Journal of Systems Engineering and Electronics ›› 2021, Vol. 32 ›› Issue (1): 151-162.doi: 10.23919/JSEE.2021.000014

• SYSTEMS ENGINEERING • Previous Articles     Next Articles

A sparse algorithm for adaptive pruning least square support vector regression machine based on global representative point ranking

Lei HU(), Guoxing YI*(), Chao HUANG()   

  1. 1 School of Astronautics, Harbin Institute of Technology, Harbin 150001, China
  • Received:2020-06-02 Online:2021-02-25 Published:2021-02-25
  • Contact: Guoxing YI E-mail:maple_hsjz@163.com;ygx@hit.edu.cn;huangchao198311@126.com
  • About author:|HU Lei was born in 1993. He received his M.S. degree in control science and engineering, School of Astronautics, Harbin Institute of Technology in 2018. Currently, he is pursuing his Ph.D. degree in Harbin Institute of Technology. His research interests are artificial intelligence, UAV cluster, weapon system combat effectiveness, and decision-making. E-mail: maple_hsjz@163.com||YI Guoxing was born in 1974. He received his Ph.D. degree in control science and engineering, School of Astronautics, Harbin Institute of Technology in 2005. His research interests are UAV system and application technology, the mechanism and application of hemispherical resonance gyro, and the research of inertial and integrated navigation. E-mail: ygx@hit.edu.cn||HUANG Chao was born in 1983. She received her Ph.D. degree in control science and engineering, School of Astronautics, Harbin Institute of Technology in 2019. Her research interests are artificial intelligence and inertial navigation. E-mail: huangchao198311@126.com
  • Supported by:
    This work was supported by the Science and Technology on Space Intelligent Control Laboratory for National Defense (KGJZDSYS-2018-08)

Abstract:

Least square support vector regression (LSSVR) is a method for function approximation, whose solutions are typically non-sparse, which limits its application especially in some occasions of fast prediction. In this paper, a sparse algorithm for adaptive pruning LSSVR algorithm based on global representative point ranking (GRPR-AP-LSSVR) is proposed. At first, the global representative point ranking (GRPR) algorithm is given, and relevant data analysis experiment is implemented which depicts the importance ranking of data points. Furthermore, the pruning strategy of removing two samples in the decremental learning procedure is designed to accelerate the training speed and ensure the sparsity. The removed data points are utilized to test the temporary learning model which ensures the regression accuracy. Finally, the proposed algorithm is verified on artificial datasets and UCI regression datasets, and experimental results indicate that, compared with several benchmark algorithms, the GRPR-AP-LSSVR algorithm has excellent sparsity and prediction speed without impairing the generalization performance.

Key words: least square support vector regression (LSSVR), global representative point ranking (GRPR), initial training dataset, pruning strategy, sparsity, regression accuracy