Abstract

We consider the characterization of muscle fatigue through a noninvasive sensing mechanism such as Surface ElectroMyoGraphy (SEMG). While changes in the properties of SEMG signals with respect to muscle fatigue have been reported in the literature, the large variation in these signals across different individuals makes the task of modeling and classification of SEMG signals challenging. Indeed, the variation in SEMG parameters from subject to subject creates differences in the data distribution. In this article, we propose two transfer learning frameworks based on the multisource domain adaptation methodology for detecting different stages of fatigue using SEMG signals, that addresses the distribution differences. In the proposed frameworks, the SEMG data of a subject represent a domain; data from multiple subjects in the training set form the multiple source domains and the test subject data form the target domain. SEMG signals are predominantly different in conditional probability distribution across subjects. The key feature of the first framework is a novel weighting scheme that addresses the conditional probability distribution differences across multiple domains (subjects) and the key feature of the second framework is a two-stage domain adaptation methodology which combines weighted data from multiple sources based on marginal probability differences (first stage) as well as conditional probability differences (second stage), with the target domain data. The weights for minimizing the marginal probability differences are estimated independently, while the weights for minimizing conditional probability differences are computed simultaneously by exploiting the potential interaction among multiple sources. We also provide a theoretical analysis on the generalization performance of the proposed multisource domain adaptation formulation using the weighted Rademacher complexity measure. We have validated the proposed frameworks on Surface ElectroMyoGram signals collected from 8 people during a fatigue-causing repetitive gripping activity. Comprehensive experiments on the SEMG dataset demonstrate that the proposed method improves the classification accuracy by 20% to 30% over the cases without any domain adaptation method and by 13% to 30% over existing state-of-the-art domain adaptation methods.

Original languageEnglish (US)
Article number18
JournalACM Transactions on Knowledge Discovery from Data
Volume6
Issue number4
DOIs
StatePublished - Dec 2012

Fingerprint

Electromyography
Fatigue of materials
Probability distributions
Muscle

Keywords

  • Multisource domain adaption
  • Subject-based variability
  • Surface electromyogram
  • Transfer learning

ASJC Scopus subject areas

  • Computer Science(all)

Cite this

Multisource domain adaptation and its application to early detection of fatigue. / Chattopadhyay, Rita; Sun, Qian; Fan, Wei; Davidson, Ian; Panchanathan, Sethuraman; Ye, Jieping.

In: ACM Transactions on Knowledge Discovery from Data, Vol. 6, No. 4, 18, 12.2012.

Research output: Contribution to journalArticle

Chattopadhyay, Rita ; Sun, Qian ; Fan, Wei ; Davidson, Ian ; Panchanathan, Sethuraman ; Ye, Jieping. / Multisource domain adaptation and its application to early detection of fatigue. In: ACM Transactions on Knowledge Discovery from Data. 2012 ; Vol. 6, No. 4.
@article{d9e71f2bfc3648bc8c4ef3f666551c63,
title = "Multisource domain adaptation and its application to early detection of fatigue",
abstract = "We consider the characterization of muscle fatigue through a noninvasive sensing mechanism such as Surface ElectroMyoGraphy (SEMG). While changes in the properties of SEMG signals with respect to muscle fatigue have been reported in the literature, the large variation in these signals across different individuals makes the task of modeling and classification of SEMG signals challenging. Indeed, the variation in SEMG parameters from subject to subject creates differences in the data distribution. In this article, we propose two transfer learning frameworks based on the multisource domain adaptation methodology for detecting different stages of fatigue using SEMG signals, that addresses the distribution differences. In the proposed frameworks, the SEMG data of a subject represent a domain; data from multiple subjects in the training set form the multiple source domains and the test subject data form the target domain. SEMG signals are predominantly different in conditional probability distribution across subjects. The key feature of the first framework is a novel weighting scheme that addresses the conditional probability distribution differences across multiple domains (subjects) and the key feature of the second framework is a two-stage domain adaptation methodology which combines weighted data from multiple sources based on marginal probability differences (first stage) as well as conditional probability differences (second stage), with the target domain data. The weights for minimizing the marginal probability differences are estimated independently, while the weights for minimizing conditional probability differences are computed simultaneously by exploiting the potential interaction among multiple sources. We also provide a theoretical analysis on the generalization performance of the proposed multisource domain adaptation formulation using the weighted Rademacher complexity measure. We have validated the proposed frameworks on Surface ElectroMyoGram signals collected from 8 people during a fatigue-causing repetitive gripping activity. Comprehensive experiments on the SEMG dataset demonstrate that the proposed method improves the classification accuracy by 20{\%} to 30{\%} over the cases without any domain adaptation method and by 13{\%} to 30{\%} over existing state-of-the-art domain adaptation methods.",
keywords = "Multisource domain adaption, Subject-based variability, Surface electromyogram, Transfer learning",
author = "Rita Chattopadhyay and Qian Sun and Wei Fan and Ian Davidson and Sethuraman Panchanathan and Jieping Ye",
year = "2012",
month = "12",
doi = "10.1145/2382577.2382582",
language = "English (US)",
volume = "6",
journal = "ACM Transactions on Knowledge Discovery from Data",
issn = "1556-4681",
publisher = "Association for Computing Machinery (ACM)",
number = "4",

