Advertisement

Deep Learning Approaches for Automated Seizure Detection from Scalp Electroencephalograms

  • Meysam Golmohammadi
  • Vinit Shah
  • Iyad Obeid
  • Joseph Picone
Chapter
  • 34 Downloads

Abstract

Scalp electroencephalograms (EEGs) are the primary means by which physicians diagnose brain-related illnesses such as epilepsy and seizures. Automated seizure detection using clinical EEGs is a very difficult machine learning problem due to the low fidelity of a scalp EEG signal. Nevertheless, despite the poor signal quality, clinicians can reliably diagnose illnesses from visual inspection of the signal waveform. Commercially available automated seizure detection systems, however, suffer from unacceptably high false alarm rates. Deep learning algorithms that require large amounts of training data have not previously been effective on this task due to the lack of big data resources necessary for building such models and the complexity of the signals involved. The evolution of big data science, most notably the release of the Temple University EEG (TUEG) Corpus, has motivated renewed interest in this problem.

In this chapter, we discuss the application of a variety of deep learning architectures to automated seizure detection. Architectures explored include multi-layer perceptrons, convolutional neural networks (CNNs), long short-term memory networks (LSTMs), gated recurrent units, and residual neural networks. We use the TUEG Corpus, supplemented with data from Duke University, to evaluate the performance of these hybrid deep structures. Since TUEG contains a significant amount of unlabeled data, we also discuss unsupervised pre-training methods used prior to training these complex recurrent networks.

Exploiting spatial and temporal context is critical for accurate disambiguation of seizures from artifacts. We explore how effectively several conventional architectures are able to model context and introduce a hybrid system that integrates CNNs and LSTMs. The primary error modalities observed by this state-of-the-art system were false alarms generated during brief delta range slowing patterns such as intermittent rhythmic delta activity. A variety of these types of events have been observed during inter-ictal and post-ictal stages. Training models on such events with diverse morphologies has the potential to significantly reduce the remaining false alarms. This is one reason we are continuing our efforts to annotate a larger portion of TUEG. Increasing the data set size significantly allows us to leverage more advanced machine learning methodologies.

Keywords

Deep learning Convolutional neural networks Electroencephalography Generative adversarial networks Long short-term networks Recurrent neural networks Seizure detection 

References

  1. 1.
    Ilmoniemi, R., & Sarvas, J. (2019). Brain signals: Physics and mathematics of MEG and EEG. Boston, MA: MIT.CrossRefGoogle Scholar
  2. 2.
    Ebersole, J. S., & Pedley, T. A. (2014). Current practice of clinical electroencephalography. Philadelphia, PA: Wolters Kluwer.Google Scholar
  3. 3.
    Yamada, T., & Meng, E. (2017). Practical guide for clinical neurophysiologic testing: EEG. Philadelphia, PA: Lippincott Williams & Wilkins.Google Scholar
  4. 4.
    Ercegovac, M., & Berisavac, I. (2015). Importance of EEG in intensive care unit. Clinical Neurophysiology, 126, e178–e179.  https://doi.org/10.1016/j.clinph.2015.04.027.CrossRefGoogle Scholar
  5. 5.
    Ney, J. P., van der Goes, D. N., Nuwer, M. R., & Nelson, L. (2016). Continuous and routine EEG in intensive care: utilization and outcomes, United States 2005-2009. Neurology, 81, 2002–2008.  https://doi.org/10.1212/01.wnl.0000436948.93399.2a.CrossRefGoogle Scholar
  6. 6.
    Boashash, B. (2015). Time-frequency signal analysis and processing: A comprehensive reference. London: Academic.Google Scholar
  7. 7.
    Gotman, J. (1999). Automatic detection of seizures and spikes. Journal of Clinical Neurophysiology, 16, 130–140.CrossRefGoogle Scholar
  8. 8.
    Li, P., Wang, X., Li, F., Zhang, R., Ma, T., Peng, Y., et al. (2015). Autoregressive model in the Lp norm space for EEG analysis. Journal of Neuroscience Methods, 240, 170–178.  https://doi.org/10.1016/j.jneumeth.2014.11.007.CrossRefGoogle Scholar
  9. 9.
