ABSTRACT
In recent years, the number of patients with depression has grown rapidly. The traditional diagnosis of depression includes mental scales, clinical inquiry etc., which is time consuming and lacks objective confirmation of relevant physiology indicators. In order to overcome the drawback of traditional methods, brain imaging techniques such as electroencephalogram (EEG) have provided new tools for diagnosing depression and shown excellent performance. In this paper, a major depressive disorder (MDD) detection framework is proposed based on parallel spatiotemporal convolution network and mix-multilayer perceptron. First, the wavelet entropy and differential entropy features of EEG were extracted and then parallel spatial temporal convolutional network and mix-multilayer perceptron were employed for further feature representation and extraction. In this process, mmd-loss was creatively added to shorten the gap between the training dataset and the test dataset. Further extracted features were fused and multilayer-perceptron (MLP) was used to perform binary classification. This experiment was evaluated on the MODMA dataset and achieved an accuracy of 0.7832. The experimental results show that the model proposed in our paper is effective in MDD detection and provides better performance compared with the baseline systems.
- Hao Chen, Ming Jin, Zhunan Li, Cunhang Fan, Jinpeng Li, and Huiguang He. 2021. MS-MDA: Multisource marginal distribution adaptation for cross-subject and cross-session EEG emotion recognition. Frontiers in Neuroscience 15 (2021), 778488.Google ScholarCross Ref
- Ruo-Nan Duan, Jia-Yi Zhu, and Bao-Liang Lu. 2013. Differential entropy feature for EEG-based emotion classification. In 2013 6th International IEEE/EMBS Conference on Neural Engineering (NER). IEEE, 81–84.Google ScholarCross Ref
- Zhongke Gao, Rumei Li, Chao Ma, Linge Rui, and Xinlin Sun. 2021. Core-brain-network-based multilayer convolutional neural network for emotion recognition. IEEE Transactions on Instrumentation and Measurement 70 (2021), 1–9.Google Scholar
- Sandhya Kumari Golla and Suman Maloji. 2023. Maximum Overlap Discrete Transform (MODT)—Gaussian Kernel Radial Network (GKRN) Model for Epileptic Seizure Detection from EEG Signals. Journal of Advances in Information Technology (2023). https://api.semanticscholar.org/CorpusID:262163201Google Scholar
- Rodrigo Capobianco Guido. 2018. A tutorial review on entropy-based handcrafted feature extraction for information fusion. Information Fusion 41 (2018), 161–175.Google ScholarDigital Library
- Sepp Hochreiter and Jürgen Schmidhuber. 1997. Long short-term memory. Neural computation 9, 8 (1997), 1735–1780.Google ScholarDigital Library
- KA Jellinger. 2011. Niedermeyer’s Electroencephalography: Basic Principles, Clinical Applications, and Related Fields, 6th edn.Google Scholar
- Ziyu Jia, Youfang Lin, Jing Wang, Ronghao Zhou, Xiaojun Ning, Yuanlai He, and Yaoshuai Zhao. 2020. GraphSleepNet: Adaptive Spatial-Temporal Graph Convolutional Networks for Sleep Stage Classification.. In IJCAI, Vol. 2021. 1324–1330.Google Scholar
- Thomas N Kipf and Max Welling. 2016. Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907 (2016).Google Scholar
- Yann Le Cun, Ofer Matan, Bernhard Boser, John S Denker, Don Henderson, Richard E Howard, Wayne Hubbard, LD Jacket, and Henry S Baird. 1990. Handwritten zip code recognition with multilayer networks. In [1990] Proceedings. 10th International Conference on Pattern Recognition, Vol. 2. IEEE, 35–40.Google Scholar
- Yann LeCun, Léon Bottou, Yoshua Bengio, and Patrick Haffner. 1998. Gradient-based learning applied to document recognition. Proc. IEEE 86, 11 (1998), 2278–2324.Google ScholarCross Ref
- Valentina Lorenzetti, Nicholas B Allen, Alex Fornito, and Murat Yücel. 2009. Structural brain abnormalities in major depressive disorder: a selective review of recent MRI studies. Journal of affective disorders 117, 1-2 (2009), 1–17.Google ScholarCross Ref
- Shalini Mahato and Sanchita Paul. 2019. Detection of major depressive disorder using linear and non-linear features from EEG signals. Microsystem Technologies 25 (2019), 1065–1076.Google ScholarDigital Library
- Reza Shalbaf, Hamid Behnam, Jamie W Sleigh, Alistair Steyn-Ross, and Logan J Voss. 2013. Monitoring the depth of anesthesia using entropy features and an artificial neural network. Journal of neuroscience methods 218, 1 (2013), 17–24.Google ScholarCross Ref
- Zhang Shu-Qing, Zhao Yu-Chun, Jia Jian, Zhang Li-Guo, and Shangguan Han-Lu. 2010. Research on the chaos recognition method based on differential entropy. Chinese Physics B 19, 6 (2010), 060514.Google ScholarCross Ref
- Ilya O Tolstikhin, Neil Houlsby, Alexander Kolesnikov, Lucas Beyer, Xiaohua Zhai, Thomas Unterthiner, Jessica Yung, Andreas Steiner, Daniel Keysers, Jakob Uszkoreit, 2021. Mlp-mixer: An all-mlp architecture for vision. Advances in neural information processing systems 34 (2021), 24261–24272.Google Scholar
- Min Wang, Heba El-Fiqi, Jiankun Hu, and Hussein A Abbass. 2019. Convolutional neural networks using dynamic functional connectivity for EEG-based person identification in diverse human states. IEEE Transactions on Information Forensics and Security 14, 12 (2019), 3259–3272.Google ScholarDigital Library
- Zonghan Wu, Shirui Pan, Fengwen Chen, Guodong Long, Chengqi Zhang, and S Yu Philip. 2020. A comprehensive survey on graph neural networks. IEEE transactions on neural networks and learning systems 32, 1 (2020), 4–24.Google ScholarCross Ref
- Yongsheng Zhu and Qinghua Zhong. 2021. Differential entropy feature signal extraction based on activation mode and its recognition in convolutional gated recurrent unit network. Frontiers in Physics 8 (2021), 629620.Google ScholarCross Ref
Index Terms
- Major Depressive Disorder Detection based on Parallel Spatiotemporal Convolution Network
Recommendations
Imagery Signal-Based Deep Learning Method for Prescreening Major Depressive Disorder
Cognitive Computing – ICCC 2019AbstractDepression is a high-risk mental illness that can lead to suicide. However, for a variety of reasons, such as a negative perception of mental illness, most patients with depressive symptoms are reluctant to go to the hospital and miss appropriate ...
Entropies based detection of epileptic seizures with artificial neural network classifiers
Computer assisted automated detection is highly inevitable for recognizing neurological disorders, as it involves continuous monitoring of Electroencephalogram (EEG) signal. Being a non-stationary signal, suitable analysis is essential for EEG to ...
Automatic recognition of vigilance state by using a wavelet-based artificial neural network
In this study, 5-s long sequences of full-spectrum electroencephalogram (EEG) recordings were used for classifying alert versus drowsy states in an arbitrary subject. EEG signals were obtained from 30 healthy subjects and the results were classified ...
Comments