Yifei Sun
ABSTRACT
Due to individual variability of electroencephalogram (EEG) data and a severe imbalance in the proportion of acquired detection samples, the development of automatic epilepsy detection technology has been constrained. This paper presents an epilepsy detection method based on Temporal Convolutional Network-Long Short Term Memory (TCN-LSTM). First, raw EEG signals are subjected to initial filtering and balancing pre-processing. Subsequently, the TCN-LSTM network, known for its excellent handling of time-series data, is used for feature extraction and classification of EEG signals. In addition, the Squeeze-and-Excitation Networks (SENet) channel attention mechanism is incorporated, which assigns different weights to extracted features based on different leads, emphasizing channels with higher weights, thereby enhancing detection efficiency. This approach avoids the complex process of manual feature extraction. Experimental testing on a dataset from Boston Children's Hospital yielded results of 84.18% sensitivity, 92.84% specificity, and 92.86% accuracy. The proposed model is suitable for an automated epilepsy detection system.
- B. Abbasi and D. M. Goldenholz, "Machine learning applications in epilepsy," (in English), EPILEPSIA, vol. 60, no. 10, pp. 2037-2047, OCT 2019.Google Scholar
- S. Supriya, S. Siuly, H. Wang, and Y. Zhang, "Epilepsy Detection From EEG Using Complex Network Techniques: A Review," IEEE Reviews in Biomedical Engineering, vol. 16, pp. 292-306, 2023.Google ScholarCross Ref
- S. Singh and H. Kaur, "An Intelligent Method for Epilepsy Seizure Detection Based on Hybrid Nonlinear EEG Data Features Using Adaptive Signal Decomposition Methods," Circuits, Systems, and Signal Processing, vol. 42, no. 5, pp. 2782-2803, 2023/05/01 2023.Google ScholarDigital Library
- Y. Sun and X. Chen, "Automatic Detection of Epilepsy Based on Entropy Feature Fusion and Convolutional Neural Network," Oxidative Medicine and Cellular Longevity, vol. 2022, p. 1322826, 2022/05/11 2022.Google ScholarCross Ref
- K. M. Hassan, M. R. Islam, T. T. Nguyen, and M. K. I. Molla, "Epileptic seizure detection in EEG using mutual information-based best individual feature selection," Expert Systems with Applications, vol. 193, p. 116414, 2022/05/01/ 2022.Google ScholarDigital Library
- A. Zou, J. Ji, M. Lei, J. Liu, and Y. Song, "Exploring Brain Effective Connectivity Networks Through Spatiotemporal Graph Convolutional Models," IEEE Transactions on Neural Networks and Learning Systems, pp. 1-13, 2022.Google Scholar
- S. Bai, J. Kolter, and V. Koltun, "An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling," 03/03 2018.Google Scholar
- S. Gupta, G. K. Yadav, and G. C. Nandi, "Development of human motion prediction strategy using inception residual block," (in English), MULTIMEDIA TOOLS AND APPLICATIONS, vol. 82, no. 14, pp. 21177-21191, JUN 2023.Google ScholarDigital Library
- Y. Huang, P. Shi, H. He, H. He, and B. Zhao, "Senet: spatial information enhancement for semantic segmentation neural networks," The Visual Computer, 2023/08/10 2023.Google Scholar
- Y. Zeng , "Deep arrhythmia classification based on SENet and lightweight context transform," Mathematical Biosciences and Engineering, vol. 20, no. 1, pp. 1-17, 2023.Google ScholarCross Ref
- F. Aksan, Y. Li, V. Suresh, and P. Janik, "CNN-LSTM vs. LSTM-CNN to Predict Power Flow Direction: A Case Study of the High-Voltage Subnet of Northeast Germany," (in eng), Sensors (Basel), vol. 23, no. 2, Jan 12 2023.Google Scholar
- F. Bayram, P. Aupke, B. S. Ahmed, A. Kassler, A. Theocharis, and J. Forsman, "DA-LSTM: A dynamic drift-adaptive learning framework for interval load forecasting with LSTM networks," Engineering Applications of Artificial Intelligence, vol. 123, p. 106480, 2023/08/01/ 2023.Google ScholarDigital Library
- X. Y. Wen and W. B. Li, "Time Series Prediction Based on LSTM-Attention-LSTM Model," (in English), IEEE ACCESS, vol. 11, pp. 48322-48331, 2023.Google Scholar
Index Terms
- An Epileptic Seizure Detection Method Based on TCN-LSTM
Recommendations
An efficient detection of epileptic seizure by differentiation and spectral analysis of electroencephalograms
Epilepsy is a critical neurological disorder resulting from abnormal hyper-excitability of neurons in the brain. Studies have shown that epilepsy can be detected in electroencephalography (EEG) recordings of patients suffering from seizures. The ...
Siamese Network-Based Feature Transformation for Improved Automated Epileptic Seizure Detection
Epilepsy is a common electrophysiological disorder of the brain, detected mainly by electroencephalogram (EEG) signals. Since correctly diagnosing epilepsy seizures by monitoring the EEG signal is very tedious and time-consuming for a neurologist, a ...
Context-learning based electroencephalogram analysis for epileptic seizure detection
BIBM '15: Proceedings of the 2015 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)Epileptic seizure is a serious health problem in the world and there is a huge population suffering from it every year. If an algorithm could automatically detect seizures and deliver the patient therapy or notify the hospital, that would be of great ...
Comments