Class binarization to neuroevolution for multiclass classification

Lan, Gongjin1; Gao, Zhenyu2; Tong, Lingyao3; Liu, Ting2

2022-07-01

10.1007/s00521-022-07525-6

NEURAL COMPUTING & APPLICATIONS   影响因子和分区

0941-0643

1433-3058

Multiclass classification is a fundamental and challenging task in machine learning. The existing techniques of multiclass classification can be categorized as (1) decomposition into binary (2) extension from binary and (3) hierarchical classification. Decomposing multiclass classification into a set of binary classifications that can be efficiently solved by using binary classifiers, called class binarization, which is a popular technique for multiclass classification. Neuroevolution, a general and powerful technique for evolving the structure and weights of neural networks, has been successfully applied to binary classification. In this paper, we apply class binarization techniques to a neuroevolution algorithm, NeuroEvolution of Augmenting Topologies (NEAT), that are used to generate neural networks for multiclass classification. We propose a new method that applies Error-Correcting Output Codes (ECOC) to design the class binarization strategies on the neuroevolution for multiclass classification. The ECOC strategies are compared with the class binarization strategies of One-vs-One and One-vs-All on three well-known datasets of Digit, Satellite, and Ecoli. We analyse their performance from four aspects of multiclass classification degradation, accuracy, evolutionary efficiency, and robustness. The results show that the NEAT with ECOC performs high accuracy with low variance. Specifically, it shows significant benefits in a flexible number of binary classifiers and strong robustness.

Multiclass classification Binary classification Error correcting output codes NEAT One-vs-one One-vs-all

SCI ; EI

英语

第一

Guangdong Natural Science Funds for Young Scholar[2021A1515110641] ; National Natural Science Foundation of China[61773197] ; Shenzhen Fundamental Research Program[JCYJ20200109141622964]

Computer Science

Computer Science, Artificial Intelligence

WOS:000822478900001

SPRINGER LONDON LTD

20222812340633

Codes (symbols)

Information Theory and Signal Processing:716.1 ; Data Processing and Image Processing:723.2 ; Information Sources and Analysis:903.1

ENGINEERING

Web of Science

1.Southern Univ Sci & Technol, Dept Comp Sci & Engn, Shenzhen 518055, Peoples R China
2.Vrije Univ Amsterdam, Dept Comp Sci, Amsterdam, Netherlands
3.Vrije Univ Amsterdam, Dept Clin Neuro & Dev Psychol, Amsterdam, Netherlands

Lan, Gongjin,Gao, Zhenyu,Tong, Lingyao,et al. Class binarization to neuroevolution for multiclass classification[J]. NEURAL COMPUTING & APPLICATIONS,2022.

Lan, Gongjin,Gao, Zhenyu,Tong, Lingyao,&Liu, Ting.(2022).Class binarization to neuroevolution for multiclass classification.NEURAL COMPUTING & APPLICATIONS.

Lan, Gongjin,et al."Class binarization to neuroevolution for multiclass classification".NEURAL COMPUTING & APPLICATIONS (2022).