复杂网络与GA-PSO算法下的癫痫脑电识别

doi:10.3778/j.issn.1002-8331.2206-0275

摘要/Abstract

摘要： 癫痫（epilepsy，EP）是大脑神经元异常放电的一种慢性脑部神经疾病，临床上大多由专业神经科医生在癫痫患者的脑电图（electroencephalogram，EEG）信号上进行人工视觉检测分析，容易受医生的主观影响。因此，筛选有效的脑电特征对EP进行自动识别显得尤为重要。对多通道EEG信号构建相位同步（phase synchronization index，PSI）脑网络，从网络节点和结构功能角度提取15个拓扑特征，并结合支持向量机（support vector machine，SVM）分类器实现癫痫脑电自动识别。分析发现delta（δ）频带下EP脑网络连接显著增加，网络传输效率与小世界属性降低，分类效果最好。进一步将特征进行频带内与频带间交叉组合，并应用粒子群优化算法（particle swarm optimization，PSO）和引入遗传算法（genetic algorithm，GA）的改进算法GA-PSO筛选特征组合，研究发现GA-PSO算法优于PSO算法，EP识别准确率更高，且在四频带交叉下达到0.933 5。结果表明，引入GA算法使得GA-PSO算法保持种群多样性，避免出现过早收敛从而陷入局部最优，可提高种群的搜索能力，从而快速、稳定地筛选得到最优特征组合，有效对EP脑电信号进行识别。

关键词: 癫痫, 脑电, 复杂网络, 特征选择, 粒子群算法, 支持向量机

Abstract: Epilepsy（EP） is a chronic brain neurological disease with abnormal discharge of brain neurons. Clinically, most professional neurologists perform manual visual detection and analysis on electroencephalogram（EEG） signals, which is easily influenced by individual subjective opinion. Therefore, it is particularly significant to select effective EEG features for automatic recognition of epileptic seizure. The phase synchronization（PSI） brain network is constructed for the multi-channel EEG signals, and 15 topological features are extracted from the perspective of network nodes and structure functions, and support vector machine（SVM） classifier is used to realize the automatic recognition of epileptic EEG. It is found that the connection of EP brain network increases significantly in the delta （δ） frequency band, the network transmission efficiency and small world attribute decrease, and the classification performance is the best. The features are further combined with intra-band and inter-band, then the particle swarm optimization（PSO） and improved algorithm GA-PSO （with genetic algorithm（GA） introduced） are applied to determine the feature combinations. It is found that the GA-PSO algorithm performs better than PSO with a higher recognition accuracy of 0.933 5 under the four cross-frequency. The results show that the introduction of GA algorithm makes the GA-PSO algorithm maintain the diversity of the population, avoid premature convergence and fall into local optimization, and improve the search ability of the population, so as to quickly and stably screen the optimal feature combination, which can effectively recognize EEG signals of epilepsy patients.

Key words: epilepsy, electroencephalogram, complex network, feature selection, particle swarm optimization, support vector machine

王若凡, 王浩东, 石连栓. 复杂网络与GA-PSO算法下的癫痫脑电识别[J]. 计算机工程与应用, 2023, 59(20): 119-128.

WANG Ruofan, WANG Haodong, SHI Lianshuan. EEG Recognition of Epilepsy Based on Complex Network and GA-PSO[J]. Computer Engineering and Applications, 2023, 59(20): 119-128.

