基于功能近红外光谱的跨受试心理任务识别的深度迁移学习方法  

A deep transfer learning approach for cross-subject recognition of mental tasks based on functional near-infrared spectroscopy

作　　者：张耀[1] 刘东远 高峰[1,2] ZHANG Yao;LIU Dongyuan;GAO Feng(School of Precision Instrument and Optoelectronics Engineering,Tianjin University,Tianjin 300072,P.R.China;Tianjin Key Laboratory of Biomedical Detecting Techniques and Instruments,Tianjin 300072,P.R.China)

机构地区：[1]天津大学精密仪器与光电子工程学院,天津300072 [2]天津市生物医学检测技术与仪器重点实验室,天津300072

出　　处：《生物医学工程学杂志》2024年第4期673-683,共11页Journal of Biomedical Engineering

基　　金：国家自然科学基金资助项目(61575140,62075156,81871393,81971656,62205239);中国博士后基金资助项目(2023M732600)。

摘　　要：在基于功能近红外光谱(fNIRS)的脑-机接口(BCI)领域中,传统的受试特定解码方法存在校准时间长和跨受试泛化性低等问题,从而限制了BCI系统在日常生活和临床领域中的推广和应用。为解决上述困境,本文提出了一种新颖的深度迁移学习方法,该方法联合了改进型启发式残差网络(rIRN)模型和基于模型的迁移学习(TL)策略,简称TL-rIRN。本文开展了跨受试识别心算和心唱任务的试验,以验证TL-rIRN方法的有效性和优越性。结果表明,相较于受试特定解码方法和其他深度迁移学习方法,TL-rIRN方法显著缩短了校准时间,减少了目标模型的训练时间和计算资源的消耗,并增强了跨受试解码性能。综上,本研究为fNIRS-BCI系统的跨受试、跨任务以及实时解码算法的选择提供了依据,在构建便捷通用型BCI系统方面具有潜在应用价值。In the field of brain-computer interfaces(BCIs)based on functional near-infrared spectroscopy(fNIRS),traditional subject-specific decoding methods suffer from the limitations of long calibration time and low crosssubject generalizability,which restricts the promotion and application of BCI systems in daily life and clinic.To address the above dilemma,this study proposes a novel deep transfer learning approach that combines the revised inceptionresidual network(rIRN)model and the model-based transfer learning(TL)strategy,referred to as TL-rIRN.This study performed cross-subject recognition experiments on mental arithmetic(MA)and mental singing(MS)tasks to validate the effectiveness and superiority of the TL-rIRN approach.The results show that the TL-rIRN significantly shortens the calibration time,reduces the training time of the target model and the consumption of computational resources,and dramatically enhances the cross-subject decoding performance compared to subject-specific decoding methods and other deep transfer learning methods.To sum up,this study provides a basis for the selection of cross-subject,cross-task,and real-time decoding algorithms for fNIRS-BCI systems,which has potential applications in constructing a convenient and universal BCI system.

关 键 词：功能近红外光谱 脑-机接口 深度迁移学习 跨受试解码 改进型启发式残差网络 

分 类 号：R318[医药卫生—生物医学工程] O657.33[医药卫生—基础医学] TP18[理学—分析化学]