Application of SVM Based on Improved Quantum Particle Swarm Optimization in Bio-Mimetic Robotic Horse

Abstract:

Quantum principles is introduced in particle swarm optimization to optimize SVM, aiming that common optimization algorithms of SVM are easy to relapse into local extreme values and optimization result bad. Quantum particle swarm optimization can improve traverse property of particle, thus can overcome the limitation of local extreme values and optimize SVM well. Use the optimized SVM to control the motion of bio-mimetic robotic horse. And simulation results show that this algorithm can achieve the best control effect quickly and accurately.

• Periodical: Advanced Materials Research (Volumes 204-210)
• Pages: 306-309
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.204-210.306
• Online since: February 2011
• Authors: Yu Yan Ren, Jie Bao, Ming Sun, Hong Rui Wang
• Keywords: Bio-Mimetic Robotic Horse, Parameter Selection, Particle Swarm Optimization Algorithm (PSO), Quantum Principle, Support Vector Machine (SVM)

References

[1] Vapnik V N: submitted to Transactions on Neural Networks (1999).

[2] D E Falco I, Della Cioppa A and Tarantino E: submitted to Applied Soft Computing Journal (2007).

[3] Lin S W, Ying K C and Chen S C, et al: submitted to Expert Systems with Applications (2008).

[4] Huang Cheng-Lung, Dun Jian-Fan: submitted to Applied soft computing (2007).

[5] Ni Li-Ping, Ni Zhi-Wei, Li Feng-Gang and Pan Yong-Gang: submitted to Computer Technology and Development. (2007).

[6] Lou Der-Chyuan, Liu Chiang-Lung and Lin Chih-Lin: submitted to Computer Standards & Interfaces (2009).