参考文献

[1] YANG C Z，LIU Z L，WANG Q S，et al.Epilepsy as a dynamical disorder orchestrated by epileptogenic zone：a review[J].Nonlinear Dynamics，2021，104（3）：1901-1916.
[2] MILLIGAN T A.Epilepsy：a clinical overview[J].The American Journal of Medicine，2021，134（7）：840-847.
[3] YU H T，ZHU L，CAI L H，et al.Variation of functional brain connectivity in epileptic seizures：an EEG analysis with cross-frequency phase synchronization[J].Cognitive Neurodynamics，2020，14（1）：35-49.
[4] ALVI A M，SIULY S，WANG H.Neurological abnormality detection from electroencephalography data：a review[J].Artificial Intelligence Review，2022，55（3）：2275-2312.
[5] ZHAO H，ZHU C G，HUANG D H.Microglial activation：an important process in the onset of epilepsy[J].American Journal of Translational Research，2018，10（9）：2877.
[6] BOYLAN G B，KHAROSHANKAYA L，MATHIESON S R.Diagnosis of seizures and encephalopathy using conventional EEG and amplitude integrated EEG[J].Handbook of Clinical Neurology，2019，162：363-400.
[7] AKBARI H，GHOFRANI S，ZAKALVAND P，et al.Schizophrenia recognition based on the phase space dynamic of EEG signals and graphical features[J].Biomedical Signal Processing and Control，2021，69：102917.
[8] DONOS C，DüMPELMANN M，SCHULZE-BONHAGE A.Early seizure detection algorithm based on intracranial EEG and random forest classification[J].International Journal of Neural Systems，2015，25（5）：1550023.
[9] HORTAL E，úBEDA A，Iá?EZ E，et al.EEG-based detection of starting and stopping during gait cycle[J].International Journal of Neural Systems，2016，26（7）：1650029.
[10] DAS S，PUTHANKATTIL S D.Complex network analysis of MCI-AD EEG signals under cognitive and resting state[J].Brain Research，2020，1735：146743.
[11] ELTRASS A S，TAVEL M B，EL-GADY A F.Automatic epileptic seizure detection approach based on multi-stage quantized kernel least mean square filters[J].Biomedical Signal Processing and Control，2021，70：103031.
[12] GAO Z K，DANG W D，WANG X M，et al.Complex networks and deep learning for EEG signal analysis[J].Cognitive Neurodynamics，2021，15（3）：369-388.
[13] ISMAIL L E，KARWOWSKI W.A graph theory-based modeling of functional brain connectivity based on EEG：a systematic review in the context of neuroergonomics[J].IEEE Access，2020，8：155103-155135.
[14] SITZENFREI R，WANG Q，KAPELAN Z，et al.Using complex network analysis for optimization of water distribution networks[J].Water Resources Research，2020，56（8）：e2020WR027929.
[15] RAJAEI H，CABERIZAO M，JANWATTANAPONG P，et al.Dynamics and distant effects of frontal/temporal epileptogenic focus using functional connectivity maps[J].IEEE Transactions on Biomedical Engineering，2019，67（2）：632-643.
[16] DE LA PAVA PANCHE I，áLVAREZl-MEZA A，HERRERA GóMEZ P M，et al.Kernel-based phase transfer entropy with enhanced feature relevance analysis for brain computer interfaces[J].Applied Sciences，2021，11（15）：6689.
[17] SZYMANSKI C，PESQUITA A，BRENNAN A A，et al.Teams on the same wavelength perform better：inter-brain phase synchronization constitutes a neural substrate for social facilitation[J].Neuroimage，2017，152：425-436.
[18] CAI L H，WEI X L，WANG J，et al.Reconstruction of functional brain network in Alzheimer’s disease via cross-frequency phase synchronization[J].Neurocomputing，2018，314：490-500.
[19] BUSCHE M A，HYMAN B T.Synergy between amyloid-β and tau in Alzheimer’s disease[J].Nature Neuroscience，2020，23（10）：1183-1193.
[20] PEI Z，WANG H，BEZERIANOS A，et al.EEG-based multiclass workload identification using feature fusion and selection[J].IEEE Transactions on Instrumentation and Measurement，2020，70：1-8.
[21] MAHATO S，PAUL S.Classification of depression patients and normal subjects based on electroencephalogram（EEG） signal using alpha power and theta asymmetry[J].Journal of Medical Systems，2020，44（1）：1-8.
[22] NARAYAN Y.Motor-imagery EEG signals classification using SVM，MLP and LDA classifiers[J].Turkish Journal of Computer and Mathematics Education（TURCOMAT），2021，12（2）：3339-3344.
[23] WANG R F，WANG J，YU H T，et al.Decreased coherence and functional connectivity of electroencephalograph in Alzheimer’s disease[J].Chaos，2014，24（3）：033136.
