Transfer learning on electromyography EMG tasks approaches and beyond Di Wu Jie Yang and Mohamad Sawan

2025-04-26 0 0 856.98KB 31 页 10玖币

侵权投诉

Transfer learning on electromyography (EMG) tasks:

approaches and beyond

Di Wu, Jie Yang, and Mohamad Sawan

Center of Excellence in Biomedical Research on Advanced Integrated-on-chips

Neurotechnologies, School of Engineering, Westlake University, Hangzhou, 310024, China

Institute of Advanced Technology, Westlake Institute for Advanced Study, Hangzhou,

310024, China

E-mail: yangjie@westlake.edu.cn, Sawan@westlake.edu.cn

Abstract. Objective. Machine learning on electromyography (EMG) has recently achieved

remarkable success on a variety of tasks, while such success relies heavily on the assumption

that the training and future data must be of the same data distribution. However, this

assumption may not hold in many real-world applications. Model calibration is required

via data re-collection and label annotation, which is generally very expensive and time-

consuming. To address this problem, transfer learning (TL), which aims to improve target

learners’ performance by transferring the knowledge from related source domains, is emerging

as a new paradigm to reduce the amount of calibration effort. Approach. In this survey,

we assess the eligibility of more than ﬁfty published peer-reviewed representative transfer

learning approaches for EMG applications. Main results. Unlike previous surveys on purely

transfer learning or EMG-based machine learning, this survey aims to provide an insight into

the biological foundations of existing transfer learning methods on EMG-related analysis. In

speciﬁc, we ﬁrst introduce the physiological structure of the muscles and the EMG generating

mechanism, and the recording of EMG to provide biological insights behind existing transfer

learning approaches. Further, we categorize existing research endeavors into data based,

model based, training scheme based, and adversarial based. Signiﬁcance. This survey

systematically summarizes and categorizes existing transfer learning approaches for EMG

related machine learning applications. In addition, we discuss possible drawbacks of existing

works and point out the future direction of better EMG transfer learning algorithms to enhance

practicality for real-world applications.

Keywords: Transfer learning, electromyography (EMG), machine learning, meta learning,

domain-adversarial neural networks (DANN), random forest, model ensemble, ﬁne-tuning,

gesture recognition.

1. Introduction

The human motor control system is a complex neural system that is crucial for daily human

activities. One way to study the human motor control system is to record the signal due

to muscle ﬁber contractions associated with human motor activities by means of either

arXiv:2210.06295v2 [eess.SP] 13 Oct 2022

inserting needle electrodes into the muscles or attaching electrodes onto the surface of the

skin. The signal obtained is referred to as electromyography (EMG). Given the location of

the electrodes, EMG is further divided into surface EMG (sEMG) and intramuscular EMG

(iEMG). Advancement in the analysis of EMG and machine learning has recently achieved

remarkable success enabling a wide variety of applications, including but not limited to

rehabilitation with prostheses [1], hand gesture recognition [2] and human-machine interfaces

(HMIs) [3].

The current success of applying deep learning onto EMG related tasks is largely conﬁned

to the following two assumptions, which are usually infeasible when it comes to real-world

EMG related scenarios:

1) Sufﬁcient amount of annotated training data. The growing capability and capacity

of deep neural networks (DNN) architectures are associated with million-scale labeled

data [4, 5]. Such high quality abundant labeled data are often limited, expensive, and

inaccessible in the domain of EMG analysis. On the one hand, EMG data annotation

requires expert knowledge. On the other hand, EMG data acquisition process is a

highly physical and time-consuming task that requires several days of collaboration from

multiple parties [6].

2) Training data and testing data are independent and identically distributed (i.i.d).

The performance of the model is largely affected by the distribution gap between the

training and testing datasets. The testing data might also refer to the data generated

during actual application usage after model deployment. Take hand gesture recognition,

for example. The model is only capable of giving accurate predictions with the exact

same positioning of the forearm of the test subject and the exact placement of the

electrodes.

As the distribution of data changes, models based on statistics need to be reconstructed

with newly collected training data. In many real-world applications, it is expensive and

impractical to recollect a large amount of training data and rebuild the models each time a

distribution change is observed. Transfer learning (TL), which emphasizes the transfer of

knowledge across domains, emerges as a promising machine learning solution for solving the

above problems. The notion of transfer learning is not new, Thorndike et al. [7] suggested that

the improvement over one task is beneﬁcial to the efﬁciency of learning other tasks given the

similarity exists between these two tasks. In practice, a person knowing how to ride a bicycle

can learn to ride a motorcycle faster than others since both tasks require balance keeping.