    Li, Y., Luo, M.-L., & Li, K. (2016). A multiwavelet-based time-varying model identification approach for time–frequency analysis of EEG signals. Neurocomputing, 193, 106–114.  https://doi.org/10.1016/j.neucom.2016.01.062.CrossRefGoogle Scholar
  10. 10.
    Rodrıguez-Bermudez, G., & Garcıa-Laencina, P. J. (2015). Analysis of EEG signals using nonlinear dynamics and chaos: A review. Applied Mathematics & Information Science, 9, 2309–2321.  https://doi.org/10.12785/amis/090512.MathSciNetCrossRefGoogle Scholar
  11. 11.
    Eichler, M., Dahlhaus, R., & Dueck, J. (2017). Graphical modeling for multivariate hawkes processes with nonparametric link functions. Journal of Time Series Analysis, 38, 225–242.  https://doi.org/10.1111/jtsa.12213.MathSciNetCrossRefzbMATHGoogle Scholar
  12. 12.
    Schad, A., Schindler, K., Schelter, B., Maiwald, T., Brandt, A., Timmer, J., et al. (2008). Application of a multivariate seizure detection and prediction method to non-invasive and intracranial long-term EEG recordings. Clinical Neurophysiology, 119, 197–211.CrossRefGoogle Scholar
  13. 13.
    Schindler, K., Wiest, R., Kollar, M., & Donati, F. (2001). Using simulated neuronal cell models for detection of epileptic seizures in foramen ovale and scalp EEG. Clinical Neurophysiology, 112, 1006–1017.  https://doi.org/10.1016/S1388-2457(01)00522-3.CrossRefGoogle Scholar
  14. 14.
    Deburchgraeve, W., Cherian, P. J., De Vos, M., Swarte, R. M., Blok, J. H., Visser, G. H., et al. (2008). Automated neonatal seizure detection mimicking a human observer reading EEG. Clinical Neurophysiology, 119, 2447–2454.  https://doi.org/10.1016/j.clinph.2008.07.281.CrossRefGoogle Scholar
  15. 15.
    Baumgartner, C., & Koren, J. P. (2018). Seizure detection using scalp-EEG. Epilepsia, 59, 14–22.  https://doi.org/10.1111/epi.14052.CrossRefGoogle Scholar
  16. 16.
    Haider, H. A., Esteller, R. D., Hahn, C. B., Westover, M. J., Halford, J. W., Lee, J. M., et al. (2016). Sensitivity of quantitative EEG for seizure identification in the intensive care unit. Neurology, 87, 935–944.  https://doi.org/10.1212/WNL.0000000000003034.CrossRefGoogle Scholar
  17. 17.
    Varsavsky, A., & Mareels, I. (2006). Patient un-specific detection of epileptic seizures through changes in variance. In Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society (pp. 3747–3750). New York: IEEE.Google Scholar
  18. 18.
    Bridi, A. C., Louro, T. Q., & Da Silva, R. C. L. (2014). Clinical alarms in intensive care: implications of alarm fatigue for the safety of patients. Revista Latino-Americana de Enfermagem, 22, 1034.  https://doi.org/10.1590/0104-1169.3488.2513.CrossRefGoogle Scholar
  19. 19.
    Ahmedt-Aristizabal, D., Fookes, C., Denman, S., Nguyen, K., Sridharan, S., & Dionisio, S. (2019). Aberrant epileptic seizure identification: A computer vision perspective. Seizure European Journal of Epilepsy, 65, 65–71.  https://doi.org/10.1016/j.seizure.2018.12.017.CrossRefGoogle Scholar
  20. 20.
    Ramgopal, S. (2014). Seizure detection, seizure prediction, and closed-loop warning systems in epilepsy. Epilepsy & Behavior, 37, 291–307.  https://doi.org/10.1016/j.yebeh.2014.06.023.CrossRefGoogle Scholar
  21. 21.
