skip to main content
research-article

M2SKD: Multi-to-Single Knowledge Distillation of Real-Time Epileptic Seizure Detection for Low-Power Wearable Systems

Published: 17 October 2024 Publication History

Abstract

Integrating low-power wearable systems into routine health monitoring is an ongoing challenge. Recent advances in the computation capabilities of wearables make it possible to target complex scenarios by exploiting multiple biosignals and using high-performance algorithms, such as Deep Neural Networks (DNNs). However, there is a tradeoff between the algorithms’ performance and the low-power requirements of platforms with limited resources. Besides, physically larger and multi-biosignal-based wearables bring significant discomfort to the patients. Consequently, reducing power consumption and discomfort is necessary for patients to use wearable devices continuously during everyday life. To overcome these challenges, in the context of epileptic seizure detection, we propose the Multi-to-Single Knowledge Distillation (M2SKD) approach targeting single-biosignal processing in wearable systems. The starting point is to train a highly-accurate multi-biosignal DNN, then apply M2SKD to develop a single-biosignal DNN solution for wearable systems that achieves an accuracy comparable to the original multi-biosignal DNN. To assess the practicality of our approach to real-life scenarios, we perform a comprehensive simulation experiment analysis on several edge computing platforms.

References

[1]
Epilepsy. 2023. World Health Organization. Retrieved from http://www.who.int/mental_health/neurology/epilepsy/en/
[2]
Simon Shorvon and Torbjorn Tomson. 2011. Sudden unexpected death in epilepsy. The Lancet 378, 9808 (2011), 2028–2038.
[3]
Ala Al-Fuqaha, Mohsen Guizani, Mehdi Mohammadi, Mohammed Aledhari, and Moussa Ayyash. 2015. Internet of things: A survey on enabling technologies, protocols, and applications. IEEE Communications Surveys & Tutorials 17, 4 (2015), 2347–2376.
[4]
Philippe Ryvlin and Sandor Beniczky. 2020. Seizure detection and mobile health devices in epilepsy: Recent developments and future perspectives. Epilepsia 61 (2020), 1–2.
[5]
Riccardo Miotto, Fei Wang, Shuang Wang, Xiaoqian Jiang, and Joel T. Dudley. 2018. Deep learning for healthcare: Review, opportunities and challenges. Briefings in Bioinformatics 19, 6 (2018), 1236–1246.
[6]
Valentin Gabeff, Tomas Teijeiro, Marina Zapater, Leila Cammoun, Sylvain Rheims, Philippe Ryvlin, and David Atienza. 2021. Interpreting deep learning models for epileptic seizure detection on EEG signals. Artificial Intelligence in Medicine 117 (2021), 102084 pages.
[7]
U. Rajendra Acharya, Shu L. Oh, Yuki Hagiwara, Jen H. Tan, and Hojjat Adeli. 2018. Deep convolutional neural network for the automated detection and diagnosis of seizure using EEG signals. Computers in Biology and Medicine 100 (2018), 270–278.
[8]
Lasitha S. Vidyaratne and Khan M. Iftekharuddin. 2017. Real-time epileptic seizure detection using EEG. IEEE Transactions on Neural Systems and Rehabilitation Engineering 25, 11 (2017), 2146–2156.
[9]
Frans S. S. Leijten, Dutch TeleEpilepsy Consortium, J. van Andel, C. Ungureanu, J. Arends, F. Tan, J. van Dijk, G. Petkov, S. Kalitzin, T. Gutter, A. de Weerd, B. Vledder, R. Thijs, G. van Thiel, K. Roes, W. Hofstra, R. Lazeron, P. Cluitmans, M. Ballieux, and M. de Groot. 2018. Multimodal seizure detection: A review. Epilepsia 59 (2018), 42–47.
[10]
K. He, X. Zhang, S. Ren, and J. Sun. 2016. Deep residual learning for image recognition. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR ’16). 770–778. DOI:
[11]
Yong-Deok Kim, Eunhyeok Park, Sungjoo Yoo, Taelim Choi, Lu Yang, and Dongjun Shin. 2015. Compression of deep convolutional neural networks for fast and low power mobile applications. arXiv:1511.06530. Retrieved from https://arxiv.org/abs/1511.06530
[12]
Anouk Van de Vel, Kris Cuppens, Bert Bonroy, Milica Milosevic, Katrien Jansen, Sabine Van Huffel, Bart Vanrumste, Patrick Cras, Lieven Lagae, and Berten Ceulemans. 2016. Non-EEG seizure detection systems and potential sudep prevention: State of the art: Review and update. Seizure 41 (2016), 141–153.
[13]
Jianping Gou, Baosheng Yu, Stephen J. Maybank, and Dacheng Tao. 2020. Knowledge distillation: A survey. arXiv:2006.05525. Retrieved from https://doi.org/10.1007/s11263-021-01453-z
