1. Proceedings
  2. I3M
  3. 2021
  4. IWISH
  5. 10.46354/i3m.2021.iwish.004

EpiMon: Vision-Based Early Warning System for Monitoring Uprising Epileptic Seizures During Night

  • a Gerald A. Zwettler , 
  • b Anna Reichhardt , 
  • c Michael Stradner , 
  • d Christoph Praschl , 
  • e Emmanuel Helm
  • a,c Department of Software Engineering, Faculty for Information, Communication and Media, University of Applied Sciences Upper Austria, Softwarepark 11, Hagenberg, 4232, Austria
  • a,b,c,d,e Research Group Advanced Information Systems and Technologies (AIST), University of Applied Sciences Upper Austria, Softwarepark 11, Hagenberg, 4232, Austria
  • b,e Department of Bio and Medical Informatics, Faculty for Information, Communication and Media, University of Applied Sciences Upper Austria, Softwarepark 11, Hagenberg, 4232, Austria
Cite as
Zwettler G.A. , Reichhardt A., Stradner M., Praschl C., Helm E. (2021). EpiMon: Vision-Based Early Warning System for Monitoring Uprising Epileptic Seizures During Night. Proceedings of the 10th International Workshop on Innovative Simulation for Healthcare (IWISH 2021), pp. 17-26. DOI: https://doi.org/10.46354/i3m.2021.iwish.004

Abstract

At a prevalence of almost 1%, potential epileptic seizures manifest a significant health risk for many juvenile patients. Thus, monitoring is essential to set early counteractive measurements to prevent from damage. The sensor-based monitoring systems mainly address epileptic seizures indicated by a change in the muscle tonus but cannot be utilized for patients that show Prévost’s-sign only. To monitor initiating Prévost’s-sign with opened-eyes as critical visual feature, the applicability of deep-learning eye detection systems on night vision images is evaluated in this paper as basis for modelling and classifying the eye state (closed, opened, not visible). A holistic research prototype is presented as proof of concept, showing the applicability of state-of-the-art face detection on night vision images as well as multi-variate feature analysis on Graph segmentation pre-fragmentation, applicable to detect the state of the eye in a robust way. Results show a single frame accuracy in face/eye detection of 73.91% and 94.44% for classification of the opened eyes as indication of a potentially initiating epileptic seizure. The monitoring system is based on a Raspberry computation unit with two ELP night vision cameras attached and a smart phone app for user-interaction and configuration besides on-demand visual monitoring. Future work will show that the single frame detection rate is sufficient for building up a rule-based monitoring state machine at user predefined sensitivity and specificity by analysing the visual content as time-series rather than single images.

References

  1. Asano, E., Pawlak, C., Shah, A., Shah, J., Luat, A. F., Ahn-Ewing, J., and Chugani, H. T.
    (2005). The diagnostic value of initial video-eeg monitoring in children—review of 1000 cases. Epilepsy Research, 66(1):129–135.
  2. Atanassov, E. and Dimov, I. T. (2008). What monte carlo models can do and cannot do efficiently? Applied Mathematical Modelling, 32(8):1477–1500. Special issue on numerical and computational issues related to applied mathematical modelling.
  3. Backhaus, K. (2008). Multivariate Analysemethoden. Springer, Berlin, Germany, 12 edition.
  4. Baumgartner, c., Feichtinger, M., and Pataraia, M. (2019). Dfp-literaturstudium: Epilepsie. Österreichische Ärztezeitung, (19).
  5. Beucher, S. and Lantuéjoul, C. (1979). Use of watersheds in contour detection. In International Workshop on Image Processing: Real-time Edge and Motion Detection/Estimation, 132.
  6. Dua, M., Singla, R., Raj, S., Jangra, A., et al. (2021). Deep cnn models-based ensemble approach to driver drowsiness detection. Neural Computing and Applications, 33(8):3155–3168.
  7. Epitech GmbH (2021). Epilepsieüberwachung epicare.
  8. Felzenszwalb, P. F. and Huttenlocher, D. (2004). Efficient graph-based image segmentation. International Journal of Computer Vision, 59:167–181.
  9. Fitriyani, N. L., Yang, C.-K., and Syafrudin, M. (2016). Real-time eye state detection system using haar cascade classifier and circular hough transform. In 2016 IEEE 5th Global Conference on Consumer Electronics, pages 1–3. IEEE.
  10. Forsgren, L., Beghi, E., Õun, A., and Sillanpää, M. (2005). The epidemiology of epilepsy in europe – a systematic review. European Journal of Neurology, 12(4):245–253.
  11. Gou, C., Wu, Y., Wang, K., Wang, K., Wang, F.-Y., and Ji, Q. (2017). A joint cascaded framework for simultaneous eye detection and eye state estimation. Pattern Recognition, 67:23–31.
  12. HELLOBABY Ltd. (2021). ellobaby hb25 wireless digital video baby monitor video recording.
  13. Hong, T., Qin, H., and Sun, Q. (2007). An improved real time eye state identification system
    in driver drowsiness detection. In 2007 IEEE International Conference on Control and Automation, pages 1449–1453.
  14. Izenman, A. J. (2008). Modern multivariate statistical techniques : regression, classication, and manifold learning. Springer, New York, USA.
  15. LivAssured B.V. (2021). Epilepsie und sicherer schlaf.
  16. MacDonald, B., Cockerell, O., Sander, L., and Shorvon, S. (2000). The incidence and lifetime
    prevalence of neurologic disorder in a prospective community-based study in the uk. Brain :
    a journal of neurology, 123 ( Pt 4):665–76.
  17. Mahalanobis, P. C. (1936). On the generalized distance in statistics. Proc. Natl. Inst. Sci. India, 2:49–55.
  18. Masterwork Aoitek Tech Corp Ltd. (2021). Lollipop care - sleep tracking beta.
  19. Microsoft Corp. (2021). Facial recognition.
  20. Pandey, N. N. and Muppalaneni, N. B. (2021). Real-time drowsiness identification based on
    eye state analysis. In 2021 International Conference on Artificial Intelligence and Smart Systems (ICAIS), pages 1182–1187.
  21. Prévost, J. L. (1868). De la déviation conjugée des yeux et de la rotation de la tête dans certains cas d’hémiplégie. PhD thesis.
  22. Sander, L. (2003). The epidemiology of the epilepsies revisited. Current opinion in neurology, 16:165–70.
  23. Schulc, E., Hilbe, J., Saboor, S., Ammenwerth, E., Unterberger, I., and Them, C. (2009). Automatische detektion epileptischer anfälle basierend auf beschleunigungsmessungen - literaturübersicht. PRInternet, 10:517–525.
  24. Tian, Z. and Qin, H. (2005). Real-time driver’s eye state detection. In IEEE International Conference on Vehicular Electronics and Safety, 2005., pages 285–289.
  25. Tsuchie, S. Y., Guerreiro, M. M., Chuang, E., Baccin, C. E., and Montenegro, M. A. (2006). What about us?: Siblings of children with epilepsy. Seizure, 15(8):610–614.
  26. Zahn, C. (1971). Graph-theoretical methods for detecting and describing gestalt clusters. IEEE Transactions on Computers, C-20(1):68–86.
  27. Zhang, F., Su, J., Geng, L., and Xiao, Z. (2017). Driver fatigue detection based on eye state recognition. In 2017 International Conference on Machine Vision and Information Technology
    (CMVIT), pages 105–110.
  28. Zhang, K., Zhang, Z., Li, Z., and Qiao, Y. (2016). Joint face detection and alignment using multitask cascaded convolutional networks. IEEE Signal Processing Letters, 23(10):1499–1503.