Computer Science ›› 2022, Vol. 49 ›› Issue (7): 57-63.doi: 10.11896/jsjkx.210800070

• Database & Big Data & Data Science • Previous Articles     Next Articles

Application of Graph Neural Network Based on Data Augmentation and Model Ensemble in Depression Recognition

YANG Bing-xin, GUO Yan-rong, HAO Shi-jie, Hong Ri-chang   

  1. School of Computer Science and Information Engineering,Hefei University of Technology,Hefei 230601,China
  • Received:2021-08-08 Revised:2022-03-02 Online:2022-07-15 Published:2022-07-12
  • About author:YANG Bing-xin,born in 1995,postgra-duate.His main research interests include machine learning and computer vision.
    GUO Yan-rong,born in 1984,professor.Her main research interests include biomedical image segmentation and ana-lysis.
  • Supported by:
    National Key R&D Program of China(2019YFA0706200),National Nature Science Foundation of China(62072152),Natural Science Foundation of Anhui Province,China(1808085QF188) and Fundamental Research Funds for the Central Universities of Ministry of Education of China(PA2020GDKC0023,PA2019GDZC0095).

Abstract: At present,the mainstream diagnosis of depression is through the communication between doctors and patients,filling in the relevant questionnaire,which needs corresponding clinical knowledge and is subjective.It brings a lot of challenges to the diagnosis of depression.Using information processing technology to analyze physiological signals and build an accurate and objective auxiliary diagnosis model is of great value.However,the sample size of the public data set of depression auxiliary diagnosis is generally small,which makes the accuracy of auxiliary diagnosis is generally low.On this basis,this paper proposes a graph neural network (GNN) method for depression recognition based on data augmentation and model ensemble strategy.The method uses 128 channel EEG signals of 53 subjects and segments the collected EEG data.After data augmentation,Pearson correlation coefficient is used to calculate the correlation between different channels to construct a brain network,graph neural network is used to learn the features of brain network,and the final prediction results are obtained by majority voting with model ensemble strategy.Experimental results show that the proposed method improves the classification ability of the network and solves the problem of poor classification performance caused by small sample size.The proposed method achieves 77% classification accuracy on the MODMA data set(including 24 patients with depression and 29 normal controls) provided by the Pervasive Sensing and Intelligent Systems Laboratory of Lanzhou University.The classification accuracy of the proposed method is significantly improved compared to other methods.

Key words: Classification, Data augmentation, Depression recognition, EEG, Graph neural network, Model ensemble

CLC Number: 

