Data augmentation for Convolutional LSTM based brain computer interface system

计算机科学 脑电图 人工智能 脑-机接口 卷积神经网络 模式识别(心理学) 深度学习 运动表象 任务(项目管理) 人工神经网络 语音识别 机器学习 心理学 精神科 经济 管理
作者
Kahoko Takahashi,Zhe Sun,Jordi Solé‐Casals,Andrzej Cichocki,Anh Huy Phan,Qibin Zhao,Hui‐Hai Zhao,Shangkun Deng,Ruggero Micheletto
出处
期刊:Applied Soft Computing [Elsevier BV]
卷期号:122: 108811-108811 被引量:4
标识
DOI:10.1016/j.asoc.2022.108811
摘要

Electroencephalogram (EEG) is a noninvasive method to detect spatio-temporal electric signals in human brain, actively used in the recent development of Brain Computer Interfaces (BCI). EEG’s patterns are affected by the task, but also other variable factors influence the subject focus on the task and result in noisy EEG signals difficult to decipher. To surpass these limitations methods based on artificial neural networks (ANNs) are used, they are inherently robust to noise and do not require models. However, they learn from examples and require lots of training data-sets. This will increase costs, need research time and subjects effort. To reduce the number of experiments necessary for network training, we devised a methodology to provide artificial data from a limited number of training data-sets. This was done by applying Empirical Mode Decomposition (EMD) on the EEG frames and intermixing their Intrinsic Mode Function (IMFs). We experimented on motor imagery (MI) tests where participants were asked to imagine movement of the left (or right) arm while under EEG recording. The EEG data were firstly transformed using the Morlet wavelet and then fed to an originally designed Convolutional Neural Network (CNN) with long short term memory blocks (LSTM-RNN). The introduction of artificial frames improved performances when compared with standard algorithms. The artificial frames become advantageous even when the number of available real frames was only of 7 or 8. In a test with two subjects (200 recordings for each subject), we reached an accuracy better than 88% for both subjects. Improvements due to the artificial data were especially noticeable for the under-performing subject, whose EEG had lower accuracy. Imagination recognition accuracy was about 89% with 360 training frames, in which 300 were artificially created starting from 60 real ones. We believe this methodology of synthesizing artificial data may contribute to the development of novel and more efficient ways to train neural networks for brain computer interfaces.
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
PDF的下载单位、IP信息已删除 (2025-6-4)

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
yulia完成签到 ,获得积分10
1秒前
佳期如梦完成签到 ,获得积分10
1秒前
2秒前
阿Q完成签到,获得积分10
3秒前
4秒前
彬琪发布了新的文献求助10
5秒前
5秒前
6秒前
6秒前
雨木目完成签到,获得积分10
7秒前
小鱼完成签到,获得积分10
7秒前
chenkaixin发布了新的文献求助10
7秒前
梦XING完成签到 ,获得积分10
8秒前
eternity136发布了新的文献求助10
8秒前
vv完成签到,获得积分10
9秒前
9秒前
哈哈哈哈发布了新的文献求助20
9秒前
KANG完成签到,获得积分10
10秒前
义气黄焖排骨完成签到,获得积分10
10秒前
11秒前
如梦如画发布了新的文献求助10
11秒前
Hannes应助15902933324sjc采纳,获得10
12秒前
12秒前
12秒前
梓默完成签到 ,获得积分10
12秒前
我是老大应助Japan采纳,获得10
13秒前
彬琪完成签到,获得积分10
13秒前
红尘踏歌完成签到,获得积分10
13秒前
不忘初心发布了新的文献求助10
14秒前
18746005898完成签到 ,获得积分10
14秒前
chenkaixin完成签到,获得积分10
15秒前
WangZhen完成签到,获得积分20
16秒前
乔木木完成签到,获得积分10
16秒前
一路畅通accept完成签到,获得积分10
16秒前
潇湘学术完成签到,获得积分10
16秒前
烂漫的如冬完成签到,获得积分10
17秒前
koi发布了新的文献求助10
17秒前
19秒前
19秒前
罗小马完成签到 ,获得积分10
19秒前
高分求助中
【提示信息,请勿应助】关于scihub 10000
Les Mantodea de Guyane: Insecta, Polyneoptera [The Mantids of French Guiana] 3000
徐淮辽南地区新元古代叠层石及生物地层 3000
The Mother of All Tableaux: Order, Equivalence, and Geometry in the Large-scale Structure of Optimality Theory 3000
Global Eyelash Assessment scale (GEA) 1000
Picture Books with Same-sex Parented Families: Unintentional Censorship 550
Research on Disturbance Rejection Control Algorithm for Aerial Operation Robots 500
热门求助领域 (近24小时)
化学 材料科学 医学 生物 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 遗传学 基因 物理化学 催化作用 冶金 细胞生物学 免疫学
热门帖子
关注 科研通微信公众号,转发送积分 4038619
求助须知:如何正确求助?哪些是违规求助? 3576294
关于积分的说明 11375058
捐赠科研通 3306084
什么是DOI,文献DOI怎么找? 1819374
邀请新用户注册赠送积分活动 892698
科研通“疑难数据库(出版商)”最低求助积分说明 815066