Quantum beetle swarm algorithm optimized extreme learning machine for intrusion detection

• Published in: Quantum information processing Vol. 21; no. 1
• Main Authors: Dong, Yumin, Hu, Wanbin, Zhang, Jinlei, Chen, Min, Liao, Wei, Chen, Zhengquan
• Format: Journal Article
• Language: English
• Published: New York Springer US 2022; Springer Nature B.V
• Subjects: Accuracy; Antennae; Artificial neural networks; Convergence; Data Structures and Information Theory; Intrusion; Machine learning; Mathematical Physics; Optimization algorithms; Particle swarm optimization; Physics; Physics and Astronomy; QR algorithms; Quantum Computing; Quantum Information Technology; Quantum mechanics; Quantum Physics; Spintronics; Quantum computing; Neural network; Extreme learning machine; Intrusion detection
• ISSN: 1570-0755; 1573-1332
• DOI: 10.1007/s11128-021-03311-w

Because of the low accuracy in intrusion detection, a model of extreme learning machine based on the optimization of quantum beetle swarm algorithm is proposed. First of all, this paper proposes a quantum beetle swarm optimization algorithm, which introduces quantum mechanics and combines the advantages of beetle antennae search and particle swarm optimization. In this way, the individual can learn both their own experience and group experience, which enables the beetle to move purposefully and instructively, and improves the convergence performance of the algorithm. In extreme learning machine, it is more difficult to solve the problem in high-dimensional data. This paper proposed an improved extreme learning machine that uses the least squares QR algorithm to decompose the matrix, which can reduce the computational complexity of the traditional extreme learning machine. The improved extreme learning machine model optimized by quantum beetle swarm optimization algorithm is applied to intrusion detection, and the simulation results show that the model proposed in this paper can significantly improve detection accuracy and increase convergence rate.