由于对运动伪迹不敏感、适合特殊人群和可穿戴式检测等优势，功能近红外光谱技术（fNIRS）在脑机接口（BCI）、心理认知等领域发挥着日益重要的作用。肢体运动想象是BCI在残疾人康复训练等领域应用的重要范式，伴随穿戴式fNIRS的发展，有望帮助残疾人在家庭或社区开展长期脑康复训练。本文针对目前基于fNIRS的运动想象任务分类准确率普遍不高这一现状，应用基于Pearson积差相关系数的相关指数R2，对被试进行个性化参数优化，期望改善运动想象的分类结果。实验采集了17名被试的左、右手运动想象任务期间大脑皮层主运动区的血红蛋白浓度变化数据，并采用支持向量机（SVM）分类。结果表明，经过R2参数优化之后，分类准确率相对无优化情况显著提升，分类准确率在60%以上的被试比例由原本的58.8%提高到了94%，分类准确率在65%以上的被试比例由原本的41.2%提升到了64.7%。
Due to advantages such as robustness with respect to motion artifact, suitability for special populations like infants, and being able to be measured in wearable settings, the functional near-infrared spectroscopy (fNIRS) is an emerging and more and more important brain functional imaging modality in many research fields e.g. the brain computer interface, the psychology and the cognitive science. Motor imagination is an important paradigm in the rehabilitation trainings for disabled people. With the development of wearable fNIRS systems, these systems may assist the disabled people in long-term brain rehabilitation trainings at home or in community. However, the classification accuracies of the current fNIRS-based motor imaginary tasks are generally low. This paper aims to improve the classification accuracy of the fNIRS-based motor imaginary task by the individualized parameter optimization using the Pearson correlation based R2 method. In this experiment, the concentration variation data of hemoglobin species during the left and right hand motor imaginary tasks of 17 subjects were collected using the fNIRS method, and the support vector machine (SVM) classifier was then adopted for classification. Experimental results show that the classification accuracy is significantly improved by the parameter optimization using the R2 method. With the R2 method, the percentage of the subjects with classification accuracies above 60% is turned from 58.8% to 94% and that with classification accuracies above 65% is turned from 41.2% to 64.7% in the whole subject pool.
[1] Wallois F, Roche N, Aarabi A, et al. Co-recording of electrical (EEG) and hemodynamic (NIRS) activities in children and neonates[J]. Clini-cal Neurophysiol, 2008, 119(9):e120.
[2] Isobe K, Kusaka T, Nagano K, et al. Functional imaging of brain in se-dated newborn infants using near infrared topography during passive knee movement[J]. Neuroscience Letters, 2001, 299(3):221-224.
[3] Tamaura M, Hoshi Y, Okada F. Localized near-infrared spectroscopy and functional optical imaging of brain activity[J]. Philosophical Trans-actions of the Royal Society B:Biological Sciences, 1997, 352(1354):737-742.
[4] Piper S K, Krueger A, Koch S P, et al. A wearable multi-channel fNIRS system for brain imaging in freely moving subjects[J]. Neuroim-age, 2014, 85:64-71.
[5] Pinti P, Aichelburg C, Lind F, et al. Using fiberless, wearable fNIRS to monitor brain activity in real-world cognitive tasks[J]. Journal of Visual-ized Expeiriments, 2015, 106:e53336.
[6] 张琪涵, 刘颖, 周菘, 等. 主运动区与辅助运动区在运动执行与运动想象任务中的作用:一个近红外光谱技术的研究[C]//全国心理学学术会议. 北京:中国心理学会, 2014:1272-1275. Zhang Qihan, Liu Ying, Zhou Song, et al. Exploring the role of primary and supplementary motor areas in motor execution tasks or motor imag-ery tasks:An fNIRS study[C]//Chinese Psychological Society. Beijing:Chinese Psychological Society, 2014:1272-1275.
[7] Holper L, Wolf M. Single-trial classification of motor imagery differing in task complexity:A functional near-infrared spectroscopy study[J]. Journal of Neuroengineering and Rehabilitation, 2011, 8(1):1.
[8] Hwang H J, Kim S, Choi S, et al. EEG-based brain-computer interfac-es:A thorough literature survey[J]. International Journal of HumanComputer Interaction, 2013, 29(12):814-826.
[9] Naseer N, Hong K S. Classification of functional near-infrared spectros-copy signals corresponding to the right-and left-wrist motor imagery for development of a brain-computer interface[J]. Neuroscience letters, 2013, 553:84-89.
[10] Hong B, Guo F, Liu T, et al. N200-speller using motion-onset visual response[J]. Clinical Neurophysiology, 2009, 120:1658-1666.
[11] Lisa H, Martin W. Single-trial classification of motor imagery differ-ing in task complexity:A functional near-infrared spectroscopy study[J]. Journal of NeuroEngineering and Rehabilitation. 2011, 8(1):1.
[12] 张琪涵, 章鹏, 周菘, 等. 基于fNIRS的运动执行与运动想象脑激活模式比较[J]. 心理学报, 2016, 48(5):495-508. Zhang Qihan, Zhang Peng, Zhou Song, et al. Comparison of motor exe-cution and motor imagery brain activation patterns:A fNIRS Study[J]. Acta Psychologica Sinica, 2016, 48(5):495-508.
