Study on Advantages of Space Design Based on BP Neural Network and Regression Support Vector Machine

Abstract:

The development of information technology makes the increasingly perfect of virtual reality technology, and it can make the efficient fusion of computer hardware, software and virtual reality technology as well as dynamic simulation of real world. Dynamic environmental technology is according to the human movements, language and so on to make timely response, which can be real-time analysis of the athletes' state, making up the randomness of traditional sports training plan. In order to predict and analyze of the sports leisure space superiority, the basic characteristics of intelligent algorithm is summarized, the basic principle of BP neural network and regression support vector is described. Through the selection of sports leisure space dominances related data, and through the MATLAB simulation, the results show that the virtual reality technology has good adaptability, and its decision coefficient is greater than BP neural network. In this example, the virtual reality technology has better performance, this method provides a new way for the study of the physical recreation space dominance forecast, there has certain reference significance.

• Periodical: Applied Mechanics and Materials (Volumes 543-547)
• Pages: 4710-4713
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.543-547.4710
• Online since: March 2014
• Authors: Yan Xia Cao*, Zhi Gang Wang
• Keywords: BP Neural Network (BPNN), MATLAB Simulation, Regression Support Vector Machine, Virtual Reality Technology

References

[1] Li Hongyan, Ye Jiandong. Review of the Quartet leisure space ceramic composites [J]. China ceramic, 2011, 34 (5): 30-33.

[2] Li Peng, Luo Fa, Xu Jie et al. The mechanical and dielectric properties of sports leisure space ceramic [J]. Journal of the Chinese Ceramic Society, 2010, 36 (3): 306-310.

[3] Ren Yongguo, Liu Ziqiang, Yang Kai, et al. Sports leisure space materials and its application [J]. China ceramic, 2011, 44 (4): 44-46.

[4] Liu Lijun, Li Dongbo, Peng Jinhui, et al. Research on the microwave heating physical recreation space and its dominance forecasting [J]. Materials review B: research, 2011, 25 (10): 131-134.

[5] Zhao Guangpeng, Zheng Zhongcheng. Analysis of the soft soil foundation subsidence prediction method [J]. Journal of Tianjin Institute of Urban Construction, 2012, 14 (3): 176-179.

[6] Li Xibin. Discussion on the prediction methods of freeway soft soil foundation [J]. Road, 2011, (5): 16-20.

[7] Qi Zhidong, Zhu Xinjian, Cao Guangyi. Study on the DMFC modeling based on the identification of improved BP neural network [J]. Computer simulation, 2011, 23 (5): 58-61.

[8] Wang Xiangyang, Cui Changying. Digital watermarking algorithm model based on regression support vector machine [J]. Mini microcomputer systems, 2011, 28 (12): 2260-2263.

[9] Zhang Min, Jiang Hua. The wavelet blind watermarking algorithm based on regression support vector machine [J]. Computer engineering and applications, 2010, 45 (30): 174-176.

[10] Sun Yu, Ceng Weidong, Zhao Yongqing, et al. TC21 alloy hydrogen performance prediction based on BP neural network [J]. Rare metal materials and engineering, 2012, 41 (6): 1041-1044.

[11] Sun Yu, Ceng Weidong, Zhao Yongqing, et al. Ti600 alloy constitutive relationship model of based on BP neural network [J]. Rare metal materials and engineering, 2011, 40 (2): 220-224.

[12] Yang Jianhui, Li Long. Option price forecasting model based on SVR [J]. Systems engineering theory & practice, 2011, 31 (5): 848-854.