计算机科学 ›› 2022, Vol. 49 ›› Issue (2): 241-247.doi: 10.11896/jsjkx.201200067

• 人工智能 • 上一篇    下一篇

静息态人脑功能超网络模型鲁棒性对比分析

张程瑞, 陈俊杰, 郭浩   

  1. 太原理工大学信息与计算机学院 山西 晋中030600
  • 收稿日期:2020-12-07 修回日期:2021-05-17 出版日期:2022-02-15 发布日期:2022-02-23
  • 通讯作者: 郭浩(feiyu_guo@sina.com)
  • 作者简介:zcr130613@163.com
  • 基金资助:
    国家自然科学基金(61672374,61741212,61876124,61873178);山西省科技厅应用基础研究项目青年面上项目(201601D021073,201801D121135);山西省教育厅高等学校科技创新研究项目(2016139);教育部赛尔网络下一代互联网技术创新项目(NGII20170712);山西省重点研发计划项目(201803D31043);国家留学基金资助出国留学项目(201708140216);国家基金面上项目(61976150)

Comparative Analysis of Robustness of Resting Human Brain Functional Hypernetwork Model

ZHANG Cheng-rui, CHEN Jun-jie, GUO Hao   

  1. School of Information and Computer,Taiyuan University of Technology,Jinzhong,Shanxi 030600,China
  • Received:2020-12-07 Revised:2021-05-17 Online:2022-02-15 Published:2022-02-23
  • About author:ZHANG Cheng-rui,born in 1996,M.S candidate.Her main research interests include intelligent information proces-sing,brain informatics.
    GUO Hao,born in 1981,Ph.D,professor,is a senior member of China Computer Federation.His main research interests include artificial intelligence,intelligent information processing,brain informatics.
  • Supported by:
    National Natural Science Foundation of China(61672374,61741212,61876124,61873178),Applied Basic Research Project of Shanxi Provincial Department of Science and Technology Youth General Project(201601D021073,201801D121135),Science and Technology Innovation Research Project of Shanxi(2016139),CERNET Innovation Project Provincial Department of Education(NGII20170712),Key R & D projects In Shanxi Province(201803D31043),Study Abroad Program Supported by National Study Fund(201708140216) and General Projects of National Fund(61976150).

摘要: 鲁棒性作为一种动态行为也是超网络领域的研究热点,对构建鲁棒网络具有重要的现实意义。尽管对超网络的研究越来越多,但对其动态研究相对较少,尤其是在神经影像领域。在现有的脑功能超网络研究中,大多是探究网络的静态拓扑属性,并没有相关研究对脑功能超网络的动力学特性——鲁棒性展开分析。针对这些问题,文中首先引入lasso,group lasso和sparse group lasso方法来求解稀疏线性回归模型以构建超网络;然后基于蓄意攻击中的节点度和节点介数攻击两种实验模型,利用全局效率和最大连通子图相对大小探究脑功能超网络在应对攻击时的节点失效网络的鲁棒性,最后通过实验进行对比分析,以探究更为稳定的网络。实验结果表明,在蓄意攻击模式下,group lasso和sparse group lasso方法构建的超网络的鲁棒性更强一些。同时,综合来看,group lasso方法构建的超网络最稳定。

关键词: group lasso, lasso, sparse group lasso, 超网络, 鲁棒性, 脑网络, 蓄意攻击

Abstract: As a kind of dynamic behavior,robustness is also a research hotspot in the field of hypernetworks,which has important practical significance for the construction of robust networks.Although there are more and more researches on hypernetwork,the dynamic research is relatively less,especially in the field of neural imaging.Most of the existing researches on brain functional hypernetworks are about the static topological properties of the networks,and there is no relevant research on the dynamic characteristics robustness of brain functional hypernetworks.To solve these problems,lasso,group lasso and sparse group lasso me-thods are used to solve the sparse linear regression model to construct a hypernetwork.Then,based on the two experimental mo-dels of deliberate attack,node degree and node betweenness attack,the robustness of brain functional hypernetwork in response to node failure is explored by using the global efficiency and the relative size of the largest connected subgraph.Finally,a comparative analysis is made to explore a more stable network.The experimental results show that the hypernetwork constructed by group lasso and sparse group lasso is more robust in intentional attack mode.At the same time,the hypernetwork constructed by group lasso method is the most stable.

