Advertisement

Brute Force ECG Feature Extraction Applied on Discomfort Detection

  • Guillermo Hidalgo Gadea
  • Annika Kreuder
  • Carsten Stahlschmidt
  • Sebastian Schnieder
  • Jarek Krajewski
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 762)

Abstract

This paper presents the idea of brute force feature extraction for Electrocardiography (ECG) signals applied to discomfort detection. To build an ECG Discomfort Corpus an experimental discomfort induction was conducted. 50 subjects underwent a 2 h (dis-)comfort condition in separate sessions in randomized order. ECG and subjective discomfort was recorded. 5 min ECG segments were labeled with corresponding subjective discomfort ratings, and 6365 brute force features (65 low-level descriptors, first and second order derivatives, and 47 functionals) and 11 traditional heart rate variability (HRV) parameters were extracted. Random Forest machine learning algorithm outperformed SVM and kNN approaches and achieved the best subject-dependent, 10-fold cross-validation results (\(r=.51\)). With this experiment, we are able to show that (a) brute force ECG feature sets achieved better discomfort detection than traditional HRV based ECG feature set; (b) cepstral and spectral flux based features appear to be the most promising to capture HRV phenomena.

Keywords

Affective computing ECG HRV Brute force feature extraction Machine learning Low-level descriptors Functionals 