However, transfer learning for EMG related tasks has only been gaining attention with the

recent development of both DNN and HMIs. Existing surveys provide an overview of DNN

for EMG-based human machine interfaces [8], and transfer learning in general for various

machine learning tasks [9]. This survey focuses on the intersection of machine learning for

EMG and transfer learning via EMG biological foundations, providing insights into a novel

and growing area of research. Besides the analysis of recent deep learning works, we make

an attempt to explain the relationships and differences between non-deep learning and the

deep models, for these works usually share similar intuitions and observations. Some of the

previous non-deep learning works contain more biological signiﬁcance that can inspire further

DNN-based research in this ﬁeld. To consolidate these recent advances, we propose a new

taxonomy for transfer learning on EMG tasks, and also provide a collection of predominant

benchmark datasets following our taxonomy.

The main contributions of this paper are :

•Over ﬁfty representative up-to-date transfer learning approaches on EMG analysis are

summarized with organized categorization, presenting a comprehensive overview to the

readers.

•Delve deep into the generating mechanisms of EMG and bridge transfer learning

practices with the underlying biological foundation.

•Point out the technical limitations of current research and discuss promising directions

on transfer learning on EMG analysis to propose further studies.

The remainder of this paper is organized as follows. We introduce in section 2 the basics

of transfer learning, generation and acquisition of EMG and EMG transfer learning scenarios.

In Section 3, we ﬁrst provide the categorization of EMG transfer learning based on existing

works and then introduce in detail. We also give a summary of common used dataset in

Section 4. Lastly, we discuss existing methods and the future research direction of EMG

transfer learning.

2. Preliminaries

This section introduces the deﬁnitions of transfer learning, related concepts, and also the

basics of EMG, from how EMG signal is generated to how EMG signal is recorded. We also

summarize possible transfer scenarios in this section.

2.1. Transfer Learning

We ﬁrst give the deﬁnitions of a “domain” and a “task”, respectively. Deﬁne Dto be a domain

which consists of a feature space Xand a marginal probability distribution P(X), where X

is a set of data samples X= [xi]n

i=1. In particular, if two domains have different feature

spaces or marginal probability distributions, they differ from each other. Given a domain

D={X , P (X)}, a task is then represented by T={Y, f(·)}where f(·)denotes the

objective prediction function and Yis the label space associated with X. From the probability

point of view, f(x)can also be regarded as conditional probability distribution P(y|x). Two

tasks are considered different if they have different label spaces of different conditional

probability distributions. Then, transfer learning can be formally deﬁned as follows:

Deﬁnition 1 (Transfer Learning): Given a source learning task TSbased on a source

domain DS, transfer learning aims to help improve the learning of the target objective

prediction function fT(x)of the target task TSbased on the target domain DT, given that

DT6=DSor TS6=TT.

The above deﬁnition could be extended to multiple domains and tasks for both source and

target. In this survey, we only consider the case where there is one source domain DS, and one

target domain DT, as by far this is the most intensively studied transfer setup of the research

works in the literature. Based on different setups of the source and target domains and tasks,

transfer learning could be roughly categorized into inductive transfer learning,transductive

transfer learning and unsupervised transfer learning [10].

Deﬁnition 2 (Inductive Transfer Learning): Given a transfer learning task

(DS,TS,DT,TT, fT(x)). It is a inductive transfer learning task where the knowledge of (DS

and TSis used to improve the learning of the target objective prediction function fT(x)when

TS6=TT.

The target objective predictive function can be induced by using a few labeled data in the

target domain as the training data.

Deﬁnition 3 (Transductive Transfer Learning): Given a transfer learning task

(DS,TS,DT,TT, fT(x)). It is a transductive transfer learning task where the knowledge of

DSand TSis used to improve the learning of the target objective prediction function fT(x)

when DS6=DTand TS=TT.

For transductive transfer learning, the source and target tasks are the same, while the

source and target domain vary. Similar to the setting of transductive learning of traditional

machine learning [11], transductive transfer learning aims to make the best use of the given

unlabeled data in the target domain to adapt the objective predictive function learned in the

source domain, minimizing the expected error on the target domain. It is worth to notice that

domain adaptation is a special case where XS=XT,YS=YT,PS(y|X)6=PT(y|X)and/or

PS(X)6=PT(X).

