Unsupervised learning for mental stress detection exploration of self-organizing maps

Dorien Huysmans, Elena Smets, Walter De Raedt, Chris Van Hoof, Katleen Bogaerts, Ilse Van Diest, Denis Helic

    Publikation: Beitrag in Buch/Bericht/KonferenzbandBeitrag in einem KonferenzbandForschungBegutachtung

    Abstract

    One of the major challenges in the field of ambulant stress detection lies in the model validation. Commonly, different types of questionnaires are used to record perceived stress levels. These only capture stress levels at discrete moments in time and are prone to subjective inaccuracies. Although, many studies have already reported such issues, a solution for these difficulties is still lacking. This paper explores the potential of unsupervised learning with Self-Organizing Maps (SOM) for stress detection. In unsupervised learning settings, the labels from perceived stress levels are not needed anymore. First, a controlled stress experiment was conducted during which relax and stress phases were alternated. The skin conductance (SC) and electrocardiogram (ECG) of test subjects were recorded. Then, the structure of the SOM was built based on a training set of SC and ECG features. A Gaussian Mixture Model was used to cluster regions of the SOM with similar characteristics. Finally, by comparison of features values within each cluster, two clusters could be associated to either relax phases or stress phases. A classification performance of 79.0% (±5.16) was reached with a sensitivity of 75.6% (±11.2). In the future, the goal is to transfer these first initial results from a controlled laboratory setting to an ambulant environment.

    Originalspracheenglisch
    TitelBIOSIGNALS 2018 - 11th International Conference on Bio-Inspired Systems and Signal Processing, Proceedings; Part of 11th International Joint Conference on Biomedical Engineering Systems and Technologies, BIOSTEC 2018
    Herausgeber (Verlag)SciTePress 2013
    Seiten26-35
    Seitenumfang10
    Band4
    ISBN (elektronisch)9789897582790
    PublikationsstatusVeröffentlicht - 1 Jan 2018
    Veranstaltung11th International Conference on Bio-Inspired Systems and Signal Processing, BIOSIGNALS 2018 - Part of 11th International Joint Conference on Biomedical Engineering Systems and Technologies, BIOSTEC 2018 - Funchal, Madeira, Portugal
    Dauer: 19 Jan 201821 Jan 2018

    Konferenz

    Konferenz11th International Conference on Bio-Inspired Systems and Signal Processing, BIOSIGNALS 2018 - Part of 11th International Joint Conference on Biomedical Engineering Systems and Technologies, BIOSTEC 2018
    LandPortugal
    OrtFunchal, Madeira
    Zeitraum19/01/1821/01/18

    Fingerprint

    Unsupervised learning
    Self organizing maps
    Electrocardiography
    Skin
    Labels
    Experiments

    Schlagwörter

      ASJC Scopus subject areas

      • !!Signal Processing
      • !!Biomedical Engineering
      • !!Electrical and Electronic Engineering

      Dies zitieren

      Huysmans, D., Smets, E., De Raedt, W., Van Hoof, C., Bogaerts, K., Van Diest, I., & Helic, D. (2018). Unsupervised learning for mental stress detection exploration of self-organizing maps. in BIOSIGNALS 2018 - 11th International Conference on Bio-Inspired Systems and Signal Processing, Proceedings; Part of 11th International Joint Conference on Biomedical Engineering Systems and Technologies, BIOSTEC 2018 (Band 4, S. 26-35). SciTePress 2013.

      Unsupervised learning for mental stress detection exploration of self-organizing maps. / Huysmans, Dorien; Smets, Elena; De Raedt, Walter; Van Hoof, Chris; Bogaerts, Katleen; Van Diest, Ilse; Helic, Denis.

      BIOSIGNALS 2018 - 11th International Conference on Bio-Inspired Systems and Signal Processing, Proceedings; Part of 11th International Joint Conference on Biomedical Engineering Systems and Technologies, BIOSTEC 2018. Band 4 SciTePress 2013, 2018. S. 26-35.

      Publikation: Beitrag in Buch/Bericht/KonferenzbandBeitrag in einem KonferenzbandForschungBegutachtung