References

  1. 1.
    Aha, D.W., Kibler, D., Albert, M.K.: Instance-based learning algorithms. Mach. Learn. 6(1), 37–66 (1991).  https://doi.org/10.1023/A:1022689900470CrossRefGoogle Scholar
  2. 2.
    Boussaa, M., Atouf, I., Atibi, M., Bennis, A.: ECG signals classification using MFCC coefficients and ANN classifier. In: Proceedings of 2016 International Conference on Electrical and Information Technologies, ICEIT 2016, pp. 480–484, May 2016.  https://doi.org/10.1109/EITech.2016.7519646
  3. 3.
    Breiman, L.: Random forests. Mach. Learn. 45(1), 5–32 (2001).  https://doi.org/10.1023/A:1010933404324CrossRefzbMATHGoogle Scholar
  4. 4.
    Datta, S., Puri, C., Mukherjee, A., Banerjee, R., Choudhury, A.D., Singh, R., Ukil, A., et al.: Identifying Normal, AF and other Abnormal ECG Rhythms using a cascaded binary classifier. Comput. Cardiol. 44, 2–5 (2017).  https://doi.org/10.22489/CinC.2017.173-154CrossRefGoogle Scholar
  5. 5.
    Eyben, F.: Real-time Speech and Music Classification by Large Audio Feature Space Extraction (2016).  https://doi.org/10.1007/978-3-319-27299-3CrossRefGoogle Scholar
  6. 6.
    Eyben, F., Wöllmer, M., and Schuller, B.: Opensmile: the munich versatile and fast open-source audio feature extractor. In: Proceedings of ACM Multimedia, pp. 1459–1462 (2010).  https://doi.org/10.1145/1873951.1874246
  7. 7.
    movisens GmbH: Data analyzer sensor data analysis. Technical report (2018)Google Scholar
  8. 8.
    Hall, M., National, H., Frank, E., Holmes, G., Pfahringer, B., Reutemann, P., Witten, I.H.: The WEKA data mining software: an update. ACM SIGKDD Explor. Newslett. 11(1), 10–18 (2009).  https://doi.org/10.1145/1656274.1656278CrossRefGoogle Scholar
  9. 9.
    Hidalgo Gadea, G.: Fatigue detection based on multimodal biosignal processing. Thesis. Bergische Universität Wuppertal (2017).  https://doi.org/10.13140/RG.2.2.29666.63684
  10. 10.
    Jang, E.H., Cho, H.Y., Kim, S.H., Eum, Y., Sohn, J.H.: Reliability of physiological signals induced by sadness and disgust. In: HUSO 2015: The First International Conference on Human and Social Analytics, pp. 35–36. IARIA (2015)Google Scholar
  11. 11.
    Koelstra, S., Muhl, C., Soleymani, M., Lee, J.-S., Yazdani, A., Ebrahimi, T., Pun, T., et al.: DEAP: a database for emotion analysis; usingphysiological signals. IEEE Trans. Affect. Comput. 3(1), 18–31 (2012).  https://doi.org/10.1109/T-AFFC.2011.15CrossRefGoogle Scholar
  12. 12.
    Koenig, J., Jarczok, M., Ellis, R., Hillecke, T., Thayer, J.: Heart rate variability and experimentally induced pain in healthy adults: a systematic review. Eur. J. Pain 18(3), 301–314 (2014).  https://doi.org/10.1002/j.1532-2149.2013.00379.xCrossRefGoogle Scholar
  13. 13.
    Krajewski, J., Schnieder, S., Sommer, D., Batliner, A., Schuller, B.: Applying multiple classifiers and non-linear dynamics features for detection sleepiness from speech. Neurocomputing 84, 65–75 (2012).  https://doi.org/10.1016/j.neucom.2011.12.021CrossRefGoogle Scholar
  14. 14.
    Laborde, S., Mosley, E., Thayer, J.F.: Heart rate variability and cardiac vagal tone in psychophysiological research - recommendations for experiment planning, data analysis, and data reporting. Front. Psychol. 8, 1–18 (2017).  https://doi.org/10.3389/fpsyg.2017.00213CrossRefGoogle Scholar
  15. 15.
    Michail, E., Kokonozi, A., Chouvarda, I., Maglaveras, N.: EEG and HRV markers of sleepiness and loss of control during car driving. In: 30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, pp. 2566–2569 (2008).  https://doi.org/10.1109/IEMBS.2008.4649724
  16. 16.
    Moody, G.B., Mark, R.G., Goldberger, A.L.: PhysioNet: a web-based resource for the study of physiologic signals. IEEE Eng. Med. Biol. Mag. 20(3), 70–75 (2001).  https://doi.org/10.1109/51.932728CrossRefGoogle Scholar
  17. 17.
    Nkurikiyeyezu, K.N., Suzuki, Y., Lopez, G.F.: Heart rate variability as a predictive biomarker of thermal comfort. J. Ambient Intell. Humaniz. Comput. (2017).  https://doi.org/10.1007/s12652-017-0567-4CrossRefGoogle Scholar
  18. 18.
    Parent, F., Dansereau, J., Lacoste, M., Aissaoui, R.: Evaluation of the new flexible contour backrest for wheelchairs. J. Rehabil. Res. Dev. 37(3), 325–333 (2000)Google Scholar
  19. 19.
    Pearson, E.J.M.: Comfort and its measurement - a literature review. Disabil. Rehabil. Assistive Technol. 4(5), 301–310 (2009).  https://doi.org/10.1080/17483100902980950CrossRefGoogle Scholar
  20. 20.
    Platt, J.: Probabilistic outputs for support vector machines and comparisons to regularized likelihood methods. Adv. Large Margin Classifiers 10(3), 61–74 (1999). http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.41.1639
  21. 21.
    Poria, S., Cambria, E., Bajpai, R., Hussain, A.: A review of affective computing: From unimodal analysis to multimodal fusion. Inf. Fusion 37, 98–125 (2017).  https://doi.org/10.1016/j.inffus.2017.02.003CrossRefGoogle Scholar
  22. 22.
    Prinsloo, G.E., Rauch, H.G.L., Lambert, M.I., Muench, F., Noakes, T.D., Derman, W.E.: The effect of short duration heart rate variability (HRV) biofeedback on cognitive performance during laboratory induced cognitive stress. Appl. Cogn. Psychol. 25(5), 792–801 (2011).  https://doi.org/10.1002/acp.1750CrossRefGoogle Scholar
  23. 23.
    Schuller, B., Steidl, S., Batliner, A., Vinciarelli, A., Scherer, K., Ringeval, F., Chetouani, M., et al.: The INTERSPEECH 2013 computational paralinguistics challenge: Social signals, conflict, emotion, autism. In: Proceedings of the Annual Conference of the International Speech Communication Association, pp. 148–152 (2013)Google Scholar
  24. 24.
    Steidl, S., Batliner, A., Bergelson, E., Krajewski, J., Janott, C., Amatuni, A., Casillas, M., et al.: The computational paralinguistics challenge. In: Interspeech 2017, pp. 1–5 (2017).  https://doi.org/10.21437/Interspeech.2017-43
  25. 25.
    Sudarshan, V.K., Acharya, U., Oh, S.L., Adam, M., Tan, J.H., Chua, C.K., Chua, K.P., et al.: Automated diagnosis of congestive heart failure using dual tree complex wavelet transform and statistical features extracted from 2 s of ECG signals. Comput. Biol. Med. 83, 48–58 (2017).  https://doi.org/10.1016/j.compbiomed.2017.01.019CrossRefGoogle Scholar
  26. 26.
    Valstar, M., Gratch, J., Schuller, B., Ringeval, F., Lalanne, D., Torres, M.T., Scherer, S., et al.: AVEC 2016 - Depression, Mood, and Emotion Recognition Workshop and Challenge (2016).  https://doi.org/10.1145/2988257.2988258
  27. 27.
    Wachter, R., Gröschel, K., Gelbrich, G., Hamann, G.F., Kermer, P., Liman, J., Seegers, J., et al.: Holter-electrocardiogram-monitoring in patients with acute ischaemic stroke: an open-label randomised controlled trial. Lancet Neurol. 16(4), 282–290 (2017).  https://doi.org/10.1016/S1474-4422(17)30002-9CrossRefGoogle Scholar

Copyright information

© Springer International Publishing AG, part of Springer Nature 2019

Authors and Affiliations

  • Guillermo Hidalgo Gadea
    • 1
    • 2
  • Annika Kreuder
    • 1
  • Carsten Stahlschmidt
    • 1
  • Sebastian Schnieder
    • 1
    • 2
    • 3
  • Jarek Krajewski
    • 1
    • 2
    • 4
  1. 1.Institute of Experimental PsychophysiologyDuesseldorfGermany
  2. 2.Institute of Safety TechnologyUniversity of WuppertalWuppertalGermany
  3. 3.Engineering PsychologyHMKW BerlinBerlinGermany
  4. 4.Human-Technology-InteractionRhenish University of Applied Science CologneCologneGermany

Personalised recommendations