    Alotaiby, T., Alshebeili, S., Alshawi, T., Ahmad, I., & Abd El-Samie, F. (2014). EEG seizure detection and prediction algorithms: a survey. EURASIP Journal on Advances in Signal Processing, 2014, 1–21.  https://doi.org/10.1186/1687-6180-2014-183.CrossRefGoogle Scholar
  22. 22.
    Obeid, I., & Picone, J. (2016). The Temple University Hospital EEG data corpus. Frontiers in Neuroscience. Section Neural Technology, 10, 1–8.  https://doi.org/10.3389/fnins.2016.00196.CrossRefGoogle Scholar
  23. 23.
    LeCun, Y., Bengio, Y., & Hinton, G. (2015). Deep learning. Nature, 521, 436.  https://doi.org/10.1038/nature14539.CrossRefGoogle Scholar
  24. 24.
    Shah, V., Golmohammadi, M., Ziyabari, S., von Weltin, E., Obeid, I., & Picone, J. (2017). Optimizing channel selection for seizure detection. In I. Obeid & J. Picone (Eds.), Proceedings of the IEEE signal processing in medicine and biology symposium (pp. 1–5). Philadelphia, PA: IEEE.  https://doi.org/10.1109/SPMB.2017.8257019.CrossRefGoogle Scholar
  25. 25.
    von Weltin, E., Ahsan, T., Shah, V., Jamshed, D., Golmohammadi, M., Obeid, I., et al. (2017). Electroencephalographic slowing: A primary source of error in automatic seizure detection. In I. Obeid & J. Picone (Eds.), Proceedings of the IEEE signal processing in medicine and biology symposium (pp. 1–5). Philadelphia, PA: IEEE.  https://doi.org/10.1109/SPMB.2017.8257018.CrossRefGoogle Scholar
  26. 26.
    Golmohammadi, M., Ziyabari, S., Shah, V., Obeid, I., & Picone, J. (2018). Deep architectures for spatio-temporal modeling: Automated seizure detection in scalp EEGs. In Proceedings of the IEEE International Conference on Machine Learning and Applications (ICMLA). 1–6, Orlando, Florida, USA.  https://doi.org/10.1109/ICMLA.2018.00118.CrossRefGoogle Scholar
  27. 27.
    Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., et al. (2015). Going deeper with convolutions. In Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR) (pp. 1–9). Boston, MA: IEEE.Google Scholar
  28. 28.
    Simonyan, K., & Zisserman, A. (2015). Very deep convolutional networks for large-scale image recognition. In Proceedings of the international conference on learning representations (ICLR) (pp. 1–14). San Diego, CA: ICLR.Google Scholar
  29. 29.
    He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR) (pp. 770–778). Las Vegas, NV.Google Scholar
  30. 30.
    Radford, A., Metz, L., & Chintala, S. (2016). Unsupervised representation learning with deep convolutional generative adversarial networks. In: Proceedings of the International Conference on Learning Representations (ICLR). San Juan, Puerto Rico.Google Scholar
  31. 31.
    Goodfellow, I., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., et al. (2014). Generative adversarial nets. Proceedings of the Conference on Neural Information Processing Systems, 2672–2680.  https://doi.org/10.1017/CBO9781139058452.
  32. 32.
    Hochreiter, S., & Schmidhuber, J. (1997). Long short-term memory. Neural Computation, 9, 1735–1780.  https://doi.org/10.1162/neco.1997.9.8.1735.CrossRefGoogle Scholar
  33. 33.
    Chung, J., Gulcehre, C., Cho, K., & Bengio, Y. (2014). Empirical evaluation of gated recurrent neural networks on sequence modeling. arXiv Prepr. arXiv1412.3555 (pp. 1–9).Google Scholar
  34. 34.
    Natus Medical: Nicolet® NicVue Connectivity Solution. Retrieved from https://neuro.natus.com/products-services/nicolet-nicvue-connectivity-solution.
  35. 35.
