An efcient GP approach to recognizing cognitive tasks from fNIRS neural signals  

作　　者：AN Jinungn LEE JongHyun AHN ChangWook 

机构地区：[1]Robotics Research Division, Daegu Gyeongbuk Institute of Science & Technology [2]Department of Computer Engineering, Sungkyunkwan University

出　　处：《Science China(Information Sciences)》2013年第10期277-283,共7页中国科学（信息科学）（英文版）

基　　金：supported by the DGIST R&D Program of the MEST of Korea(12-RS-01)

摘　　要：This paper presents a new genetic programming （GP） approach to accurately classifying cognitive tasks from non-stationary and noisy fNIRS neural signals. To this end, a new GP that effectively handles multi- class problems is developed. In accordance with multi-tree structure, GP operators are innovated： crossover exchanges every subtree of parents without suffering from any incongruity problem and mutation fine-tunes candidate solutions by a less destructive process. Experimental results verifies the effectiveness of the proposed GP classifier over existing references.This paper presents a new genetic programming （GP） approach to accurately classifying cognitive tasks from non-stationary and noisy fNIRS neural signals. To this end, a new GP that effectively handles multi- class problems is developed. In accordance with multi-tree structure, GP operators are innovated： crossover exchanges every subtree of parents without suffering from any incongruity problem and mutation fine-tunes candidate solutions by a less destructive process. Experimental results verifies the effectiveness of the proposed GP classifier over existing references.

关 键 词：CLASSIFICATION cognitive task genetic programming FNIRS multi-tree representation 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程]