空间适配层:用于生物信号传感器阵列应用的可解释域自适应

Joao Pereira, Michael Alummoottil, Dimitrios Halatsis, Dario Farina
{"title":"空间适配层:用于生物信号传感器阵列应用的可解释域自适应","authors":"Joao Pereira, Michael Alummoottil, Dimitrios Halatsis, Dario Farina","doi":"arxiv-2409.08058","DOIUrl":null,"url":null,"abstract":"Biosignal acquisition is key for healthcare applications and wearable\ndevices, with machine learning offering promising methods for processing\nsignals like surface electromyography (sEMG) and electroencephalography (EEG).\nDespite high within-session performance, intersession performance is hindered\nby electrode shift, a known issue across modalities. Existing solutions often\nrequire large and expensive datasets and/or lack robustness and\ninterpretability. Thus, we propose the Spatial Adaptation Layer (SAL), which\ncan be prepended to any biosignal array model and learns a parametrized affine\ntransformation at the input between two recording sessions. We also introduce\nlearnable baseline normalization (LBN) to reduce baseline fluctuations. Tested\non two HD-sEMG gesture recognition datasets, SAL and LBN outperform standard\nfine-tuning on regular arrays, achieving competitive performance even with a\nlogistic regressor, with orders of magnitude less, physically interpretable\nparameters. Our ablation study shows that forearm circumferential translations\naccount for the majority of performance improvements, in line with sEMG\nphysiological expectations.","PeriodicalId":501034,"journal":{"name":"arXiv - EE - Signal Processing","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2024-09-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Spatial Adaptation Layer: Interpretable Domain Adaptation For Biosignal Sensor Array Applications\",\"authors\":\"Joao Pereira, Michael Alummoottil, Dimitrios Halatsis, Dario Farina\",\"doi\":\"arxiv-2409.08058\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Biosignal acquisition is key for healthcare applications and wearable\\ndevices, with machine learning offering promising methods for processing\\nsignals like surface electromyography (sEMG) and electroencephalography (EEG).\\nDespite high within-session performance, intersession performance is hindered\\nby electrode shift, a known issue across modalities. Existing solutions often\\nrequire large and expensive datasets and/or lack robustness and\\ninterpretability. Thus, we propose the Spatial Adaptation Layer (SAL), which\\ncan be prepended to any biosignal array model and learns a parametrized affine\\ntransformation at the input between two recording sessions. We also introduce\\nlearnable baseline normalization (LBN) to reduce baseline fluctuations. Tested\\non two HD-sEMG gesture recognition datasets, SAL and LBN outperform standard\\nfine-tuning on regular arrays, achieving competitive performance even with a\\nlogistic regressor, with orders of magnitude less, physically interpretable\\nparameters. Our ablation study shows that forearm circumferential translations\\naccount for the majority of performance improvements, in line with sEMG\\nphysiological expectations.\",\"PeriodicalId\":501034,\"journal\":{\"name\":\"arXiv - EE - Signal Processing\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2024-09-12\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"arXiv - EE - Signal Processing\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/arxiv-2409.08058\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"arXiv - EE - Signal Processing","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/arxiv-2409.08058","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

摘要

生物信号采集是医疗保健应用和穿戴设备的关键,机器学习为表面肌电图(sEMG)和脑电图(EEG)等信号的处理提供了前景广阔的方法。尽管会话内性能很高,但会话间性能却受到电极偏移的阻碍,这是众所周知的跨模态问题。现有的解决方案通常需要大量昂贵的数据集,并且/或者缺乏鲁棒性和可解释性。因此,我们提出了空间适配层(Space Adaptation Layer,SAL),它可以预置到任何生物信号阵列模型中,并在两次记录会话之间的输入端学习参数化的亲和变换。我们还引入了可学习基线归一化(LBN),以减少基线波动。在两个 HD-sEMG 手势识别数据集上的测试结果表明,SAL 和 LBN 优于常规阵列上的标准微调,甚至在使用对数回归器的情况下也能获得具有竞争力的性能,而且参数数量级更低,物理上可解释。我们的消融研究表明,前臂圆周平移占了性能改进的大部分,这与 sEMG 生理预期相符。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Spatial Adaptation Layer: Interpretable Domain Adaptation For Biosignal Sensor Array Applications
Biosignal acquisition is key for healthcare applications and wearable devices, with machine learning offering promising methods for processing signals like surface electromyography (sEMG) and electroencephalography (EEG). Despite high within-session performance, intersession performance is hindered by electrode shift, a known issue across modalities. Existing solutions often require large and expensive datasets and/or lack robustness and interpretability. Thus, we propose the Spatial Adaptation Layer (SAL), which can be prepended to any biosignal array model and learns a parametrized affine transformation at the input between two recording sessions. We also introduce learnable baseline normalization (LBN) to reduce baseline fluctuations. Tested on two HD-sEMG gesture recognition datasets, SAL and LBN outperform standard fine-tuning on regular arrays, achieving competitive performance even with a logistic regressor, with orders of magnitude less, physically interpretable parameters. Our ablation study shows that forearm circumferential translations account for the majority of performance improvements, in line with sEMG physiological expectations.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
自引率
0.00%
发文量
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信