[14]
Geoffrey Hinton, Oriol Vinyals, and Jeff Dean. 2015. Distilling the knowledge in a neural network. arXiv:1503.02531.
[15]
Matthias Ihle, Hinnerk Feldwisch-Drentrup, César A. Teixeira, Adrien Witon, Björn Schelter, Jens Timmer, and Andreas Schulze-Bonhage. 2012. Epilepsiae—A European epilepsy database. Computer Methods and Programs Biomedicine 106, 3 (June 2012), 127–138. ISSN 0169-2607.
[16]
Renée A. Shellhaas. 2015. Continuous long-term electroencephalography: The gold standard for neonatal seizure diagnosis. In Seminars in Fetal and Neonatal Medicine Vol. 20. Steve Donn and Win Tin (Eds.), Elsevier, 149–153. DOI:
[17]
Miaolin Fan and Chun-An Chou. 2018. Detecting abnormal pattern of epileptic seizures via temporal synchronization of EEG signals. IEEE Transactions on Biomedical Engineering 66, 3 (2018), 601–608.
[18]
Dong Wang, Doutian Ren, Kuo Li, Yiming Feng, Dan Ma, Xiangguo Yan, and Gang Wang. 2018. Epileptic seizure detection in long-term EEG recordings by using wavelet-based directed transfer function. IEEE Transactions on Biomedical Engineering 65, 11 (2018), 2591–2599.
[19]
Kaveh Samiee, Peter Kovacs, and Moncef Gabbouj. 2014. Epileptic seizure classification of EEG time-series using rational discrete short-time fourier transform. IEEE Transactions on Biomedical Engineering 62, 2 (2014), 541–552.
[20]
Md A. Sayeed, Saraju P. Mohanty, Elias Kougianos, and Hitten P. Zaveri. 2019. Neuro-detect: A machine learning-based fast and accurate seizure detection system in the IoMT. IEEE Transactions on Consumer Electronics 65, 3 (2019), 359–368.
[21]
Antonio Pullini, Davide Rossi, Igor Loi, Giuseppe Tagliavini, and Luca Benini. 2019. Mr. Wolf: An energy-precision scalable parallel ultra low power SoC for IoT edge processing. IEEE Journal of Solid-State Circuits 54, 7 (2019), 1970–1981.
[22]
Elisabetta De Giovanni, Fabio Montagna, Benoît Walter Denkinger, Simone Machetti, Miguel P. Quiros, Simone Benatti, Davide Rossi, Luca Benini, and David A. Alonso. 2020. Modular Design and Optimization of Biomedical Applications for Ultra-Low Power Heterogeneous Platforms. IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems. 39, 11 (2020), 3821–3832.
[23]
Dionisije Sopic, Amir Aminifar, and David Atienza. 2018. e-glass: A wearable system for real-time detection of epileptic seizures. In Proceedings of the IEEE International Symposium on Circuits and Systems (ISCAS ’18). IEEE, 1–5.
[24]
Carolina Varon, Katrien Jansen, Lieven Lagae, and Sabine Van Huffel. Detection of epileptic seizures by means of morphological changes in the ECG. In Computing in Cardiology 2013. IEEE, 863–866. IEEE, 2013.
[25]
Maeike Zijlmans, Danny Flanagan, and Jean Gotman. 2002. Heart rate changes and ECG abnormalities during epileptic seizures: Prevalence and definition of an objective clinical sign. Epilepsia 43, 8 (2002), 847–854.
[26]
Fritz Leutmezer, Christiana Schernthaner, Stefanie Lurger, Klaus Pötzelberger, and Christoph Baumgartner. 2003. Electrocardiographic changes at the onset of epileptic seizures. Epilepsia 44, 3 (2003), 348–354.
[27]
Farnaz Forooghifar, Amir Aminifar, Leila Cammoun, Ilona Wisniewski, Carolina Ciumas, Philippe Ryvlin, and David Atienza. 2019. A self-aware epilepsy monitoring system for real-time epileptic seizure detection. Mobile Networks and Applications 27 (2019), 1–14.
[28]
Farnaz Forooghifar, Amir Aminifar, and David Atienza. 2019. Resource-aware distributed epilepsy monitoring using self-awareness from edge to cloud. IEEE Transactions on Biomedical Circuits and Systems 13, 6 (2019), 1338–1350.
[29]
Francesco Onorati, Giulia Regalia, Chiara Caborni, Matteo Migliorini, Daniel Bender, Ming-Zher Poh, Cherise Frazier, Eliana Kovitch Thropp, Elizabeth D. Mynatt, Jonathan Bidwell, Roberto Mai, W. Curt LaFrance Jr, Andrew S. Blum, Daniel Friedman, Tobias Loddenkemper, Fatemeh Mohammadpour-Touserkani, Claus Reinsberger, Simone Tognetti, and Rosalind W. Picard. 2017. Multicenter clinical assessment of improved wearable multimodal convulsive seizure detectors. Epilepsia 58, 11 (2017), 1870–1879.
[30]
F. Fürbass, S. Kampusch, E. Kaniusas, J. Koren, S. Pirker, R. Hopfengärtner, H. Stefan, T. Kluge, and C. Baumgartner. 2017. Automatic multimodal detection for long-term seizure documentation in epilepsy. Clinical Neurophysiology 128, 8 (2017), 1466–1472.