    Harati, A., Lopez, S., Obeid, I., Jacobson, M., Tobochnik, S., & Picone, J. (2014). The TUH EEG corpus: A big data resource for automated EEG interpretation. In I. Obeid & J. Picone (Eds.), Proceedings of the IEEE signal processing in medicine and biology symposium (pp. 1–5). Philadelphia, PA: IEEE.  https://doi.org/10.1109/SPMB.2014.7002953.CrossRefGoogle Scholar
  36. 36.
    Lopez, S., Golmohammadi, M., Obeid, I., & Picone, J. (2016). An analysis of two common reference points for EEGs. In I. Obeid & J. Picone (Eds.), Proceedings of the IEEE signal processing in medicine and biology symposium (pp. 1–4). Philadelphia, PA: IEEE.  https://doi.org/10.1109/SPMB.2016.7846854.CrossRefGoogle Scholar
  37. 37.
    Hirsch, L. J., Laroche, S. M., Gaspard, N. T., Gerard, E. F., Svoronos, A., & Herman, S. T. (2013). American Clinical Neurophysiology Society’s Standardized Critical Care EEG Terminology: 2012 version. Journal of Clinical Neurophysiology, 30, 1–27.  https://doi.org/10.1097/WNP.0b013e3182784729. CrossRefGoogle Scholar
  38. 38.
    Shah, V., von Weltin, E., Lopez, S., McHugh, J. R., Veloso, L., Golmohammadi, M., et al. (2018). The Temple University Hospital seizure detection corpus. Frontiers in Neuroinformatics, 12, 83.  https://doi.org/10.3389/fninf.2018.00083.CrossRefGoogle Scholar
  39. 39.
    Shah, V., Anstotz, R., Obeid, I., & Picone, J. (2018). Adapting an automatic speech recognition system to event classification of electroencephalograms. In I. Obeid & J. Picone (Eds.), Proceedings of the IEEE Signal Processing in Medicine and Biology Symposium (SPMB) (p. 1). Philadelphia, PA: IEEE.  https://doi.org/10.1109/SPMB.2016.7846854.CrossRefGoogle Scholar
  40. 40.
    Harati, A., Golmohammadi, M., Lopez, S., Obeid, I., & Picone, J. (2015). Improved EEG event classification using differential energy. In I. Obeid & J. Picone (Eds.), Proceedings of the IEEE Signal Processing in Medicine and Biology Symposium (pp. 1–4). Philadelphia, PA: IEEE.  https://doi.org/10.1109/SPMB.2015.7405421.CrossRefGoogle Scholar
  41. 41.
    Swisher, C. B., White, C. R., Mace, B. E., & Dombrowski, K. E. (2015). Diagnostic accuracy of electrographic seizure detection by neurophysiologists and non-neurophysiologists in the adult ICU using a panel of quantitative EEG trends. Journal of Clinical Neurophysiology, 32, 324–330.  https://doi.org/10.1097/WNP.0000000000000144.CrossRefGoogle Scholar
  42. 42.
    Kubota, Y., Nakamoto, H., Egawa, S., & Kawamata, T. (2018). Continuous EEG monitoring in ICU. Journal of Intensive Care, 6, 39.  https://doi.org/10.1186/s40560-018-0310-z.CrossRefGoogle Scholar
  43. 43.
    Nihon Kohden Corporation. Retrieved from https://us.nihonkohden.com/products/eeg-1200.
  44. 44.
    Picone, J. (1993). Signal modeling techniques in speech recognition. Proceedings of the IEEE, 81, 1215–1247.  https://doi.org/10.1109/5.237532.CrossRefGoogle Scholar
  45. 45.
    Thodoroff, P., Pineau, J., & Lim, A. (2016). Learning robust features using deep learning for automatic seizure detection. In: Machine Learning and Healthcare Conference.Google Scholar
  46. 46.
    Mirowski, P., Madhavan, D., Lecun, Y., & Kuzniecky, R. (2009). Classification of patterns of EEG synchronization for seizure prediction. Clinical Neurophysiology, 120, 1927–1940.  https://doi.org/10.1016/j.clinph.2009.09.002.CrossRefGoogle Scholar
  47. 47.
