Machine Learning Based Diagnosis of Diseases Using the Unfolded EEG Spectra: Towards an Intelligent Software Sensor

  • Ricardo BuettnerEmail author
  • Thilo Rieg
  • Janek Frick
Conference paper
Part of the Lecture Notes in Information Systems and Organisation book series (LNISO, volume 32)


In this research-in-progress work we sketch a roadmap for the development of a novel machine-learning-based EEG software sensor. In the first step we present the idea to unfold the EEG standard bandwidths in a more fine-graded equidistant 99-point spectrum to improve accuracy when diagnosing diseases. We use this novel pre-processing step prior to entering a Random Forests classifier. In the second step we evaluate the approach on alcoholism and epilepsy and demonstrate that the approach outperforms all benchmarks. The third step sketches a further improvement by replacing the hard-coded equidistant 99-point spectrum with a flexibly-grading spectrum. In the fourth step we combine the flexibly-grading EEG spectrum, the spatial locations of the EEG electrodes, and the EEG recording time to train an intelligent EEG software sensor using self-organizing feature mapping. Our work contributes to NeuroIS research by analyzing EEG as a bio-signal though a novel machine-learning approach.


Electroencephalography Random forests Spectral analysis Machine learning 


  1. 1.
    Riedl, R., Fischer, T., & Léger, P. M. (2017). A decade of NeuroIS research: Status quo, challenges, and future directions. In ICIS 2017 Proceedings: 38th International Conference on Information Systems, December 10–13, 2017, Seoul, South Korea.Google Scholar
  2. 2.
    Müller-Putz, G. R., Riedl, R., & Wriessnegger, S. C. (2015). Electroencephalography (EEG) as a research tool in the information systems discipline: Foundations, measurement, and applications. CAIS, 37, 911–948.CrossRefGoogle Scholar
  3. 3.
    Hevner, A. R., March, S. T., Park, J., & Ram, S. (2004). Design science in information systems research. MISQ, 28(1), 75–105.CrossRefGoogle Scholar
  4. 4.
    vom Brocke, J., & Liang, T.-P. (2014). Guidelines for neuroscience studies in information systems research. JMIS, 30(4), 211–234.Google Scholar
  5. 5.
    Breiman, L. (2001). Random forests. Machine Learning, 45(1), 5–32.CrossRefGoogle Scholar
  6. 6.
    Buettner, R. (2018). Robust user identification based on facial action units unaffected by users’ emotions. In HICSS-51 Proceedings (pp. 265–273).Google Scholar
  7. 7.
    Buettner, R., Sauer, S., Maier, C., & Eckhardt, A. (2018). Real-time prediction of user performance based on pupillary assessment via eye-tracking. AIS Transactions on Human-Computer Interaction, 10(1), 26–56.CrossRefGoogle Scholar
  8. 8.
    NIH National Institute on Alcohol Abuse and Alcoholism. (2010). Beyond Hangovers—Understanding Alcohol’s impact on your health (Vol. 15, pp. 6–8). NIH Publication.Google Scholar
  9. 9.
    Mumtaz, W., Vuong, P., Xia, L., Malik, A., & Rashid, R. (2017). An EEG-based machine learing method to screen alcohol use disorder. Cognitive Neurodynamics, 11(2), 161–171.CrossRefGoogle Scholar
  10. 10.
    Mursalin, M., Zhang, Y., Chen, Y., & Chawla, N. (2017). Automated epileptic seizure detection using improved correlation-based feature selection with random forest classifier. Neurocomputing, 241, 204–214.CrossRefGoogle Scholar
  11. 11.
    Ngugi, A., Kariuki, S., Bottomley, C., Kleinschmidt, I., Sander, J., & Newton, C. (2011). Incidence of epilepsy a systematic review and meta-analysis. Neurology, 77(10), 1005–1012.CrossRefGoogle Scholar
  12. 12.
    Buettner, R., Sauer, S., Maier, C., & Eckhardt, A. (2015). Towards ex ante prediction of user performance: A novel NeuroIS methodology based on real-time measurement of mental effort. In HICSS-48 Proceedings (pp. 533–542).Google Scholar
  13. 13.
    Kohonen, T. (1997). Self-organizing maps. Berlin: Springer.CrossRefGoogle Scholar
  14. 14.
    Martinetz, T., Ritter, H., & Schulten, K. (1988). Kohonens self-organizing maps for modeling the formation of the auditory cortex of a bat. In R. Pfeifer (Ed.), Connectionism in perspective (pp. 403–412). Amsterdam: North-Holland.Google Scholar
  15. 15.
    Bajaj, V., Guo, Y., Sengur, A., Siuly, S., & Alcin, O. F. (2017). A hybrid method based on time–frequency images for classification of alcohol and control EEG signals. Neural Computing and Applications, 28(12), 3717–3723.CrossRefGoogle Scholar
  16. 16.
    Rieg, T., Frick, J., Hitzler, M., & Buettner, R. (2019). High-performance detection of alcoholism by unfolding the amalgamated EEG spectra using the Random Forests method. In HICSS-52 Proceedings (pp. 3769–3777).Google Scholar
  17. 17.
    Buettner, R., Timm, I. J., Scheuermann, I. F., Koot, C., & Rössle, M. (2017). Stationarity of a user’s pupil size signal as a precondition of pupillary-based mental workload evaluation. In Information systems and neuro science: Gmunden Retreat on NeuroIS 2017, June 12–14, 2017, Gmunden, Austria.Google Scholar
  18. 18.