Key words: Brain network, Group lasso, Hypernetwork, Intentional attack, Lasso, Robustness, Sparse group lasso

中图分类号: 

  • TP393
[1]KHALIL H K.Nonlinear Systems[M].Publishing House ofElectronics Industry,2002.
[2]OSOBA A,HÄNGGI J,LI M,et al.Disease severity is correlated to tract specific changes of fractional anisotropy in MD and CM thalamus-A DTI study in major depressive disorder[J].Journal of Affective Disorders,2013,149(1/2/3):116-128.
[3]LIU F,GUO W,LIU L,et al.Abnormal amplitude low-frequen-cy oscillations in medication-naive,first-episode patients with major depressive disorder:A resting-state fMRI study[J].Journal of Affective Disorders,2012,146(3):401-406.
[4]TAN Y J,LU X,WU J,et al.On the invulnerability research of complex networks[J].Systems Engineering Theory and Practice,2008,6:116-120.
[5]LO C,SU T W,HUANG C C,et al.Randomization and resi-lience of brain functional networks as systems-level endophenotypes of schizophrenia[J].Proceedings of the National Academy of Sciences,2015,112(29):9123-9128.
[6]HE Y,CHEN Z,EVANS A.Structural Insights into AberrantTopological Patterns of Large-Scale Cortical Networks inAlz-heimer's Disease[J].The Journal of Neuroence:The Official Journal of the Society for Neuroence,2008,28(18):4756-4766.
[7]AJILORE O,LAMAR M,LEOW A,et al.Graph Theory Analysis of Cortical-Subcortical Networks in Late-Life Depression[J].American Journal of Geriatric Psychiatry,2014,22(2):195-206.
[8]JIE B,WEE C Y,SHEN D,et al.Hyper-Connectivity of Functional Networks for Brain Disease Diagnosis[J].Medical Image Analysis,2016,32(17):84-100.
[9]WANG M L,HAO X K.Discovering network phenotype be-tween genetic risk factors and disease status via diagnosis-aligned multi-modality regression method in Alzheimer's Disease[J].Bioinformatics,2018(11):11.
[10]GUO H,LI Y,XU Y,et al.Resting-State Brain Functional Hyper-Network Construction 1129 Based on Elastic Net and Group Lasso Methods[J].Frontiers in Neuroinformatics,2018,12:25-43.
[11]JIN Y Y,GUO H,CHEN J J.Optimization of resting state brain functional hypernetwork construction based on elasticnet me-thod[J].Computer Applied Research,2018,33(11):3276-3280,3297.
[12]MEIER L,GEER S V D,BÜHLMANN P.The group Lasso for logistic regression[J].Journal of the Royal Statal Society:Series B (Statal Methodology),2008,70:53-71.
[13]FRIEDMAN J,HASTIE T,TIBSHIRANI R.A note on thegroup lasso and a sparse group lasso[J].Stats,2010,34(1):1-8.
[14]OGUTU J O,PIEPHO H P.Regularized group regression me-thods for genomic prediction:Bridge,MCP,SCAD,group bridge,group lasso,sparse group lasso,group MCP and group SCAD[J].Bmc Proceedings,2014,8(5):1-9.
[15]FORNITO A,ZALESKY A,BREAKSPEAR M.Graph analysis of the human connectome:promise,progress,and pitfalls[J].Neuroimage,2013,80:426-444.
[16]ZHANG C,YONG H.Revealing Modular Architecture of Hu-man Brain Structural Networks by Using Cortical Thickness from MRI[J].Cerebral Cortex,2008,18(10):2374-2381.
[17]SANTOS G S,GIREESH E D,PLENZ D,et al.Hierarchical Interaction Structure of Neural Activities in Cortical Slice Cultures[J].The Journal of Neuroscience,2010,30(26):8720.