    Subasi, A. (2007). EEG signal classification using wavelet feature extraction and a mixture of expert model. Expert Systems with Applications, 32, 1084–1093.  https://doi.org/10.1016/j.eswa.2006.02.005.CrossRefGoogle Scholar
  48. 48.
    Jahankhani, P., Kodogiannis, V., & Revett, K. (2006). EEG signal classification using wavelet feature extraction and neural networks. In IEEE John Vincent Atanasoff 2006 International Symposium on Modern Computing (pp. 120–124).  https://doi.org/10.1109/JVA.2006.17.CrossRefGoogle Scholar
  49. 49.
    Da Rocha Garrit, P. H., Guimaraes Moura, A., Obeid, I., & Picone, J. (2015). Wavelet analysis for feature extraction on EEG signals. In NEDC Summer Research Experience for Undergraduates (p. 1). Philadelphia: Department of Electrical and Computer Engineering, Temple University.Google Scholar
  50. 50.
    Xiong, W., Wu, L., Alleva, F., Droppo, J., Huang, X., & Stolcke, A. (2017). The Microsoft 2017 conversational speech recognition system. In Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP) (pp. 1–5). Calgary.Google Scholar
  51. 51.
    Picone, J. (1990). Continuous speech recognition using hidden Markov models. IEEE ASSP Magazine, 7, 26–41.  https://doi.org/10.1109/53.54527.CrossRefGoogle Scholar
  52. 52.
    Huang, K., & Picone, J. (2002). Internet-accessible speech recognition technology. In Proceedings of the IEEE midwest symposium on circuits and systems (pp. III-73–III-76). Tulsa, OK.Google Scholar
  53. 53.
    Parker, D., Picone, J., Harati, A., Lu, S., Jenkyns, M., & Polgreen, P. (2013). Detecting paroxysmal coughing from pertussis cases using voice recognition technology. PLoS One, 8, e82971.  https://doi.org/10.1371/journal.pone.0082971.CrossRefGoogle Scholar
  54. 54.
    Lu, S., & Picone, J. (2013). Fingerspelling gesture recognition using a two-level hidden Markov model. In Proceedings of the International Conference on image processing, computer vision, and pattern recognition (ICPV) (pp. 538–543). Las Vegas, NV.Google Scholar
  55. 55.
    Obeid, I., & Picone, J. (2018). Machine learning approaches to automatic interpretation of EEGs. In E. Sejdik & T. Falk (Eds.), Signal processing and machine learning for biomedical big data (p. 30). Boca Raton, FL: Taylor & Francis Group.  https://doi.org/10.1201/9781351061223.CrossRefGoogle Scholar
  56. 56.
    Vincent, P., Larochelle, H., Bengio, Y., & Manzagol, P.-A. (2008). Extracting and composing robust features with denoising autoencoders. In Proceedings of the International Conference on Machine Learning (ICMLA) (pp. 1096–1103). New York, NY.Google Scholar
  57. 57.
    Vincent, P., Larochelle, H., Lajoie, I., Bengio, Y., & Manzagol, P.-A. (2010). Stacked denoising autoencoders: Learning useful representations in a deep network with a local denoising criterion Pierre-Antoine Manzagol. Journal of Machine Learning Research, 11, 3371–3408.  https://doi.org/10.1111/1467-8535.00290.CrossRefzbMATHGoogle Scholar
  58. 58.
    Bengio, Y., Lamblin, P., Popovici, D., & Larochelle, H. (2007). Greedy layer-wise training of deep networks. In Advances in neural information processing system (pp. 153–160). Vancouver, BC.Google Scholar
  59. 59.
    Hinton, G. E., Osindero, S., Teh, Y.-W., & Fast Learning, A. (2006). Algorithm for deep belief nets. Neural Computation, 18, 1527–1554.  https://doi.org/10.1162/neco.2006.18.7.1527.MathSciNetCrossRefzbMATHGoogle Scholar
  60. 60.
    van der Maaten, L., Postma, E., van den Herik, J.: Dimensionality reduction: A comparative review. (2009)Google Scholar
  61. 61.
