뇌파의 중첩 분할에 기반한 CNN 앙상블 모델을 이용한뇌전증 발작 검출
Epileptic Seizure Detection Using CNN Ensemble Models Based on Overlapping Segments of EEG Signals
0
조회
0
다운로드
1
인용
0
참고문헌
키워드
초록
뇌파(electroencephalogram, EEG)를 이용한 진단이 확대되면서 EEG 신호를 자동으로 분류하기 위한 다양한 연구가 활발히 이루어지고 있다. 본 논문은 일반인과 뇌전증 환자에게서 추출한 EEG 신호를 효과적으로 식별할 수 있는 CNN 모델을 제안한다. CNN의 학습에 필요한 데이터를확장하기 위하여 EEG 신호를 낮은 차원의 신호로 분할하고, 이것을 다시 여러 개의 세그먼트로 중첩 분할하여 CNN 학습에 이용한다. 이와 더불어CNN의 성능을 개선하기 위하여 CNN 앙상블 전략을 제안한다. 공개된 Bonn 데이터세트로 실험을 수행한 결과 뇌전증 발작을 99.0% 이상의 정확도로 검출하였고, 앙상블 방식에 의해 3-클래스와 5-클래스의 EEG 분류에서 정확도가 향상되었다.
Abstract
As the diagnosis using encephalography(EEG) has been expanded, various studies have been actively performed for classifying EEGautomatically. This paper proposes a CNN model that can effectively classify EEG signals acquired from healthy persons and patientswith epilepsy. We segment the EEG signals into sub-signals with smaller dimension to augment the EEG data that is necessary to trainthe CNN model. Then the sub-signals are segmented again with overlap and they are used for training the CNN model. We also proposeensemble strategy in order to improve the classification accuracy. Experimental result using public Bonn dataset shows that the CNNcan detect the epileptic seizure with the accuracy above 99.0%. It also shows that the ensemble method improves the accuracy of 3-classand 5-class EEG classification.
참고문헌 (19)
- K. Jung, "Epidemiology of epilepsy in Korea", Epilia : Epilepsy and Community, 2(1), pp.17~20 (2020)
- R. G. Andrzejak, "Indications of nonlinear deterministic and finite-dimensional structures in time series of brain electrical activity : Dependence on recording region and brain state", Physical Review, 64(6), pp.1~8 (2001)
- Mohammad Reza Mohammadi, "EEG Classification of ADHD and Normal Children Using Non-linear Features and Neural Network", Biomedical Engineering Letters (BMEL), 6(2), pp.66~73 (2016), 대한의용생체공학회[DOI]
- S. Bavkar, "Detection of alcoholism : An EEG hybrid features and ensemble subspace K-NN based approach", International Conference on Distributed Computing and Internet Technology, pp.161~168 (2019), Springer
- A. Demerdzieva, "EEG characteristics of generalized anxiety disorder in childhood", Acta Informatica Medica, 19(1), pp.9~15 (2011)
- D. J. McFarland, "EEG-based brain-computer interfaces", Current Opinion in Biomedical Engineering, 4, pp.194~200 (2017)
- R. A. Ricardo, "Analysis of EEG signal processing techniques based on spectrograms", Research in Computing Science, 145, pp.151~162 (2017)
- W. Mao, "EEG dataset classification using CNN method", Journal of Physics : Conference Series, 1456, pp.1~7 (2020)
- N. Kumar, "Wavelet transform for classification of EEG signal using SVM and ANN", Biomedical & Phamacology Journal, 10(4), pp.2061~2069 (2017)
- K. C. Hsu, "Detection of seizures in EEG using subband nonlinear parameters and genetic algorithm", Computers in Biology and Medicine, 40(10), pp.823~830 (2010)
- M. Savadkoohi, "A machine learning approach to epileptic seizure prediction using Electroencephalogram(EEG)signal", Biocybernetics and Biomedical Engineering, 40(3), pp.1328~1341 (2020)
- A. Bhattacharyya, "A multivariate approach for patient specific EEG seizure detection using empirical wavelet transform", IEEE Transactions on Biomeical Engineering, 64(9), pp.2003~2015 (2017)
- R. T. Schirrmeister, "Deep learning with convolutional neural networks for EEG decoding and visualization", in Human Brain Mapping, 38(11), pp.5391~5420 (2017)
- K. K. Ang, "Filter bank common spatial pattern(FBCSP)in brain-computer interface", Proceedings of IEEE International Joint Conference on Neural Nwtworks, pp.2390~2397 (2008)
- P. Sandheep, "Performance analysis of deep learning CNN in classification of depression EEG signals", Proceedings of IEEE Region 10Conference, pp.1339~1344 (2019)
- U. R. Acharya, "Deep convolutional neural network for the automated detection and diagnosis of seizure using EEG signals", Computers in Biology and Medicine, 100, pp.270~278 (2018)
- I. Ullah, "An automated system for epilepsy detection using EEG brain signals based on deep learning approach", Expert Systems With Applications, 107, pp.61~71 (2018)
- G. Xu, "A one-dimensional CNN-LSTM model for epileptic seizure recognition using EEG signal analysis", Frontiers in Neuroscience, 14, pp.1~9 (2020)
- "Epileptic Seizure Recognition Data Set"[URL]