  • TP391
[1]ZUNG W W.A Self-Rating Depression Scale[J].Archives ofGeneral Psychiatry,1965,12(1):63-70.
[2]EHDE D M.Hamilton Depression Rating Scale[M]//Encyclopedia of Clinical Neuropsychology.New York:Springer,2011:1205-1207.
[3]BECK A T,STEER R A,CARBIN M G.Psychometric properties of the Beck Depression Inventory:Twenty-five years of evaluation[J].Clinical Psychology Review,1988,8(1):77-100.
[4]SEGAL D L.Diagnostic and Statistical Manual of Mental Disorders(DSM-IV-TR) [M]//The Corsini Encyclopedia of Psychology.John Wiley & Sons,Ltd,2010:1-3.
[5]CHANG C C,LIN C J.LIBSVM:a library for support vector machines[J].ACM transactions on intelligent systems and technology(TIST),2011,2(3):1-27.
[6]PETERSON L E.K-nearest neighbor[J].Scholarpedia,2009,4(2):1883-1895.
[7]CAI H,QU Z,LI Z,et al.Feature-level Fusion ApproachesBased on Multimodal EEG Data for Depression Recognition[J].Information Fusion,2020,59:127-138.
[8]HU B,RAO J,LI X,et al.Emotion regulating attentional control abnormalities in major depressive disorder:an event-related potential study[J].Scientific Reports,2017,7(1):1-21.
[9]JIANG H,HU B,LIU Z,et al.Investigation of different speech types and emotions for detecting depression using different classifiers[J].Speech Communication,2017,90:39-46.
[10]LI X,TONG C,SUN S,et al.Classification study on eye movement data:Towards a new approach in depression detection[C]//2016 IEEE Congress on Evolutionary Computation (CEC).IEEE,2016:1227-1232.
[11]LU S,XU J,LI M,et al.Attentional bias scores in patients with depression and effects of age:a controlled,eye-tracking study[J].Journal of International Medical Research,2017,45(4):1518-1527.
[12]BAILEY N W,KREPEL N,DIJK H V,et al.Resting EEG theta connectivity and alpha power to predict repetitive transcranial magnetic stimulation response in depression:A non-replication from the ICON-DB consortium[J].Clinical Neurophysiology,2021,132(2):650-659.
[13]ZHU J,WANG Z,GONG T,et al.An Improved Classification Model for Depression Detection Using EEG and Eye Tracking Data[J].IEEE Transactions on Nano Bioscience,2020,19(3):527-537.
[14]CHEN F,ZHAO L,LI B,et al.Depression evaluation based on prefrontal EEG signals in resting state using fuzzy measure entropy[J/OL].Physiological Measurement,2020,41(9):095007.
[15]LI X W,HU B,SUN S T,et al.EEG-based mild depressive detection using feature selection methods and classifiers.[J].Computer Methods & Programs in Biomedicine,2016,136(C):151-161.
[16]LI P,SONG X,JING W,et al.Reduced sensitivity to neutralfeedback versus negative feedback in subjects with mild depression:Evidence from event-related potentials study[J].Brain & Cognition,2015,100(NOV.):15-20.
[17]ACHARYA U R,SUDARSHAN V K,ADELI H,et al.A Novel Depression Diagnosis Index Using Nonlinear Features in EEG Signals[J].European Neurology,2016,74:79-83.
[18]KAUR C,SINGH P,BISHT A,et al.EEG Signal denoisingusing hybrid approach of Variational Mode Decomposition and wavelets for depression[J].Biomedical Signal Processing and Control,2020,65(4):102337.
[19]MAHATO S,GOYAL N,RAM D,et al.Detection of Depression and Scaling of Severity Using Six Channel EEG Data[J].Journal of Medical Systems,2020,44(7):118.
[20]BOCHAROV A V,KNYAZEV G G,Savostyanov A N,et al.Relationship of Depression,Anxiety,and Rumination Scores with EEG Connectivity of Resting State Networks[J].Human Physiology,2021,47(2):123-127.
[21]CAI H,HAN J,CHEN Y,et al.A Pervasive Approach to EEG-Based Depression Detection[J/OL].Complexity,2018(1):13.
[22]AKBARI H,SADIQ M T,REHMAN A U,et al.Depression recognition based on the reconstruction of phase space of EEG signals and geometrical features[J].Applied Acoustics,2021,179:1-16.
[23]ZHANG X,HU B,ZHOU L,et al.An EEG based pervasive depression detection for females[C]//Joint International Confe-rence on Pervasive Computing and the Networked World.Berlin:Springer,2012:848-861.
[24]HOSSEINIFARD B,MORADI M H,ROSTAMI R.Classifying depression patients and normal subjects using machine learning techniques and nonlinear features from EEG signal[J].Compu-ter Methods and Programs in biomedicine.2013,109(3):339-345.
[25]LIAO S C,WU C T,HUANG H C,et al.Major Depression Detection from EEG Signals Using Kernel Eigen-Filter-Bank Common Spatial Patterns[J].Sensors,2017,17(6):1385-1402.
