没有合适的资源?快使用搜索试试~ 我知道了~
文献笔记2Multi-source domain adaptation
需积分: 0 3 下载量 93 浏览量
2023-09-30
15:54:50
上传
评论
收藏 1.43MB PDF 举报
温馨提示
试读
13页
《Multi-source domain adaptation for decoder calibration of intracortical brain-machine interface》
资源推荐
资源详情
资源评论
Journal of Neural Engineering
PAPER
Multi-source domain adaptation for decoder calibration of intracortical
brain-machine interface
To cite this article: Wei Li et al 2020 J. Neural Eng. 17 066009
View the article online for updates and enhancements.
This content was downloaded from IP address 222.20.32.207 on 14/12/2020 at 11:08
J. Neural Eng. 17 (2020) 066009 https://doi.org/10.1088/1741-2552/abc528
Journal of Neural Engineering
REC E IVE D
5 April 2020
REV I SED
3 September 2020
AC C E PTED FOR P U B LICAT I O N
27 October 2020
PUBLI S HED
19 November 2020
PAPER
Multi-source domain adaptation for decoder calibration
of intracortical brain-machine interface
Wei Li
1
, Shaohua Ji
1
, Xi Chen
1
, Bo Kuai
3
, Jiping He
4
, Peng Zhang
2
and Qiang Li
2
1
School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan 430074,
People’s Republic of China
2
Wuhan National Laboratory for Optoelectronics, Huazhong University of Science and Technology, Wuhan 430074,
People’s Republic of China
3
School of industrial design, Hubei university of technology, Wuhan 430068, People’s Republic of China
4
Center for Neural Interface Design, Harrington Department of Bioengineering, Arizona State University, Tempe, AZ 85287,
United States of America
E-mail: [email protected]
Keywords: intracortical brain-machine interface, domain adaptation, multi-source domain adaptation, decoder calibration
Abstract
Objective. For nonstationarity of neural recordings, daily retraining is required in the decoder
calibration of intracortical brain-machine interfaces (iBMIs). Domain adaptation (DA) has started
to be applied in iBMIs to solve the problem of daily retraining by taking advantage of historical
data. However, previous DA studies used only a single source domain, which might lead to
performance instability. In this study, we proposed a multi-source DA algorithm, by fully utilizing
the historical data, to achieve a better and more robust decoding performance while reducing the
decoder calibration time. Approach. The neural signals were recorded from two rhesus macaques
using intracortical electrodes to decode the reaching and grasping movements. A principal
component analysis (PCA)-based multi-source domain adaptation (PMDA) algorithm was
proposed to apply the feature transfer to diminish the disparities between the target domain and
each source domain. Moreover, the multiple weighted sub-classifiers based on multi-source
domain data and small current sample set were constructed to accomplish the decoding.
Main results. Our algorithm was able to make use of the multi-source domain data and achieve
better and more robust decoding performance compared with other methods. Only a small current
sample set was needed by our algorithm in order for the decoder calibration time to be effectively
reduced. Significance. (1) The idea of the multi-source DA was introduced into the iBMIs to solve
the problem of time consumption in the daily decoder retraining. (2) Instead of using only
single-source domain data in the previous study, our algorithm made use of multi-day historical
data, resulting in better and more robust decoding performance. (3) Our algorithm could be
accomplished with only a small current sample set, and it can effectively reduce the decoder
calibration time, which is important for further clinical applications.
1. Introduction
Intracortical brain-machine interfaces (iBMIs) aim
to restore the motor functions of people with severe
paralysis by translating neural signals into motor
commands to control assistant devices such as pros-
thesis, computer cursor, and virtual keyboard [1–3].
Typically, users need to collect new training samples,
named current data in the following, to recalibrate
the decoder before using the iBMIs properly [4–8].
In normal machine learning algorithms, it is assumed
that the training and testing data are drawn from
a same sample distribution [9, 10]. However, for
the nonstationarity of the recorded neural signals
[5, 6, 11, 12], there are disparities between the histor-
ical and current data, and the decoder calibrated by
the former cannot accurately decode the latter; thus,
daily retraining is required to maintain the perform-
ance of the decoding [13, 14]. Therefore, reducing the
calibration time or collection time for new calibra-
tion samples is important in promoting the clinical
application of iBMIs [15, 16].
© 2020 IOP Publishing Ltd
J. Neural Eng. 17 (2020) 066009 W Li et al
To reduce the time required to collect new
samples, an efficient method is to take advantage
of the historical data to reduce the demand for
new samples. There may be three main solutions,
one way is to design an adaptive decoder which
can complete initial calibration by the historical
data and then self-recalibrate during the decoding
[16, 17]. Bishop et al developed a probabilistic self-
recalibrating classifier which could maintain stable
day-to-day performance without any daily supervised
retraining [17]. Jarosiewicz et al proposed a retro-
spective target inference-based decoder which could
achieve stable neural control quality for long periods
of self-paced iBMI use without the need for disruptive
recalibration tasks [16]. For the adaptive decoder, no
new current data need to be collected before iBMIs
using, however, the self-recalibration of the adapt-
ive decoder during the decoding will take some cal-
ibration time and increase computational burden.
