance of the proposed algorithm NSL-KDD dataset is used. Experimental results show that the algorithm proposed can effectively improve the recognition rate of intrusion detection and reduce the rates of false positives and false negatives.