[26]ZHONG P,WANG D,MIAO C.EEG-Based Emotion Recognition Using Regularized Graph Neural Networks[J/OL].IEEE Transactions on Affective Computing,2020.
[27]SONG T,LIU S,ZHENG W,et al.Instance-Adaptive Graph for EEG Emotion Recognition[C]//Proceedings of the AAAI Conference on Artificial Intelligence.2020:2701-2708.
[28]SUNS T,LI X W,ZHU J,et al.Graph Theory Analysis ofFunctional Connectivity in Major Depression Disorder with High-Density Resting State EEG Data[J].IEEE transactions on neural systems and rehabilitation engineering:a publication of the IEEE Engineering in Medicine and Biology Society,2019,27(3):429-439.
[29]SCARSELLI F,GORI M,AC TSOI,et al.The Graph Neural Network Model[J].IEEE Transactions on Neural Networks,2009,20(1):61-80.
[30]DOUGLAS B L.The Weisfeiler-Lehman Method and Graph Isomorphism Testing[J].arXiv:1101.5211,2011.
[31]XU K,HU W,LESKOVEC J,et al.How powerful are graphneural networks? [J].arXiv:1810.00826,2018.
[32]WIENER G.Search for a majority element[J].Journal of Statistical Planning & Inference,2002,100(2):313-318.
[33]CAI H,GAO Y,SUN S,et al.MODMA dataset:a Multi-model Open Dataset for Mental- disorder Analysis[J].arXiv:2002.09283,2020.
[34]NGUYEN D Q,NGUYEN T D,PHUNG D.Unsupervised Universal Self-Attention Network for Graph Classification[J].ar-Xiv:1909.11855,2019.
[35]ZHANG Z,BU J,ESTER M,et al.Hierarchical Graph Pooling with Structure Learning[J].arXiv:1911.05954,2019.
[36]YANG J,NIU J,ZENG S,et al.Resting state EEG based depression recognition research using voting strategy method[C]//2018 IEEE International Conference on Bioinformatics and Biomedicine(BIBM).IEEE,2018:2666-2673.
[1] CHEN Zhi-qiang, HAN Meng, LI Mu-hang, WU Hong-xin, ZHANG Xi-long. Survey of Concept Drift Handling Methods in Data Streams [J]. Computer Science, 2022, 49(9): 14-32.
[2] ZHOU Fang-quan, CHENG Wei-qing. Sequence Recommendation Based on Global Enhanced Graph Neural Network [J]. Computer Science, 2022, 49(9): 55-63.
[3] ZHOU Xu, QIAN Sheng-sheng, LI Zhang-ming, FANG Quan, XU Chang-sheng. Dual Variational Multi-modal Attention Network for Incomplete Social Event Classification [J]. Computer Science, 2022, 49(9): 132-138.
[4] HAO Zhi-rong, CHEN Long, HUANG Jia-cheng. Class Discriminative Universal Adversarial Attack for Text Classification [J]. Computer Science, 2022, 49(8): 323-329.
[5] WU Hong-xin, HAN Meng, CHEN Zhi-qiang, ZHANG Xi-long, LI Mu-hang. Survey of Multi-label Classification Based on Supervised and Semi-supervised Learning [J]. Computer Science, 2022, 49(8): 12-25.
[6] TAN Ying-ying, WANG Jun-li, ZHANG Chao-bo. Review of Text Classification Methods Based on Graph Convolutional Network [J]. Computer Science, 2022, 49(8): 205-216.
[7] YAN Jia-dan, JIA Cai-yan. Text Classification Method Based on Information Fusion of Dual-graph Neural Network [J]. Computer Science, 2022, 49(8): 230-236.
[8] QI Xiu-xiu, WANG Jia-hao, LI Wen-xiong, ZHOU Fan. Fusion Algorithm for Matrix Completion Prediction Based on Probabilistic Meta-learning [J]. Computer Science, 2022, 49(7): 18-24.
[9] GAO Zhen-zhuo, WANG Zhi-hai, LIU Hai-yang. Random Shapelet Forest Algorithm Embedded with Canonical Time Series Features [J]. Computer Science, 2022, 49(7): 40-49.
[10] ZHANG Hong-bo, DONG Li-jia, PAN Yu-biao, HSIAO Tsung-chih, ZHANG Hui-zhen, DU Ji-xiang. Survey on Action Quality Assessment Methods in Video Understanding [J]. Computer Science, 2022, 49(7): 79-88.
[11] DU Li-jun, TANG Xi-lu, ZHOU Jiao, CHEN Yu-lan, CHENG Jian. Alzheimer's Disease Classification Method Based on Attention Mechanism and Multi-task Learning [J]. Computer Science, 2022, 49(6A): 60-65.
[12] LI Xiao-wei, SHU Hui, GUANG Yan, ZHAI Yi, YANG Zi-ji. Survey of the Application of Natural Language Processing for Resume Analysis [J]. Computer Science, 2022, 49(6A): 66-73.
[13] DENG Kai, YANG Pin, LI Yi-zhou, YANG Xing, ZENG Fan-rui, ZHANG Zhen-yu. Fast and Transmissible Domain Knowledge Graph Construction Method [J]. Computer Science, 2022, 49(6A): 100-108.
[14] HUANG Shao-bin, SUN Xue-wei, LI Rong-sheng. Relation Classification Method Based on Cross-sentence Contextual Information for Neural Network [J]. Computer Science, 2022, 49(6A): 119-124.
[15] LIN Xi, CHEN Zi-zhuo, WANG Zhong-qing. Aspect-level Sentiment Classification Based on Imbalanced Data and Ensemble Learning [J]. Computer Science, 2022, 49(6A): 144-149.
Full text



No Suggested Reading articles found!