Another way is using a more powerful decoder based
on deep neural network, which has good generaliza-
tion ability to deal with the nonstationarity. Sussillo
et al developed a new multiplicative recurrent neural
network iBMI decoder that successfully learned a
large variety of neural-to-kinematic mappings and
achieve more robust decoding performance for differ-
ent datasets [18]. This method needs a large amount
of historical data to finish the training of the decoder.
The last way is aligning the current data to the his-
torical data to diminish the nonstationarity. This way
tries to diminish the disparities between the historical
(source domain) and current data (target domain) in
order for the decoder calibrated by plenty of historical
data from the source domain to be generalized to the
target domain [19]. This is a typical domain adapta-
tion (DA) task [9, 10]. After aligning the current data
to the historical data, the decoder calibrated by the
aligned historical data can decode the aligned current
data properly without requiring additional recalibra-
tion. Therefore, we focused on this way in this study.
In the DA, the feature spaces of the source and
target domains are the same but have different mar-
ginal probability distributions. DA approaches can
handle the disparities between the source and tar-
get domains, and effectively apply knowledge learned
from the source to target domain [5, 20, 21]. DA
has been widely used in machine learning research,
such as computer vision [22, 23], natural language
processing [24, 25], bioinformatics [26–28]. In recent
years, DA has been applied to iBMIs, and some stud-
ies have been presented. Our previous study pro-
posed a principal component analysis (PCA)-based
domain adaptation (PDA) method to calibrate the
decoder [5]. Taking advantage of historical data from
the previous day, we used small current sample
set to calibrate the decoder and achieved favorable
performance. Dyer et al introduced a distribution-
alignment decoding method (DAD) which found a
low-dimensional mapping of current neural activities
to match the distribution of historical motor variables
by minimizing their Kullback–Leibler divergence
[29]. Lee et al proposed a hierarchical formulation
of optimal transport which leveraged clustered struc-
ture in data to improve alignment and could achieve
better performance than the DAD method [30].
Pandarinath et al proposed a latent factor analysis
via dynamical systems (LFADs) which used artifi-
cial recurrent neural networks to infer latent dynam-
ics from single-trial neural spiking data and could
accurately predict motor variables [31]. Similar to
the LFADs, Farshchian et al proposed an adversarial
domain adaptation network (ADAN) based on Gen-
erative Adversarial Network, which could align neural
recordings from different days [32]. Comparing with
two other methods (canonical correlation analysis
(CCA) and Kullback–Leibler divergence minimiza-
tion) proposed in the same study, the ADAN achieved
the best performance. The CCA was also used in
another study to extract stable low-dimensional latent
dynamics across different days [33]. Degenhart et al
proposed a manifold-based stabilizer to align estim-
ates of the manifold obtained from nonstationary
neural recordings from different days, which could
maintain iBMI performance in the presence of neural
recording instabilities [34].
These DA methods could effectively diminish the
disparities between the source and target domain
to maintain robust decoding performance. However,
most methods described above need to collect suf-
ficient target samples for finishing the alignment,
which will affect the real-time performance in online
decoding. Moreover, these methods either use only a
single-day historical dataset as the source domain or
combine the historical data from multi-days together
to be one source domain, they do not consider multi-
source domains by using each single-day historical
dataset separately as a source domain. Taking the PDA
method as an example, the PDA is a single source DA
method that only uses historical data from the pre-
vious day as the source domain. It works under the
assumption that data from the previous day is the
most similar to the target domain among all histor-
ical data [5]. However, this assumption is not always
satisfied because the nonstationarity of neural sig-
nals is unpredictable. If this assumption is not satis-
fied, using other source domains may achieve better
performance, which is also the case for other meth-
ods. Therefore, choosing the historical dataset that is
the most similar to the target domain or maximiz-
ing their use to achieve better and more robust per-
formance needs further study. Finally, most studies
described above focus on continuous decoding, such
as decoding continuous hand velocity and move-
ment trajectory from neural signals [29–34]. While
continuous decoding is very important, construct-
ing classifiers to decode discrete actions is also an
important part of the iBMIs [17, 35]. In the applic-
ation of prosthetic hand control with the iBMI, the
2
剩余12页未读,继续阅读
资源评论
TianYU_DaRen
- 粉丝: 0
- 资源: 4
上传资源 快速赚钱
- 我的内容管理 展开
- 我的资源 快来上传第一个资源
- 我的收益 登录查看自己的收益
- 我的积分 登录查看自己的积分
- 我的C币 登录后查看C币余额
- 我的收藏
- 我的下载
- 下载帮助
最新资源
- rdf0412-kcu116-pcie-c-2019-1.zip(XILINX KCU116 源码)
- 基于C#语言的winform界面火车票订票系统(源码+实验报告)
- 【华为OD部分真题及讲解】华为OD部分真题及讲解
- 基于Python+Django的京东商品比价系统源码+全部资料(毕业设计).zip
- G460 G560 Z460 Z560的最新BIOS 2.18版(无白名单)
- MetaJUI v0.4
- 基于Python+Django的京东商品比价系统源码+全部资料(毕业设计).zip
- linux常用命令大全
- 立体相机标定-使用OpenCV+Cpp对立体相机进行标定-calibration-附项目源码+流程教程-优质项目实战.zip
- 基于SpringBoot+Mysql开发的酒店管理系统
资源上传下载、课程学习等过程中有任何疑问或建议,欢迎提出宝贵意见哦~我们会及时处理!
点击此处反馈
安全验证
文档复制为VIP权益,开通VIP直接复制
信息提交成功