[18]TZOURIO-MAZOYER N,LANDEAU B,PAPATHANAS-SIOU D,et al.Automated Anatomical Labeling of Activations in SPM Using a Macroscopic Anatomical Parcellation of the MNI MRI Single-Subject Brain[J].Neuroimage,2002,15(1):273-289.
[19]SANTOS G S,GIREESH E D,PLENZ D,et al.Hierarchical In-teraction Structure of Neural Activities in Cortical Slice Cultures[J].The Journal of Neuroscience,2010,30(26):8720.
[20]LI Y,GAO X Q,JIE B,et al.Multimodal Hyper-connectivityNetworks for MCI Classification[J].Medical image computing and computer-assisted intervention:MICCAI.International Conference on Medical Image Computing and Computer-Assisted Intervention,2017,20:433-441.
[21]ZU C,YUE G,BRENT M,et al.Identifying disease-related subnetwork connectome biomarkers by sparse hypergraph learning[J].Brain Imaging and Behavior,2018,13:879-892.
[22]WEE C Y,YAP P T,ZHANG D,et al.Group-constrainedsparse fMRI connectivity modeling for mild cognitive impairment identification[J].Brain Structure and Function,2014,219(2):641-656.
[23]HYEKYOUNG L,DONG S L,HYEJIN K,et al.Sparse Brain Network Recovery Under Compressed Sensing[J].IEEE Tran-sactions on Medical Imaging,2011,30(5):1-31.
[24]LIU J,JI S W,YE J P.SLEP:sparse learning with efficient projections[R].Arizona:Arizona State University,2013.
[25]YUAN M,LIN Y.Model selection and estimation in regression with grouped variables[J].Journal of the Royal Statal Society:Series B (Statal Methodology),2006,68(1):49-67.
[26]PARK H S,JUN C H.A Simple And Fast Algorithm For K-medoids Clustering[J].Expert Systems with Applications,2009,36(Part2):3336-3341.
[27]MONTI R P,HYVÄRINEN A.A Unified Probabilistic Model for Learning Latent Factors and Their Connectivities from High-Dimensional Data[J].Conference on Uncertainty in Artificial Intelligence,2018.
[28]SUO Q,GUO J L.The structure and dynamics of hypernetworks[J].Systems Engineering-theory & Practice,2017,37(3):720-734.
[29]LIANG X,WANG J H,HE Y.Brain connectome study:brain structural network and brain functional network[J].Scientific Bulletin,2010,55(16):1565-1583.
[30]ESTRADA E,RODRÍGUEZ-VELÑZQUEZ J A.Subgraph centrality and clustering in complex hyper-networks[J].Physica A,2006,364(none):581-594.
[31]WANG F H,WAN N,WANG L,et al.Study on Location and Robustness of Freight High-railway Hypernetwork[J].Tech-noeconomics & Management Research,2017(10):17-23.
[32]SMART A G,AMARAL L A N,OTTINO J M.Cascading fai-lure and robustness in metabolic networks[J].Proceedings of the National Academy of Sciences,2008,105(36):13223-13228.
[33]IYER S,KILLINGBACK T,SUNDARAM B,et al.Attack robustness and centrality of complex networks[J].PloS one,2013,8(4):1-17.
[34]DAI F,LIN J,HU J,et al.Analysis of robustness in electromagnetic compatibility supernetwork[C]//2013 5th IEEE International Symposium on Microwave,Antenna,Propagation and EMC Technologies for Wireless Communications.IEEE,2013:515-518.
[35]LU R M,GUO J L.Topological characteristics and robustness analysis of Shanghai public transport super network[J].Mathematics in Practice and Theory,2018,58 (20):131-139.
[36]YU W,WANG T,ZHENG Y,et al.Parameter Selection andEvaluation of Robustness of Nanjing Metro Network Based on Supernetwork[J].IEEE Access,2019,7:70876-70890.
[37]PEI W D,XIA W,MA X R,et al.Robustness and Statistical Characters of a Class of Complex Network Models[J].Recent Advances in Computer Science and Information Engineering,2012,129:747-752.