[31]
Barry R. Greene, Geraldine B. Boylan, Richard B. Reilly, Philip de Chazal, and Sean Connolly. 2007. Combination of EEG and ECG for improved automatic neonatal seizure detection. Clinical Neurophysiology 118, 6 (2007), 1348–1359.
[32]
Iosif Mporas, Vasiliki Tsirka, Evangelia I. Zacharaki, Michalis Koutroumanidis, Mark Richardson, and Vasileios Megalooikonomou. 2015. Seizure detection using EEG and ECG signals for computer-based monitoring, analysis and management of epileptic patients. Expert Systems with Applications 42, 6 (2015), 3227–3233.
[33]
Marwa Qaraqe, Muhammad Ismail, Erchin Serpedin, and Haneef Zulfi. 2016. Epileptic seizure onset detection based on EEG and ECG data fusion. Epilepsy & Behavior 58 (2016), 48–60.
[34]
Yu Liu, Shobi Sivathamboo, Peter Goodin, Paul Bonnington, Patrick Kwan, Levin Kuhlmann, Terence O’Brien, Piero Perucca, and Zongyuan Ge. 2020. Epileptic seizure detection using convolutional neural network: A multi-biosignal study. In Proceedings of the Australasian Computer Science Week Multiconference. 1–8.
[35]
Mrutyunjaya Sahani, Susanta K. Rout, and Pradipta K. Dash. 2021. Epileptic seizure recognition using reduced deep convolutional stack autoencoder and improved kernel RVFLN from EEG signals. IEEE Transactions on Biomedical Circuits and Systems 15, 3 (2021), 595–605.
[36]
Jianping Gou, Liyuan Sun, Baosheng Yu, Shaohua Wan, Weihua Ou, and Zhang Yi. 2022. Multilevel attention-based sample correlations for knowledge distillation. IEEE Transactions on Industrial Informatics 19, 5 (2022), 7099–7109.
[37]
Jianping Gou, Liyuan Sun, Baosheng Yu, Shaohua Wan, and Dacheng Tao. 2023. Hierarchical multi-attention transfer for knowledge distillation. ACM Transactions on Multimedia Computing, Communications and Applications 20, 2 (2023), 1–20.
[38]
Pradip Chitrakar, Chengcui Zhang, Gary Warner, and Xinpeng Liao. 2016. Social media image retrieval using distilled convolutional neural network for suspicious e-crime and terrorist account detection. In Proceedings of the IEEE International Symposium on Multimedia (ISM ’16). IEEE, 493–498.
[39]
Andrew G. Howard, Menglong Zhu, Bo Chen, Dmitry Kalenichenko, Weijun Wang, Tobias Weyand, Marco Andreetto, and Hartwig Adam. 2017. Mobilenets: Efficient convolutional neural networks for mobile vision applications. arXiv:1704.04861. Retrieved from https://arxiv.org/abs/1704.04861
[40]
Zhengping Che, Sanjay Purushotham, Robinder Khemani, and Yan Liu. 2015. Distilling knowledge from deep networks with applications to healthcare domain. arXiv:1512.03542. Retrieved from https://arxiv.org/abs/1512.03542
[41]
Qi Dou, Quande Liu, Pheng Ann Heng, and Ben Glocker. 2020. Unpaired multi-modal segmentation via knowledge distillation. IEEE Transactions on Medical Imaging 39, 7 (2020), 2415–2425.
[42]
Kang Li, Shujun Wang, Lequan Yu, and Pheng-Ann Heng. 2020. Dual-teacher: Integrating intra-domain and inter-domain teachers for annotation-efficient cardiac segmentation. In Proceedings of the International Conference on Medical Image Computing and Computer-Assisted Intervention. Springer, 418–427.
[43]
Raj D. Sheth. 2002. Focal vs. generalized seizures: Why classify? Clinical Pediatrics 41, 2 (2002), 73–75.
[44]
Damian Pascual, Alireza Amirshahi, Amir Aminifar, David Atienza, Philippe Ryvlin, and Roger Wattenhofer. 2020. EpilepsyGAN: Synthetic epileptic brain activities with privacy preservation. IEEE Transactions on Biomedical Engineering 68, 8 (2020) 2435–2446.
[45]
Xuyang Zhao, Jordi Solé-Casals, Binghua Li, Zihao Huang, Andong Wang, Jianting Cao, Toshihisa Tanaka, and Qibin Zhao. 2020. Classification of epileptic IEEG signals by CNN and data augmentation. In Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP ’20). IEEE, 926–930.
[46]
Lei Huang, Jie Qin, Yi Zhou, Fan Zhu, Li Liu, and Ling Shao. 2020. Normalization techniques in training DNNs: Methodology, analysis and application. arXiv:2009.12836. Retrieved from https://arxiv.org/abs/2009.12836
[47]
Fuhai Huang, Zhenhai Wang, and Xu Bo. 2015. Design of 50hz notch filter based on virtual instrument. In Proceedings of the 2015 2nd International Conference on Electrical, Computer Engineering and Electronics. Atlantis Press, 453–456.
[48]