      Huysmans, D, Smets, E, De Raedt, W, Van Hoof, C, Bogaerts, K, Van Diest, I & Helic, D 2018, Unsupervised learning for mental stress detection exploration of self-organizing maps. in BIOSIGNALS 2018 - 11th International Conference on Bio-Inspired Systems and Signal Processing, Proceedings; Part of 11th International Joint Conference on Biomedical Engineering Systems and Technologies, BIOSTEC 2018. Bd. 4, SciTePress 2013, S. 26-35, Funchal, Madeira, Portugal, 19/01/18.
      Huysmans D, Smets E, De Raedt W, Van Hoof C, Bogaerts K, Van Diest I et al. Unsupervised learning for mental stress detection exploration of self-organizing maps. in BIOSIGNALS 2018 - 11th International Conference on Bio-Inspired Systems and Signal Processing, Proceedings; Part of 11th International Joint Conference on Biomedical Engineering Systems and Technologies, BIOSTEC 2018. Band 4. SciTePress 2013. 2018. S. 26-35
      Huysmans, Dorien ; Smets, Elena ; De Raedt, Walter ; Van Hoof, Chris ; Bogaerts, Katleen ; Van Diest, Ilse ; Helic, Denis. / Unsupervised learning for mental stress detection exploration of self-organizing maps. BIOSIGNALS 2018 - 11th International Conference on Bio-Inspired Systems and Signal Processing, Proceedings; Part of 11th International Joint Conference on Biomedical Engineering Systems and Technologies, BIOSTEC 2018. Band 4 SciTePress 2013, 2018. S. 26-35
      @inproceedings{5b46f99bbc2542468311a59d4e8f3562,
      title = "Unsupervised learning for mental stress detection exploration of self-organizing maps",
      abstract = "One of the major challenges in the field of ambulant stress detection lies in the model validation. Commonly, different types of questionnaires are used to record perceived stress levels. These only capture stress levels at discrete moments in time and are prone to subjective inaccuracies. Although, many studies have already reported such issues, a solution for these difficulties is still lacking. This paper explores the potential of unsupervised learning with Self-Organizing Maps (SOM) for stress detection. In unsupervised learning settings, the labels from perceived stress levels are not needed anymore. First, a controlled stress experiment was conducted during which relax and stress phases were alternated. The skin conductance (SC) and electrocardiogram (ECG) of test subjects were recorded. Then, the structure of the SOM was built based on a training set of SC and ECG features. A Gaussian Mixture Model was used to cluster regions of the SOM with similar characteristics. Finally, by comparison of features values within each cluster, two clusters could be associated to either relax phases or stress phases. A classification performance of 79.0{\%} (±5.16) was reached with a sensitivity of 75.6{\%} (±11.2). In the future, the goal is to transfer these first initial results from a controlled laboratory setting to an ambulant environment.",
      keywords = "Electrocardiogram, Mental Stress Detection, Skin Conductance, SOM, Unsupervised Learning",
      author = "Dorien Huysmans and Elena Smets and {De Raedt}, Walter and {Van Hoof}, Chris and Katleen Bogaerts and {Van Diest}, Ilse and Denis Helic",
      year = "2018",
      month = "1",
      day = "1",
      language = "English",
      volume = "4",
      pages = "26--35",
      booktitle = "BIOSIGNALS 2018 - 11th International Conference on Bio-Inspired Systems and Signal Processing, Proceedings; Part of 11th International Joint Conference on Biomedical Engineering Systems and Technologies, BIOSTEC 2018",
      publisher = "SciTePress 2013",

      }

      TY - GEN

      T1 - Unsupervised learning for mental stress detection exploration of self-organizing maps

      AU - Huysmans, Dorien

      AU - Smets, Elena

      AU - De Raedt, Walter

      AU - Van Hoof, Chris

      AU - Bogaerts, Katleen

      AU - Van Diest, Ilse

      AU - Helic, Denis

      PY - 2018/1/1

      Y1 - 2018/1/1

      N2 - One of the major challenges in the field of ambulant stress detection lies in the model validation. Commonly, different types of questionnaires are used to record perceived stress levels. These only capture stress levels at discrete moments in time and are prone to subjective inaccuracies. Although, many studies have already reported such issues, a solution for these difficulties is still lacking. This paper explores the potential of unsupervised learning with Self-Organizing Maps (SOM) for stress detection. In unsupervised learning settings, the labels from perceived stress levels are not needed anymore. First, a controlled stress experiment was conducted during which relax and stress phases were alternated. The skin conductance (SC) and electrocardiogram (ECG) of test subjects were recorded. Then, the structure of the SOM was built based on a training set of SC and ECG features. A Gaussian Mixture Model was used to cluster regions of the SOM with similar characteristics. Finally, by comparison of features values within each cluster, two clusters could be associated to either relax phases or stress phases. A classification performance of 79.0% (±5.16) was reached with a sensitivity of 75.6% (±11.2). In the future, the goal is to transfer these first initial results from a controlled laboratory setting to an ambulant environment.

      AB - One of the major challenges in the field of ambulant stress detection lies in the model validation. Commonly, different types of questionnaires are used to record perceived stress levels. These only capture stress levels at discrete moments in time and are prone to subjective inaccuracies. Although, many studies have already reported such issues, a solution for these difficulties is still lacking. This paper explores the potential of unsupervised learning with Self-Organizing Maps (SOM) for stress detection. In unsupervised learning settings, the labels from perceived stress levels are not needed anymore. First, a controlled stress experiment was conducted during which relax and stress phases were alternated. The skin conductance (SC) and electrocardiogram (ECG) of test subjects were recorded. Then, the structure of the SOM was built based on a training set of SC and ECG features. A Gaussian Mixture Model was used to cluster regions of the SOM with similar characteristics. Finally, by comparison of features values within each cluster, two clusters could be associated to either relax phases or stress phases. A classification performance of 79.0% (±5.16) was reached with a sensitivity of 75.6% (±11.2). In the future, the goal is to transfer these first initial results from a controlled laboratory setting to an ambulant environment.

      KW - Electrocardiogram

      KW - Mental Stress Detection

      KW - Skin Conductance

      KW - SOM

      KW - Unsupervised Learning

      UR - http://www.scopus.com/inward/record.url?scp=85051748731&partnerID=8YFLogxK

      M3 - Conference contribution

      VL - 4

      SP - 26

      EP - 35

      BT - BIOSIGNALS 2018 - 11th International Conference on Bio-Inspired Systems and Signal Processing, Proceedings; Part of 11th International Joint Conference on Biomedical Engineering Systems and Technologies, BIOSTEC 2018

      PB - SciTePress 2013

      ER -