Multi-Scale Self-Attention Approach for Analysing Motor Imagery Signals in Brain-Computer Interfaces

运动表象 脑-机接口 比例(比率) 心理学 计算机科学 认知心理学 人工智能 脑电图 神经科学 地图学 地理
作者
Mohammed Wasim Bhatt,Sparsh Sharma
出处
期刊:Journal of Neuroscience Methods [Elsevier]
卷期号:408: 110182-110182 被引量:1
标识
DOI:10.1016/j.jneumeth.2024.110182
摘要

Motor imagery-based electroencephalogram (EEG) brain-computer interface (BCI) technology has seen tremendous advancements in the past several years. Deep learning has outperformed more traditional approaches, such next-gen neuro-technologies, in terms of productivity. It is still challenging to develop and train an end-to-end network that can sufficiently extract the possible characteristics from EEG data used in motor imaging. Brain-computer interface research is largely reliant on the fundamental problem of accurately classifying EEG data. There are still many challenges in the field of MI classification even after researchers have proposed a variety of methods, such as deep learning and machine learning techniques. We provide a model for four-class categorization of motor imagery EEG signals using attention mechanisms: left hand, right hand, foot, and tongue/rest. The model is built on multi-scale spatiotemporal self-attention networks. To determine the most effective channels, self-attention networks are implemented spatially to assign greater weight to channels associated with motion and lesser weight to channels unrelated to motion. To eliminate noise in the temporal domain, parallel multi-scale Temporal Convolutional Network (TCN) layers are utilized to extract temporal domain features at various scales. On the IV-2b dataset from the BCI Competition, the suggested model achieved an accuracy of 85.09%; on the IV-2a and IV-2b datasets from the HGD datasets, it was 96.26%. In single-subject classification, this approach demonstrates superior accuracy when compared to existing methods. The findings suggest that this approach exhibits commendable performance, resilience, and capacity for transfer learning.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
更新
大幅提高文件上传限制,最高150M (2024-4-1)

科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
blueming完成签到,获得积分10
刚刚
跳跃幻儿发布了新的文献求助40
刚刚
火火火完成签到,获得积分10
1秒前
冬冬完成签到,获得积分10
1秒前
sunwei完成签到,获得积分10
1秒前
1秒前
小蘑菇应助吕洺旭采纳,获得10
1秒前
阔达的访风完成签到,获得积分10
2秒前
蜜蜜完成签到,获得积分10
2秒前
章鱼完成签到,获得积分20
2秒前
onfire发布了新的文献求助10
2秒前
全智甜发布了新的文献求助20
3秒前
3秒前
3秒前
水木完成签到,获得积分10
4秒前
一只胖赤赤完成签到 ,获得积分10
4秒前
yunsww完成签到,获得积分10
4秒前
5秒前
流砂完成签到,获得积分10
5秒前
呆萌的秋天完成签到,获得积分10
5秒前
丶Dawn完成签到,获得积分10
5秒前
郭凌云发布了新的文献求助50
6秒前
6秒前
lr完成签到 ,获得积分10
6秒前
ALIVE_STAR完成签到,获得积分10
6秒前
maz123456完成签到,获得积分10
6秒前
6秒前
yibaozhangfa完成签到,获得积分10
7秒前
7秒前
惠归尘完成签到,获得积分10
7秒前
乐乐应助丁仪采纳,获得10
8秒前
好吃的蛋挞完成签到,获得积分10
8秒前
蓝冰完成签到,获得积分10
8秒前
充电宝应助氪蔼采纳,获得40
8秒前
任性雨柏完成签到,获得积分10
8秒前
8秒前
9秒前
柯北完成签到 ,获得积分20
10秒前
vhjino完成签到,获得积分10
10秒前
惠归尘发布了新的文献求助10
10秒前
高分求助中
Sustainability in Tides Chemistry 2000
Microlepidoptera Palaearctica, Volumes 1 and 3 - 13 (12-Volume Set) [German] 1122
Дружба 友好报 (1957-1958) 1000
The Data Economy: Tools and Applications 1000
A Dissection Guide & Atlas to the Rabbit 600
Mantiden - Faszinierende Lauerjäger – Buch gebraucht kaufen 500
PraxisRatgeber Mantiden., faszinierende Lauerjäger. – Buch gebraucht kaufe 500
热门求助领域 (近24小时)
化学 医学 生物 材料科学 工程类 有机化学 生物化学 物理 内科学 纳米技术 计算机科学 化学工程 复合材料 基因 遗传学 催化作用 物理化学 免疫学 量子力学 细胞生物学
热门帖子
关注 科研通微信公众号,转发送积分 3104211
求助须知:如何正确求助?哪些是违规求助? 2755498
关于积分的说明 7633314
捐赠科研通 2408986
什么是DOI,文献DOI怎么找? 1278114
科研通“疑难数据库(出版商)”最低求助积分说明 617284
版权声明 599207