}

TY - JOUR

T1 - Multisource domain adaptation and its application to early detection of fatigue

AU - Chattopadhyay, Rita

AU - Sun, Qian

AU - Fan, Wei

AU - Davidson, Ian

AU - Panchanathan, Sethuraman

AU - Ye, Jieping

PY - 2012/12

Y1 - 2012/12

N2 - We consider the characterization of muscle fatigue through a noninvasive sensing mechanism such as Surface ElectroMyoGraphy (SEMG). While changes in the properties of SEMG signals with respect to muscle fatigue have been reported in the literature, the large variation in these signals across different individuals makes the task of modeling and classification of SEMG signals challenging. Indeed, the variation in SEMG parameters from subject to subject creates differences in the data distribution. In this article, we propose two transfer learning frameworks based on the multisource domain adaptation methodology for detecting different stages of fatigue using SEMG signals, that addresses the distribution differences. In the proposed frameworks, the SEMG data of a subject represent a domain; data from multiple subjects in the training set form the multiple source domains and the test subject data form the target domain. SEMG signals are predominantly different in conditional probability distribution across subjects. The key feature of the first framework is a novel weighting scheme that addresses the conditional probability distribution differences across multiple domains (subjects) and the key feature of the second framework is a two-stage domain adaptation methodology which combines weighted data from multiple sources based on marginal probability differences (first stage) as well as conditional probability differences (second stage), with the target domain data. The weights for minimizing the marginal probability differences are estimated independently, while the weights for minimizing conditional probability differences are computed simultaneously by exploiting the potential interaction among multiple sources. We also provide a theoretical analysis on the generalization performance of the proposed multisource domain adaptation formulation using the weighted Rademacher complexity measure. We have validated the proposed frameworks on Surface ElectroMyoGram signals collected from 8 people during a fatigue-causing repetitive gripping activity. Comprehensive experiments on the SEMG dataset demonstrate that the proposed method improves the classification accuracy by 20% to 30% over the cases without any domain adaptation method and by 13% to 30% over existing state-of-the-art domain adaptation methods.

AB - We consider the characterization of muscle fatigue through a noninvasive sensing mechanism such as Surface ElectroMyoGraphy (SEMG). While changes in the properties of SEMG signals with respect to muscle fatigue have been reported in the literature, the large variation in these signals across different individuals makes the task of modeling and classification of SEMG signals challenging. Indeed, the variation in SEMG parameters from subject to subject creates differences in the data distribution. In this article, we propose two transfer learning frameworks based on the multisource domain adaptation methodology for detecting different stages of fatigue using SEMG signals, that addresses the distribution differences. In the proposed frameworks, the SEMG data of a subject represent a domain; data from multiple subjects in the training set form the multiple source domains and the test subject data form the target domain. SEMG signals are predominantly different in conditional probability distribution across subjects. The key feature of the first framework is a novel weighting scheme that addresses the conditional probability distribution differences across multiple domains (subjects) and the key feature of the second framework is a two-stage domain adaptation methodology which combines weighted data from multiple sources based on marginal probability differences (first stage) as well as conditional probability differences (second stage), with the target domain data. The weights for minimizing the marginal probability differences are estimated independently, while the weights for minimizing conditional probability differences are computed simultaneously by exploiting the potential interaction among multiple sources. We also provide a theoretical analysis on the generalization performance of the proposed multisource domain adaptation formulation using the weighted Rademacher complexity measure. We have validated the proposed frameworks on Surface ElectroMyoGram signals collected from 8 people during a fatigue-causing repetitive gripping activity. Comprehensive experiments on the SEMG dataset demonstrate that the proposed method improves the classification accuracy by 20% to 30% over the cases without any domain adaptation method and by 13% to 30% over existing state-of-the-art domain adaptation methods.

KW - Multisource domain adaption

KW - Subject-based variability

KW - Surface electromyogram

KW - Transfer learning

UR - http://www.scopus.com/inward/record.url?scp=84878555728&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84878555728&partnerID=8YFLogxK

U2 - 10.1145/2382577.2382582

DO - 10.1145/2382577.2382582

M3 - Article

VL - 6

JO - ACM Transactions on Knowledge Discovery from Data

JF - ACM Transactions on Knowledge Discovery from Data

SN - 1556-4681

IS - 4

M1 - 18

ER -