Seung-Won Shin, Kyeong-Seop Kim, Chul-Gyu Song, Jeong-Whan Lee, Jeong-Hwan Kim, and Gyeo-Wun Jeung. 2015. Removal of baseline wandering in ECG signal by improved detrending method. Bio-Medical Materials and Engineering 26, s1 (2015), S1087–S1093.
[49]
Saleh Baghersalimi, Tomas Teijeiro, David Atienza, and Amir Aminifar. 2022. Personalized real-time federated learning for epileptic seizure detection. IEEE Journal of Biomedical and Health Informatics 26, 2 (2022), 898–909. DOI:
[50]
Cha Zhang and Yunqian Ma. 2012. Ensemble Machine Learning: Methods and Applications. Springer.
[51]
Thomas G. Dietterich. 2000. Ensemble methods in machine learning. In Proceedings of the International Workshop on Multiple Classifier Systems. Springer, 1–15.
[52]
Cristian Buciluǎ, Rich Caruana, and Alexandru Niculescu-Mizil. 2006. Model compression. In Proceedings of the 12th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. 535–541.
[53]
Jangho Kim, SeoungUK Park, and Nojun Kwak. 2018. Paraphrasing complex network: Network compression via factor transfer. arXiv:1802.04977. Retrieved from https://arxiv.org/abs/1802.04977
[54]
Lei J. Ba and Rich Caruana. 2013. Do deep nets really need to be deep? arXiv:1312.6184. Retrieved from https://arxiv.org/abs/1312.6184
[55]
Warren Gay. 2014. Raspberry Pi Hardware Reference. Apress.
[56]
Sándor Beniczky, Philippa Karoly, Ewan Nurse, Philippe Ryvlin, and Mark Cook. 2021. Machine learning and wearable devices of the future. Epilepsia 62 (2021), S116–S124.
[57]
Philip J. Fleming and John J. Wallace. 1986. How not to lie with statistics: The correct way to summarize benchmark results. Communications of the ACM 29, 3 (1986), 218–221.
[59]
Qoitech AB. (2020). Otii Arc Otii by Qoitech. Retrieved from https://www.qoitech.com/otii/
[60]
Diederik P. Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. arXiv:1412.6980. Retrieved from https://arxiv.org/abs/1412.6980
[61]
Martín Abadi, Ashish Agarwal, Paul Barham, Eugene Brevdo, Zhifeng Chen, Craig Citro, Greg S. Corrado, Andy Davis, Jeffrey Dean, Matthieu Devin, Sanjay Ghemawat, Ian Goodfellow, Andrew Harp, Geoffrey Irving, Michael Isard, Yangqing Jia, Rafal Jozefowicz, Lukasz Kaiser, Manjunath Kudlur, Josh Levenberg, Dandelion Mané, Rajat Monga, Sherry Moore, Derek Murray, Chris Olah, Mike Schuster, Jonathon Shlens, Benoit Steiner, Ilya Sutskever, Kunal Talwar, Paul Tucker, Vincent Vanhoucke, Vijay Vasudevan, Fernanda Viégas, Oriol Vinyals, Pete Warden, Martin Wattenberg, Martin Wicke, Yuan Yu, and Xiaoqiang Zheng. TensorFlow: Large-Scale Machine Learning on Heterogeneous Systems, 2015. Retrieved from https://www.tensorflow.org/. Software available from tensorflow.org
[62]
Ting Chen, Simon Kornblith, Mohammad Norouzi, and Geoffrey Hinton. 2020. A simple framework for contrastive learning of visual representations. In Proceedings of the International Conference on Machine Learning. PMLR, 1597–1607.
[63]
Saleh Baghersalimi, Behzad Bozorgtabar, Philippe Schmid-Saugeon, Hazi̇m Kemal Ekenel, and Jean-Philippe Thiran. 2019. DermoNet: Densely linked convolutional neural network for efficient skin lesion segmentation. EURASIP Journal on Image and Video Processing 2019, 1 (2019), 71.
[64]
Olaf Ronneberger, Philipp Fischer, and Thomas Brox. 2015. U-Net: Convolutional networks for biomedical image segmentation. In Proceedings of the 18th International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI ’15). Springer, 234–241.
[65]
Greg Diamos, Shubho Sengupta, Bryan Catanzaro, Mike Chrzanowski, Adam Coates, Erich Elsen, Jesse Engel, Awni Hannun, and Sanjeev Satheesh. 2016. Persistent RNNs: Stashing recurrent weights on-chip. In Proceedings of the International Conference on Machine Learning. PMLR, 2024–2033.
[66]
STM32L1 Series STMicroelectronics.
[67]
Nordic Semiconductor. 2015. nRF8001 Product Specification. Retrieved from https://www.nordicsemi.com/Products/Low-power-short-range-wireless/nRF8000-series
[68]
Davide Rossi, Francesco Conti, Manuel Eggiman, Alfio Di Mauro, Giuseppe Tagliavini, Stefan Mach, Marco Guermandi, Antonio Pullini, Igor Loi, Jie Chen, Eric Flamand, and Luca Benini. 2022. Vega: A ten-core SoC for IoT endnodes with DNN acceleration and cognitive wake-up from MRAM-based state-retentive sleep mode. IEEE Journal of Solid-State Circuits 57, 1 (2022), 127–139. DOI:

Recommendations

Comments

Information & Contributors

Information

Published In

cover image ACM Transactions on Intelligent Systems and Technology
ACM Transactions on Intelligent Systems and Technology  Volume 15, Issue 5
October 2024
719 pages
EISSN:2157-6912
DOI:10.1145/3613688
  • Editor:
  • Huan Liu
Issue’s Table of Contents

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 17 October 2024
Online AM: 04 July 2024
Accepted: 28 May 2024
Revised: 17 March 2024
Received: 14 April 2023
Published in TIST Volume 15, Issue 5

Check for updates

Author Tags

  1. Edge computing
  2. deep learning
  3. electrocardiography
  4. epilepsy
  5. knowledge distillation
  6. seizure detection
  7. multi-modal biosignal processing

Qualifiers

  • Research-article

Funding Sources

  • PEDESITE Swiss NSF Sinergia
  • RESoRT
  • Knut and Alice Wallenberg Foundation

Contributors

Other Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

  • 0
    Total Citations
  • 223
    Total Downloads
  • Downloads (Last 12 months)223
  • Downloads (Last 6 weeks)60
Reflects downloads up to 12 Feb 2025

Other Metrics

Citations

View Options

Login options

Full Access

View options

PDF

View or Download as a PDF file.

PDF

eReader

View online with eReader.

eReader

Full Text

View this article in Full Text.

Full Text

Figures

Tables

Media

Share

Share

Share this Publication link

Share on social media