[24] WANG R F，WANG J，LI S，et al.Multiple feature extraction and classification of electroencephalograph signal for Alzheimers’ with spectrum and bispectrum[J].Chaos，2015，25（1）：013110.
[25] WANG R F，WANG J，YU H T，et al.Power spectral density and coherence analysis of Alzheimer’s EEG[J].Cognitive Neurodynamics，2015，9（3）：291-304.
[26] JAIN D，SINGH V.Feature selection and classification systems for chronic disease prediction：a review[J].Egyptian Informatics Journal，2018，19（3）：179-189.
[27] ABIODUN E O，ALABDULATIF A，ABIODUN O I，et al.A systematic review of emerging feature selection optimization methods for optimal text classification：the present state and prospective opportunities[J].Neural Computing and Applications，2021，33（22）：15091-15118.
[28] LI M，WANG H，YANG L，et al.Fast hybrid dimensionality reduction method for classification based on feature selection and grouped feature extraction[J].Expert Systems with Applications，2020，150：113277.
[29] KENNEY J，EBERHART R.Particle swarm optimization[C]//Proceedings of ICNN’95-International Conference on Neural Networks，1995：1942-1948.
[30] YALCIN N，TEZEL G，KARAKUZU C.Epilepsy diagnosis using artificial neural network learned by PSO[J].Turkish Journal of Electrical Engineering and Computer Sciences，2015，23（2）：421-432.
[31] YOUNUS Z S，D MOHAMAD，SABA T，et al.Content-based image retrieval using PSO and k-means clustering algorithm[J].Arabian Journal of Geosciences，2015，8：6211-6224.
[32] MARINI F，WALCZAK B.Particle swarm optimization（PSO）.A tutorial[J].Chemometrics and Intelligent Laboratory Systems，2015，149：153-165.
[33] YADVA S，EKBAL A，SAHA S.Information theoretic-PSO-based feature selection：an application in bio-medical entity extraction[J].Knowledge and Information Systems，2019，60（3）：1453-1478.
[34] 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，2021，179：108078.
[35] AHIRWAL M K，KUMAR A，SINGH G K.Adaptive filtering of EEG/ERP through noise cancellers using an improved PSO algorithm[J].Swarm and Evolutionary Computation，2014，14：76-91.
[36] ZHANG P，WANG J，TIAN Z，et al.A genetic algorithm with jumping gene and heuristic operators for traveling salesman problem[J].Applied Soft Computing，2022：109339.
[37] HUYNH T T B，PHAM D T，TRAN B T，et al.A multifactorial optimization paradigm for linkage tree genetic algorithm[J].Information Sciences，2020，540：325-344.
[38] NORONHA R P.Diversity control in the hybridization GA-PSO with fuzzy adaptive inertial weight[C]//2021 5th International Conference on Intelligent Computing and Control Systems（ICICCS），2021：1055-1062.
[39] CHANG S，WANG J，ZHU Y，et al.Nonlinear dynamical modeling of neural activity using volterra series with GA-enhanced particle swarm optimization algorithm[J].Cognitive Neurodynamics，2022：1-10.
[40] 吴祖河.经颅交流电刺激对运动想象任务能力影响及作用机制探索[D].北京：清华大学，2016.
WU Z H.Research on influence and mechanism of transcranial alternating current stimulation on motor imagery tasks[D].Beijing：Tsinghua University，2016.
[41] RUBINOV M，SPORNS O.Complex network measures of brain connectivity：uses and interpretations[J].Neuroimage，2010，52（3）：1059-1069.
[42] FARAHANI F V，KARWOWSKI W，LIGHTHALL N R.Application of graph theory for identifying connectivity patterns in human brain networks：a systematic review[J].Frontiers in Neuroscience，2019，13：585.
[43] KIM J，WILHELM T.What is a complex graph?[J].Physica A：Statistical Mechanics and Its Applications，2008，387（11）：2637-2652.
[44] KIM T K.Understanding one-way ANOVA using conceptual figures[J].Korean Journal of Anesthesiology，2017，70（1）：22.
[45] WANG R F，YIN Y Y，GUI Y，et al.Network measures and brain connectivity analysis of EEG signal of Alzheimer’s patients using SVM[C]//2021 40th Chinese Control Conference（CCC），2021：3143-3148.
[46] 尤洋.基于复数域分析的致痫区脑电信号识别算法研究[D].吉林：吉林大学，2017.
YOU Y.Research on recognition algorithm of epileptogenic foci EEG signals based on complex domain analysis[D].Jilin：Jilin University，2017.
[47] MANASRAH A M，BA ALI H.Workflow scheduling using hybrid GA-PSO algorithm in cloud computing[J].Wireless Communications and Mobile Computing，2018：1-16.
[48] SAWADA T，MATSUMOTO N，YOSHIDA N.Phase transition model between swarm behavior and territorial behavior[J].Journal of Computations & Modelling，2022，12（2）：1-15.