Deﬁnition 4 (Unsupervised Transfer Learning): Given a transfer learning task

(DS,TS,DT,TT, fT(x)). It is an unsupervised transfer learning task where the knowledge

of DSand TSis used to improve the learning of the target objective prediction function fT(x)

with YSand YTnot observed.

Based on the above deﬁnition, no data annotation is accessible in both the source and

target domain during training. There has been little research conducted on this setting to date,

given its fully unsupervised nature in both domains.

2.2. EMG Basics

Motor Unit Action Potential. Amotor unit (MU) is deﬁned as one motor neuron and the

muscle ﬁbers that it innervates. During the contraction of a normal muscle, the muscle ﬁbers

of a motor unit are activated by its associated motor neuron. The membrane depolarization of

the muscle ﬁber is accompanied by ions movement and thus generates an electromagnetic ﬁeld

in the vicinity of the muscle ﬁber. The detected potential or voltage within the electromagnetic

ﬁeld is referred to as the ﬁber action potential. The amplitude of the ﬁber action potential is

related to the diameter of the corresponding muscle ﬁber and the distance to the recording

electrode. It is worth noticing that MU, by deﬁnition, refers to the anatomical motor unit

where the functional motor unit is of more research interest when it comes to real-world

Muscle Fiber

Skin

Muscle Fiber

Skin

Muscle Fiber

Skin

Muscle Fiber

Skin

sEMG

iEMG

(a) Bi-polar sEMG (b) Mono-polar sEMG

e1 e2 e1

Figure 1. Demonstration of EMG acquisition. The sEMG acquisition conﬁguration is shown

above the dotted line, with iEMG acquisition conﬁguration shown below the dotted line. The

triangle represents an ampliﬁer. For the bi-polar setup as in (a) and (c), two electrodes are

placed on the skin surface or inserted into muscle ﬁbers penetrating the skin surface. (b) and

(d) show the case of a mono-polar setup with one electrode attached to the skin or muscle ﬁber

and the other electrode connected to the ground or a reference point with no EMG (bones).

applications. The functional motor unit can be deﬁned as a group of muscle ﬁbers whose

action potentials occur within a very short time (two milliseconds). Intuitively, one could

consider a functional motor unit as a group of muscle ﬁbers that contract for one uniﬁed

functionality. From this point on, MU refers to a functional motor unit unless otherwise

speciﬁed. A Motor Unit Action Potential (MUAP) is deﬁned as the waveform consisting

of the superimposed (both temporally and spatially) action potentials from each individual

muscle ﬁber of the motor unit. The amplitude and shape of the MUAP is a unique indicator

of the properties of the MU (functionality, ﬁber arrangement, ﬁber diameter, etc.). MUs are

repeatedly activated so that muscle contraction is sustained for stable motor movement. The

repeated activation of MUs generates a sequence of MUAPs forming a Motor Unit Action

Potential Train (MUAPT).

Signal Recording. Based on the number of electrodes used during the recording of MUAPT,

the recording techniques could be divided into mono-polar and bi-polar conﬁgurations. As

shown in Figure 1, based on whether the electrodes are inserted directly into the muscles or

文档加载中……请稍候！
如果长时间未打开，您也可以点击刷新试试。

下载文档到电脑，查找使用更方便

10 玖币 0人已下载

立即下载

摘要：

Transferlearningonelectromyography(EMG)tasks:approachesandbeyondDiWu,JieYang,andMohamadSawanCenterofExcellenceinBiomedicalResearchonAdvancedIntegrated-on-chipsNeurotechnologies,SchoolofEngineering,WestlakeUniversity,Hangzhou,310024,ChinaInstituteofAdvancedTechnology,WestlakeInstituteforAdvancedStudy...

展开>> 收起<<

Transfer learning on electromyography EMG tasks approaches and beyond Di Wu Jie Yang and Mohamad Sawan.pdf

共31页,预览5页

还剩页未读，继续阅读

声明：本站为文档C2C交易模式，即用户上传的文档直接被用户下载，本站只是中间服务平台，本站所有文档下载所得的收益归上传人(含作者)所有。玖贝云文库仅提供信息存储空间，仅对用户上传内容的表现方式做保护处理，对上载内容本身不做任何修改或编辑。若文档所含内容侵犯了您的版权或隐私，请立即通知玖贝云文库，我们立即给予删除！

Transfer learning on electromyography EMG tasks approaches and beyond Di Wu Jie Yang and Mohamad Sawan

相关推荐

开通VIP享超值会员特权

作者详情

相关内容

热门标签

举报选择: