Active learning for electrodermal activity classification
To filter noise or detect features within physiological signals, it is often effective to encode expert knowledge into a model such as a machine learning classifier. However, training such a model can require much effort on the part of the researcher; this often takes the form of manually labeling p...
| Main Authors: | , , , , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Language: | en_US |
| Published: |
Institute of Electrical and Electronics Engineers (IEEE)
2017
|
| Online Access: | http://hdl.handle.net/1721.1/109392 https://orcid.org/0000-0002-8413-9469 https://orcid.org/0000-0003-4133-9230 https://orcid.org/0000-0002-9857-0188 https://orcid.org/0000-0002-5661-0022 |
| _version_ | 1826202845777494016 |
|---|---|
| author | Xia, Victoria F. Jaques, Natasha Mary Taylor, Sara Ann Fedor, Szymon Picard, Rosalind W. |
| author2 | Massachusetts Institute of Technology. Media Laboratory. Affective Computing Group |
| author_facet | Massachusetts Institute of Technology. Media Laboratory. Affective Computing Group Xia, Victoria F. Jaques, Natasha Mary Taylor, Sara Ann Fedor, Szymon Picard, Rosalind W. |
| author_sort | Xia, Victoria F. |
| collection | MIT |
| description | To filter noise or detect features within physiological signals, it is often effective to encode expert knowledge into a model such as a machine learning classifier. However, training such a model can require much effort on the part of the researcher; this often takes the form of manually labeling portions of signal needed to represent the concept being trained. Active learning is a technique for reducing human effort by developing a classifier that can intelligently select the most relevant data samples and ask for labels for only those samples, in an iterative process. In this paper we demonstrate that active learning can reduce the labeling effort required of researchers by as much as 84% for our application, while offering equivalent or even slightly improved machine learning performance. |
| first_indexed | 2024-09-23T12:21:47Z |
| format | Article |
| id | mit-1721.1/109392 |
| institution | Massachusetts Institute of Technology |
| language | en_US |
| last_indexed | 2024-09-23T12:21:47Z |
| publishDate | 2017 |
| publisher | Institute of Electrical and Electronics Engineers (IEEE) |
| record_format | dspace |
| spelling | mit-1721.1/1093922022-09-28T07:52:55Z Active learning for electrodermal activity classification Xia, Victoria F. Jaques, Natasha Mary Taylor, Sara Ann Fedor, Szymon Picard, Rosalind W. Massachusetts Institute of Technology. Media Laboratory. Affective Computing Group Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science Massachusetts Institute of Technology. Media Laboratory Program in Media Arts and Sciences (Massachusetts Institute of Technology) Xia, Victoria F. Jaques, Natasha Mary Taylor, Sara Ann Fedor, Szymon Picard, Rosalind W. To filter noise or detect features within physiological signals, it is often effective to encode expert knowledge into a model such as a machine learning classifier. However, training such a model can require much effort on the part of the researcher; this often takes the form of manually labeling portions of signal needed to represent the concept being trained. Active learning is a technique for reducing human effort by developing a classifier that can intelligently select the most relevant data samples and ask for labels for only those samples, in an iterative process. In this paper we demonstrate that active learning can reduce the labeling effort required of researchers by as much as 84% for our application, while offering equivalent or even slightly improved machine learning performance. MIT Media Lab Consortium Robert Wood Johnson Foundation 2017-05-26T19:27:35Z 2017-05-26T19:27:35Z 2016-02 2015-12 Article http://purl.org/eprint/type/ConferencePaper 978-1-5090-1350-0 http://hdl.handle.net/1721.1/109392 Xia, Victoria, Natasha Jaques, Sara Taylor, Szymon Fedor, and Rosalind Picard. “Active Learning for Electrodermal Activity Classification.” 2015 IEEE Signal Processing in Medicine and Biology Symposium (SPMB) (December 2015). https://orcid.org/0000-0002-8413-9469 https://orcid.org/0000-0003-4133-9230 https://orcid.org/0000-0002-9857-0188 https://orcid.org/0000-0002-5661-0022 en_US http://dx.doi.org/10.1109/SPMB.2015.7405467 2015 IEEE Signal Processing in Medicine and Biology Symposium (SPMB) Creative Commons Attribution-Noncommercial-Share Alike http://creativecommons.org/licenses/by-nc-sa/4.0/ application/pdf Institute of Electrical and Electronics Engineers (IEEE) MIT web domain |
| spellingShingle | Xia, Victoria F. Jaques, Natasha Mary Taylor, Sara Ann Fedor, Szymon Picard, Rosalind W. Active learning for electrodermal activity classification |
| title | Active learning for electrodermal activity classification |
| title_full | Active learning for electrodermal activity classification |
| title_fullStr | Active learning for electrodermal activity classification |
| title_full_unstemmed | Active learning for electrodermal activity classification |
| title_short | Active learning for electrodermal activity classification |
| title_sort | active learning for electrodermal activity classification |
| url | http://hdl.handle.net/1721.1/109392 https://orcid.org/0000-0002-8413-9469 https://orcid.org/0000-0003-4133-9230 https://orcid.org/0000-0002-9857-0188 https://orcid.org/0000-0002-5661-0022 |
| work_keys_str_mv | AT xiavictoriaf activelearningforelectrodermalactivityclassification AT jaquesnatashamary activelearningforelectrodermalactivityclassification AT taylorsaraann activelearningforelectrodermalactivityclassification AT fedorszymon activelearningforelectrodermalactivityclassification AT picardrosalindw activelearningforelectrodermalactivityclassification |