ABSTRACT
Automatic recognition of electroencephalogram (EEG) signals in epileptogenic zone is of great medical significance for computer-aided epilepsy surgery. In the analysis of EEG signals, in order to achieve the purpose of automatic recognition of EEG signals in epileptogenic zone, a method based on deep reinforcement learning is proposed in this paper. First, the local mean decomposition (LMD) algorithm is applied to decompose the original EEG signals. Statistical feature extraction is then performed. Finally, a deep reinforcement learning method, Deep Q-Network (DQN), is used to train the features and finally classify them. The accuracy, sensitivity and specificity of the experimental classification results were 89.28%, 89.88% and 88.68%, respectively. Compared with other traditional machine learning methods, this method shows good classification results.
- C. Geier, K. Lehnertz, Which Brain Regions are Important for Seizure Dynamics in Epileptic Networks? Influence of Link Identification and EEG Recording Montage on Node Centralities, International Journal of Neural Systems 27 (1), 2017, 1650033.Google ScholarCross Ref
- Q. Yuan, W.D. Zhou, L.R. Zhang, F. Zhang, F.Z. Xu, Y. Leng, D.M. Wei, M.N. Chen, Epileptic seizure detection based on imbalanced classification and wavelet packet transform, Seizure-European Journal of Epilepsy 50, 2017, 99-108.Google ScholarCross Ref
- C. Baumgartner, S. Hafner, J.P. Koren, Automatic Detection of epilepsy-typical Potentials and Seizures in the EEG, Klinische Neurophysiologie 89 (9), 2017, 445-456.Google Scholar
- C. Baumgartner, J.P. Koren, M. Rothmayer, Automatic Computer-Based Detection of Epileptic Seizures, Frontiers in Neurology 9, 2018, 639.Google ScholarCross Ref
- A. Narin, Detection of Focal and Non-focal Epileptic Seizure Using Continuous Wavelet Transform-Based Scalogram Images and Pre-trained Deep Neural Networks, IRBM 43 (1), 2022, 22-31.Google ScholarCross Ref
- M. Diykh, S. Abdulla, K. Saleh, R.C. Deo, Fractal dimension undirected correlation graph-based support vector machine model for identification of focal and non-focal electroencephalography signals, Biomedical Signal Processing and Control 54, 2019, 101611.Google ScholarCross Ref
- M.M. Rahman, M.I.H. Bhuiyan, A.B. Das, Classification of focal and non-focal EEG signals in VMD-DWT domain using ensemble stacking, Biomedical Signal Processing and Control 50, 2019, 72-82.Google ScholarCross Ref
- S.M. Usman, S. Khalid, S. Bashir, A deep learning based ensemble learning method for epileptic seizure prediction, Computers in Biology and Medicine 136, 2021, 104710.Google ScholarDigital Library
- A. Shankar, H.K. Khaing, S. Dandapat, S. Barma, Analysis of epileptic seizures based on EEG using recurrence plot images and deep learning, Biomedical Signal Processing and Control 69, 2021, 102854.Google ScholarCross Ref
- W. Wu, Z. Zhou, A.R. Adhikary, B. Dutta, Discrete space reinforcement learning algorithm based on twin support vector machine classification, Pattern Recognition Letters 164, 2022, 254-260.Google ScholarDigital Library
- B.B.M. Paiva, E.R. Nascimento, M.A. Goncalves, F. Belem, A reinforcement learning approach for single redundant view co-training text classification, Information Sciences 615, 2022, 24-38.Google ScholarDigital Library
- R.F. Mansour, J. Escorcia-Gutierrez, M. Gamarra, J.A. Villanueva, N. Leal, Intelligent video anomaly detection and classification using faster RCNN with deep reinforcement learning model, Image and Vision Computing 112, 2021, 104229.Google ScholarCross Ref
- R.G. Andrzejak, K. Schindler, C. Rummel, Nonrandomness, nonlinear dependence, and nonstationarity of electroencephalographic recordings from epilepsy patients, Physical Review E 86 (4), 2012, 46206.Google ScholarCross Ref
- P. Gupta, B. Singh, Local mean decomposition and artificial neural network approach to mitigate tool chatter and improve material removal rate in turning operation, Applied Soft Computing 96, 2020, 106714.Google ScholarDigital Library
- X.D. Tang, M. Li, X. Lin, F. He, Online operations of automated electric taxi fleets: An advisor-student reinforcement learning framework, Transportation Research Part C-Emerging Technologies 121, 2021, 102844.Google ScholarCross Ref
- R. Zhao, X.J. Wang, J.J. Xia, L.S. Fan, Deep reinforcement learning based mobile edge computing for intelligent Internet of Things, Physical Communication 43, 2021, 101184.Google ScholarCross Ref
- J.Z. Zhou, L. Liu, Y. Leng, Y.Y. Yang, B. Gao, Z.H. Jiang, W.W. Nie, Q. Yuan, Both Cross-Patient and Patient-Specific Seizure Detection Based on Self-Organizing Fuzzy Logic, International Journal of Neural Systems 32 (6), 2022, 2250017.Google ScholarCross Ref
- X.Y. Zhao, T. Tanaka, W.Z. Kong, Q.B. Zhao, J.T. Cao, H. Sugano, N. Yoshiday, Epileptic Focus Localization Based on iEEG by Using Positive Unlabeled (PU) Learning, in: 2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC). https://doi.org/10.23919/APSIPA.2018.8659747.Google Scholar
- V. Gupta, R.B. Pachori, A New Method for Classification of Focal and Non-Focal EEG Signals, Machine Intelligence and Signal Analysis 748, 2018, 235–246.Google ScholarCross Ref
- A. Bhattacharyya, M. Sharma, R.B. Pachori, P. Sircar, U.R. Acharya, A novel approach for automated detection of focal EEG signals using empirical wavelet transform, Neural Computing & Applications 29 (8), 2018, 47-57.Google ScholarDigital Library
- H. Akbari, M.T. Sadiq, Detection of focal and non-focal EEG signals using non-linear features derived from empirical wavelet transform rhythms, Physical and Engineering Sciences in Medicine 44 (1), 2021, 157–171.Google ScholarCross Ref
Recommendations
Characterization of focal EEG signals: A review
AbstractEpilepsy is a common neurological condition that can occur in anyone at any age. Electroencephalogram (EEG) signals of non-focal (NF) and focal (F) types contain brain activity information that can be used to identify areas affected by ...
Highlights- Non-focal (NF) and focal (F) EEG signals are analyzed.
- The CAD system to aid in ...
Classification of focal and nonfocal EEG signals using ANFIS classifier for epilepsy detection
The electroencephalogram EEG is the frequently used signal to detect epileptic seizures in the brain. For a successful epilepsy surgery, it is very essential to localize epileptogenic area in the brain. The signals from the epileptogenic area are focal ...
Classification of focal and non focal EEG using entropies
Entropy based features and non linear features are used for classification.NNGE Classifier with optimized features enhances sensitivity.The computation time is very low leading to real time identification. Electroencephalogram (EEG) is the recording of ...
Comments