    Buettner, R. (2016). The relationship between visual website complexity and a user’s mental workload: A NeuroIS perspective. In Information systems and neuro science (Vol. 10 of LNISO, pp. 107–113), Gmunden, Austria.Google Scholar
  19. 19.
    Buettner, R. (2016). A user’s cognitive workload perspective in negotiation support systems: An eye-tracking experiment. In PACIS 2016 Proceedings.Google Scholar
  20. 20.
    Buettner, R. (2015). Investigation of the relationship between visual website complexity and users’ mental workload: A NeuroIS perspective. In Information systems and neuro science (Vol. 10 of LNISO, pp. 123–128), Gmunden, Austria.Google Scholar
  21. 21.
    Buettner, R. (2014). Analyzing mental workload states on the basis of the pupillary hippus. In NeuroIS’14 Proceedings (p. 52).Google Scholar
  22. 22.
    Buettner, R., Daxenberger, B., Eckhardt, A., & Maier, C. (2013). Cognitive workload induced by information systems: Introducing an objective way of measuring based on pupillary diameter responses. In Pre-ICIS HCI/MIS 2013 Proceedings, 2013, paper 20.Google Scholar
  23. 23.
    Buettner, R. (2013). Cognitive workload of humans using artificial intelligence systems: Towards objective measurement applying eye-tracking technology. In KI 2013 Proceedings, ser. LNAI (Vol. 8077, pp. 37–48).CrossRefGoogle Scholar
  24. 24.
    Buettner, R., Daxenberger, B., & Woesle, C. (2013). User acceptance in different electronic negotiation systems—A comparative approach. In ICEBE 2013: Proceedings of the 10th IEEE International Conference on e-Business Engineering, September 11–13, Coventry, UK, 2013 (pp. 1–8). IEEE CS Press.Google Scholar
  25. 25.
    Buettner, R., Baumgartl, H., & Sauter, D. (2018). Microsaccades as a predictor of a user’s level of concentration. In F. D. Davis, et al. (Eds.), Information systems and neuroscience: NeuroIS retreat 2018. Lecture Notes in Information Systems and Organisation (LNISO) (Vol. 29, pp. 173–177).Google Scholar
  26. 26.
    Sauer, S., Buettner, R., Heidenreich, T., Lemke, J., Berg, C., & Kurz, C. (2018). Mindful machine learning: Using machine learning algorithms to predict the practice of mindfulness. European Journal of Psychological Assessment, 34(1), 6–13.CrossRefGoogle Scholar
  27. 27.
    Sauer, S., Lemke, J., Zinn, W., Buettner, R., & Kohls, N. (2015). Mindful in a random forest: Assessing the validity of mindfulness items using random forests methods. Journal of Personality and Individual Differences, 81, 117–123.CrossRefGoogle Scholar
  28. 28.
    Buettner, R. (2017). Predicting user behavior in electronic markets based on personality-mining in large online social networks: A personality-based product recommender framework. Electronic Markets: The International Journal on Networked Business, 27(3), 247–265.CrossRefGoogle Scholar
  29. 29.
    Buettner, R. (2016). Innovative personality-based digital services. In PACIS 2016 Proceedings: 20th Pacific Asia Conference on Information Systems (PACIS), June 27–July 1, Chiayi, Taiwan.Google Scholar
  30. 30.
    Buettner, R. (2016). Personality as a predictor of business social media usage: An empirical investigation of XING usage patterns, In PACIS 2016 Proceedings: 20th Pacific Asia Conference on Information Systems (PACIS), June 27–July 1, Chiayi, Taiwan.Google Scholar
  31. 31.
    Buettner, R. (2017). Asking both the user’s brain and its owner using subjective and objective psychophysiological NeuroIS instruments. In ICIS 2017 Proceedings: 38th International Conference on Information Systems, December 10–13, 2017, Seoul, South Korea.Google Scholar
  32. 32.
    Buettner, R. (2013). Social inclusion in eParticipation and eGovernment solutions: A systematic laboratory-experimental approach using objective psychophysiological measures, In EGOV/ePart 2013: Proceedings of the Joint Conference of IFIP EGOV 2013 & IFIP ePart 2013, September 16–19, Koblenz, Germany, 2013 (Vol. P-221 of Lecture Notes in Informatics (LNI)—Proceedings, pp. 260–261).Google Scholar
  33. 33.
    Baumgartl, H., Tomas, J., Buettner, R., & Merkel, M. (2019). A novel deep-learning approach for automated non-destructive testing in quality assurance based on convolutional neural networks. In Proceedings of the 13th International Conference on Advanced Computational Engineering and Experimenting, July 1–5, 2019, Athens, Greece. Accepted.Google Scholar
  34. 34.
    Buettner, R., & Baumgartl, H. (2019). A highly effective deep learning based escape route recognition module for autonomous robots in crisis and emergency situations. In HICSS-52 Proceedings, January 8–11, 2019, Maui, Hawaii (pp. 659–666).Google Scholar
  35. 35.
    Baumgartl, H., Buettner, R., Bernthaler, T., Timm, I. J., Jansche, A., & Schneider, G. (2018). Colored micrographs significantly outperform grayscale ones in modern machine learning: Insights from a systematical analysis of lithium-ion battery micrographs using convolutional neural networks. In Proceedings of the 13th Multinational Congress of Microscopy, September 24–29, Rovinj, Croatia.Google Scholar

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  1. 1.Aalen UniversityAalenGermany

Personalised recommendations