    Ross, D. A., Lim, J., Lin, R. S., & Yang, M. H. (2008). Incremental learning for robust visual tracking. International Journal of Computer Vision, 77, 125–141.  https://doi.org/10.1007/s11263-007-0075-7.CrossRefGoogle Scholar
  62. 62.
    Zinkevich, M., Weimer, M., Smola, A., & Li, L. (2010). Parallelized stochastic gradient descent. In Proceedings of neural information processing systems (pp. 2595–2603). Vancouver, BC.Google Scholar
  63. 63.
    Golmohammadi, M., Harati Nejad Torbati, A. H., de Diego, S., Obeid, I., & Picone, J. (2019). Automatic analysis of EEGs using big data and hybrid deep learning architectures. Frontiers in Human Neuroscience, 13, 76.  https://doi.org/10.3389/fnhum.2019.00076.CrossRefGoogle Scholar
  64. 64.
    Saon, G., Sercu, T., Rennie, S., & Kuo, H.-K. J. (2016). The IBM 2016 English Conversational Telephone Speech Recognition System. In Proceedings of the Annual Conference of the International Speech Communication Association (pp. 7–11).Google Scholar
  65. 65.
    Lopez, S. (2017). Automated identification of abnormal adult electroencephalograms, Department of Electrical and Computer Engineering, Temple University. 58, Philadelphia, PA, USA. Retrieved from https://digital.library.temple.edu/digital/collection/p245801coll10/id/463223/rec/1.
  66. 66.
    LeCun, Y., Bengio, Y., & Hinton, G. (2015). Deep learning. Nature, 521, 436–444.CrossRefGoogle Scholar
  67. 67.
    Nair, V., & Hinton, G. E. (2010). Rectified linear units improve restricted Boltzmann machines. Proceedings of the International Conference on Machine Learning, 807–814.Google Scholar
  68. 68.
    Maas, A. L., Hannun, A. Y., & Ng, A. Y. (2013). Rectifier nonlinearities improve neural network acoustic models. In ICML workshop on deep learning for audio, speech and language processing (p. 6). Atlanta, Georgia, USA.Google Scholar
  69. 69.
    Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I., & Salakhutdinov, R. (2014). Dropout: a simple way to prevent neural networks from overfitting. Journal of Machine Learning Research, 15, 1929–1958.  https://doi.org/10.1214/12-AOS1000.MathSciNetCrossRefzbMATHGoogle Scholar
  70. 70.
    Kingma, D. P., & Ba, J. L. (2015). Adam: a method for stochastic optimization. In Proceedings of the International conference on learning representations (pp. 1–15). San Diego, CA.Google Scholar
  71. 71.
    Jelinek, F. (1997). Statistical methods for speech recognition. Boston, MA: MIT.Google Scholar
  72. 72.
    Bishop, C. (2011). Pattern recognition and machine learning. New York, NY: Springer.zbMATHGoogle Scholar
  73. 73.
    Cortes, C., & Vapnik, V. (1995). Support-vector networks. Machine Learning, 20, 273–297.  https://doi.org/10.1007/BF00994018.CrossRefzbMATHGoogle Scholar
  74. 74.
    Bahl, L., Brown, P., de Souza, P., & Mercer, R. (1986). Maximum mutual information estimation of hidden Markov model parameters for speech recognition. In Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (pp. 49–52). Tokyo.Google Scholar
  75. 75.
    Pandey, P. Deep generative models. Retrieved from https://towardsdatascience.com/deep-generative-models-25ab2821afd3
  76. 76.
    Day, M. Y., Tsai, C. C., Chuang, W. C., Lin, J. K., Chang, H. Y., Fergus, R., et al. (2016). NIPS 2016 Tutorial: generative adversarial networks. EMNLP.  https://doi.org/10.1007/978-3-319-10590-1_53.CrossRefGoogle Scholar
  77. 77.
