{"title":"BLSAN:用于运动图像分类的大脑侧化引导的受试者自适应网络","authors":"Fulin Wei;Xueyuan Xu;Qing Li;Xiuxing Li;Xia Wu","doi":"10.1109/LSP.2024.3465348","DOIUrl":null,"url":null,"abstract":"A major challenge in motor imagery Brain-Computer Interfaces (MI-BCIs) arises from domain shift due to large individual differences. Currently, most cross-subject MI-BCI decoding methods rely on transfer learning to extract subject-shared features or align data distributions. However, these methods typically require all unlabeled data from the target subjects or labeled calibration data, which is unavailable in practical applications. To address this, we propose a brain lateralization-guided subject adaptive network, BLSAN, to enhance model generalization through local-global adversarial training. Specifically, two separate adversarial networks for left and right hemispheres are designed to reduce local differences, and features extracted from both hemispheres are combined for global adversarial training. Additionally, we design a confidence-based pseudo label generation method to enhance model discriminability. We validate the effectiveness of our approach on two public MI datasets, BCI Competition IV 2a and 2b, only with some unlabeled calibration data, which improves the practicality of MI-BCIs.","PeriodicalId":13154,"journal":{"name":"IEEE Signal Processing Letters","volume":null,"pages":null},"PeriodicalIF":3.2000,"publicationDate":"2024-09-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"BLSAN: A Brain Lateralization-Guided Subject Adaptive Network for Motor Imagery Classification\",\"authors\":\"Fulin Wei;Xueyuan Xu;Qing Li;Xiuxing Li;Xia Wu\",\"doi\":\"10.1109/LSP.2024.3465348\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"A major challenge in motor imagery Brain-Computer Interfaces (MI-BCIs) arises from domain shift due to large individual differences. Currently, most cross-subject MI-BCI decoding methods rely on transfer learning to extract subject-shared features or align data distributions. However, these methods typically require all unlabeled data from the target subjects or labeled calibration data, which is unavailable in practical applications. To address this, we propose a brain lateralization-guided subject adaptive network, BLSAN, to enhance model generalization through local-global adversarial training. Specifically, two separate adversarial networks for left and right hemispheres are designed to reduce local differences, and features extracted from both hemispheres are combined for global adversarial training. Additionally, we design a confidence-based pseudo label generation method to enhance model discriminability. We validate the effectiveness of our approach on two public MI datasets, BCI Competition IV 2a and 2b, only with some unlabeled calibration data, which improves the practicality of MI-BCIs.\",\"PeriodicalId\":13154,\"journal\":{\"name\":\"IEEE Signal Processing Letters\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":3.2000,\"publicationDate\":\"2024-09-20\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"IEEE Signal Processing Letters\",\"FirstCategoryId\":\"5\",\"ListUrlMain\":\"https://ieeexplore.ieee.org/document/10684550/\",\"RegionNum\":2,\"RegionCategory\":\"工程技术\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q2\",\"JCRName\":\"ENGINEERING, ELECTRICAL & ELECTRONIC\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"IEEE Signal Processing Letters","FirstCategoryId":"5","ListUrlMain":"https://ieeexplore.ieee.org/document/10684550/","RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"ENGINEERING, ELECTRICAL & ELECTRONIC","Score":null,"Total":0}
引用次数: 0
摘要
运动图像脑机接口(MI-BCI)面临的一大挑战是个体差异较大导致的领域偏移。目前,大多数跨受试者 MI-BCI 解码方法都依赖于迁移学习来提取受试者共享特征或调整数据分布。然而,这些方法通常需要来自目标受试者的所有未标记数据或标记校准数据,这在实际应用中是不可用的。为了解决这个问题,我们提出了一种大脑侧向化引导的主体自适应网络(BLSAN),通过局部-全局对抗训练来增强模型泛化。具体来说,我们为左右半球设计了两个独立的对抗网络,以减少局部差异,并将从两个半球提取的特征结合起来进行全局对抗训练。此外,我们还设计了一种基于置信度的伪标签生成方法,以增强模型的可区分性。我们在 BCI Competition IV 2a 和 2b 两个公开的 MI 数据集上验证了我们的方法的有效性,仅使用了一些未标记的校准数据,这提高了 MI-BCI 的实用性。
BLSAN: A Brain Lateralization-Guided Subject Adaptive Network for Motor Imagery Classification
A major challenge in motor imagery Brain-Computer Interfaces (MI-BCIs) arises from domain shift due to large individual differences. Currently, most cross-subject MI-BCI decoding methods rely on transfer learning to extract subject-shared features or align data distributions. However, these methods typically require all unlabeled data from the target subjects or labeled calibration data, which is unavailable in practical applications. To address this, we propose a brain lateralization-guided subject adaptive network, BLSAN, to enhance model generalization through local-global adversarial training. Specifically, two separate adversarial networks for left and right hemispheres are designed to reduce local differences, and features extracted from both hemispheres are combined for global adversarial training. Additionally, we design a confidence-based pseudo label generation method to enhance model discriminability. We validate the effectiveness of our approach on two public MI datasets, BCI Competition IV 2a and 2b, only with some unlabeled calibration data, which improves the practicality of MI-BCIs.
期刊介绍:
The IEEE Signal Processing Letters is a monthly, archival publication designed to provide rapid dissemination of original, cutting-edge ideas and timely, significant contributions in signal, image, speech, language and audio processing. Papers published in the Letters can be presented within one year of their appearance in signal processing conferences such as ICASSP, GlobalSIP and ICIP, and also in several workshop organized by the Signal Processing Society.