    Salimans, T., Goodfellow, I., Zaremba, W., Cheung, V., Radford, A., & Chen, X. (2016). Improved techniques for training GANs. In Proceedings of neural information processing systems (NIPS) (pp. 1–9). Barcelona.Google Scholar
  78. 78.
    Yang, S., López, S., Golmohammadi, M., Obeid, I., & Picone, J. (2016). Semi-automated annotation of signal events in clinical EEG data. In I. Obeid & J. Picone (Eds.), Proceedings of the IEEE signal processing in medicine and biology symposium (SPMB) (pp. 1–5). Philadelphia, PA: IEEE.  https://doi.org/10.1109/SPMB.2016.7846855.CrossRefGoogle Scholar
  79. 79.
    Lang, K. J., Waibel, A., & Hinton, G. E. (1990). A time-delay neural network architecture for isolated word recognition. Neural Networks, 3, 23–43.  https://doi.org/10.1016/0893-6080(90)90044-L.CrossRefGoogle Scholar
  80. 80.
    Levy, A., & Lindenbaum, M. (2000). Sequential Karhunen-Loeve basis extraction and its application to images. IEEE Transactions on Image Processing, 9, 1371–1374.  https://doi.org/10.1109/ICIP.1998.723422.CrossRefzbMATHGoogle Scholar
  81. 81.
    Clevert, D., Unterthiner, T., & Hochreiter, S. (2016). Fast and accurate deep network learning by exponential linear units (ELUs). In International conference on learning representations (ICLR) (pp. 1–14). San Juan, Puerto Rico.Google Scholar
  82. 82.
    Golmohammadi, M., Ziyabari, S., Shah, V., Obeid, I., & Picone, J. (2017). Gated recurrent networks for seizure detection. In I. Obeid & J. Picone (Eds.), Proceedings of the IEEE Signal Processing in Medicine and Biology Symposium (pp. 1–5). Philadelphia, PA: IEEE.  https://doi.org/10.1109/SPMB.2017.8257020.CrossRefGoogle Scholar
  83. 83.
    Hermans, M., & Schrauwen, B. (2013). Training and analyzing deep recurrent neural networks. Advances in Neural Information Processing Systems, 190–198. Retrieved from http://dl.acm.org/citation.cfm?id=2999611.2999633.
  84. 84.
    Graves, A., Mohamed, A., & Hinton, G. (2013). Speech recognition with deep recurrent neural networks. International Conference on Acoustics, Speech and Signal Processing, 6645–6649.  https://doi.org/10.1109/ICASSP.2013.6638947.
  85. 85.
    Krauss, G. L., & Fisher, R. S. (2011). The Johns Hopkins Atlas of Digital EEG: An interactive training guide. Baltimore, MD: Johns Hopkins University Press.Google Scholar
  86. 86.
    Ioffe, S., & Szegedy, C. (2015). Batch normalization: Accelerating deep network training by reducing internal covariate shift. In Proceedings of the International conference on machine learning (ICML) (pp. 448–456). Lille, France.Google Scholar
  87. 87.
    Sutskever, I., Martens, J., Dahl, G., & Hinton, G. (2013). On the importance of initialization and momentum in deep learning. In Proceedings of the International Conference on Machine Learning (ICML) (pp. 1139–1147). Atlanta, Georgia.Google Scholar
  88. 88.
    Shah, V., von Weltin, E., Ahsan, T., Obeid, I., & Picone, J. (2019). A cost-effective method for generating high-quality annotations of seizure events. Journal of Clinical Neurophysiology. (in review). Retrieved from www.isip.piconepress.com/publications/unpublished/journals/2017/jcn/ira.
  89. 89.
    Fiscus, J., Ajot, J., Garofolo, J., & Doddingtion, G. (2007). Results of the 2006 spoken term detection evaluation. In Proceedings of the SIGIR 2007 workshop: searching spontaneous conversational speech (pp. 45–50). Amsterdam, The Netherlands.Google Scholar
  90. 90.
    Japkowicz, N., & Shah, M. (2014). Evaluating learning algorithms: A classification perspective. Retrieved from https://www.amazon.com/Evaluating-Learning-Algorithms-Classification-Perspective/dp/1107653118.
  91. 91.
    Shah, V., & Picone, J. NEDC Eval EEG: A comprehensive scoring package for sequential decoding of multichannel signals. Retrieved from https://www.isip.piconepress.com/projects/tuh_eeg/downloads/nedc_eval_eeg/.Google Scholar
  92. 92.
    Shah, V., Golmohammadi, M., Obeid, I., & Picone, J. (2018). Objective evaluation metrics for automatic classification of EEG events. Journal of Neural Engineering, 1–21. (in review). Retrieved from www.isip.piconepress.com/publications/unpublished/journals/2018/iop_jne/metrics/.
  93. 93.
    Liu, A., Hahn, J. S., Heldt, G. P., & Coen, R. W. (1992). Detection of neonatal seizures through computerized EEG analysis. Electroencephalography and Clinical Neurophysiology, 82, 32–37.  https://doi.org/10.1016/0013-4694(92)90179-L.CrossRefGoogle Scholar
  94. 94.
    Navakatikyan, M. A., Colditz, P. B., Burke, C. J., Inder, T. E., Richmond, J., & Williams, C. E. (2006). Seizure detection algorithm for neonates based on wave-sequence analysis. Clinical Neurophysiology, 117, 1190–1203.  https://doi.org/10.1016/j.clinph.2006.02.016.CrossRefGoogle Scholar
  95. 95.
    Fiscus, J. G., & Chen, N. (2013). Overview of the NIST Open Keyword Search 2013 Evaluation Workshop. Bethesda, Maryland, USA.Google Scholar
  96. 96.
    Sundermeyer, M., Ney, H., & Schluter, R. (2015). From feedforward to recurrent LSTM neural networks for language modeling. IEEE/ACM Transactions on Audio, Speech, and Language Processing, 23, 517–529.  https://doi.org/10.1109/TASLP.2015.2400218.CrossRefGoogle Scholar
  97. 97.
    Bottou, L., & Lecun, Y. (2004). Large scale online learning. Advances in Neural Information Processing Systems, 217–225. Retrieved from https://papers.nips.cc/paper/2365-large-scale-online-learning.
  98. 98.
    Tieleman, T., & Hinton, G. (2012). Lecture 6.5-rmsprop: Divide the gradient by a running average of its recent magnitude. COURSERA Neural Networks for Machine Learning.Google Scholar
  99. 99.
    Duchi, J., Hazan, E., & Singer, Y. (2011). Adaptive subgradient methods for online learning and stochastic optimization. Journal of Machine Learning Research, 12, 2121–2159. Retrieved from https://dl.acm.org/citation.cfm?id=2021068.MathSciNetzbMATHGoogle Scholar
  100. 100.
    Zeiler, M. D. (2012). ADADELTA: An adaptive learning rate method. arXiv. abs/1212.5 (pp. 1–6).Google Scholar
  101. 101.
    Saxe, A. M., McClelland, J. L., & Ganguli, S. (2014). Exact solutions to the nonlinear dynamics of learning in deep linear neural networks. In Proceedings of the International conference on learning representations (ICLR) (pp. 1–22). Banff, Canada.Google Scholar
  102. 102.
    Goodfellow, I., Bengio, Y., & Courville, A. (2016). Deep learning. Cambridge, MA: MIT.zbMATHGoogle Scholar
  103. 103.
    Perez, L., & Wang, J. (2017). The effectiveness of data augmentation in image classification using deep learning. arXiv.Google Scholar

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  • Meysam Golmohammadi
    • 1
    • 2
  • Vinit Shah
    • 2
  • Iyad Obeid
    • 2
  • Joseph Picone
    • 2
  1. 1.Internet BrandsEl SegundoUSA
  2. 2.Department of Electrical and Computer Engineering, The Neural Engineering Data ConsortiumTemple UniversityPhiladelphiaUSA

Personalised recommendations