[38]XIE T Y,KANG K,WANG J J,et al.Robustness analysis of supply chain network with random and intentional attacks[J].Mathematics in Practice and Theory,2018(16):40-47.
[39]ZHANG H,WU W,ZHAO L.A study of knowledge supernetworks and network robustness in different business incubators[J].Physica A:Statistical Mechanics and its Applications,2016,447:545-560.
[40]ALBERT R,JEONG H,BARABASI A L.Error and attack to-lerance of complex networks[J].Nature,2000,340(6794):378-382.
[41]LI Y,SUN C,LI P,et al.Hypernetwork Construction and Feature Fusion Analysis Based on Sparse Group Lasso Method on Functional fMRI Dataset[J].Frontiers in Neuroence,2020,14(60):243-244.
[42]LI H,ZHOU H,YANG Y,et al.More randomized and resilient in the topological properties of functional brain networks in patients with major depressive disorder[J].Journal of Clinical Neuroscience Official Journal of the Neurosurgical Society of Australasia,2017,44:274-278.
[1] 李瑶, 李涛, 李埼钒, 梁家瑞, Ibegbu Nnamdi JULIAN, 陈俊杰, 郭浩.
基于多尺度的稀疏脑功能超网络构建及多特征融合分类研究
Construction and Multi-feature Fusion Classification Research Based on Multi-scale Sparse Brain Functional Hyper-network
计算机科学, 2022, 49(8): 257-266. https://doi.org/10.11896/jsjkx.210600094
[2] 周慧, 施皓晨, 屠要峰, 黄圣君.
基于主动采样的深度鲁棒神经网络学习
Robust Deep Neural Network Learning Based on Active Sampling
计算机科学, 2022, 49(7): 164-169. https://doi.org/10.11896/jsjkx.210600044
[3] 闫萌, 林英, 聂志深, 曹一凡, 皮欢, 张兰.
一种提高联邦学习模型鲁棒性的训练方法
Training Method to Improve Robustness of Federated Learning
计算机科学, 2022, 49(6A): 496-501. https://doi.org/10.11896/jsjkx.210400298
[4] 李鹏祖, 李瑶, Ibegbu Nnamdi JULIAN, 孙超, 郭浩, 陈俊杰.
基于多特征融合的重叠组套索脑功能超网络构建及分类
Construction and Classification of Brain Function Hypernetwork Based on Overlapping Group Lasso with Multi-feature Fusion
计算机科学, 2022, 49(5): 206-211. https://doi.org/10.11896/jsjkx.210300049
[5] 穆俊芳, 郑文萍, 王杰, 梁吉业.
基于重连机制的复杂网络鲁棒性分析
Robustness Analysis of Complex Network Based on Rewiring Mechanism
计算机科学, 2021, 48(7): 130-136. https://doi.org/10.11896/jsjkx.201000108
[6] 胡聿文.
基于优化LSTM模型的股票预测
Stock Forecast Based on Optimized LSTM Model
计算机科学, 2021, 48(6A): 151-157. https://doi.org/10.11896/jsjkx.200400011
[7] 王学光, 张爱新, 窦炳琳.
复杂网络上的非线性负载容量模型
Non-linear Load Capacity Model of Complex Networks
计算机科学, 2021, 48(6): 282-287. https://doi.org/10.11896/jsjkx.200700040
[8] 仝鑫, 王斌君, 王润正, 潘孝勤.
面向自然语言处理的深度学习对抗样本综述
Survey on Adversarial Sample of Deep Learning Towards Natural Language Processing
计算机科学, 2021, 48(1): 258-267. https://doi.org/10.11896/jsjkx.200500078
[9] 吴庆洪, 高晓东.
稀疏表示和支持向量机相融合的非理想环境人脸识别
Face Recognition in Non-ideal Environment Based on Sparse Representation and Support Vector Machine
计算机科学, 2020, 47(6): 121-125. https://doi.org/10.11896/jsjkx.190500058
[10] 卢冬冬, 吴洁, 刘鹏, 盛永祥.
开源软件关键开发者类型及协作网络鲁棒性分析
Analysis of Key Developer Type and Robustness of Collaboration Network in Open Source Software
计算机科学, 2020, 47(12): 100-105. https://doi.org/10.11896/jsjkx.200300147
[11] 陈晓文, 刘光帅, 刘望华, 李旭瑞.
结合LoG边缘检测和增强局部相位量化的模糊图像识别
Blurred Image Recognition Based on LoG Edge Detection and Enhanced Local Phase Quantization
计算机科学, 2020, 47(12): 197-204. https://doi.org/10.11896/jsjkx.191000054
[12] 高利剑,毛启容.
环境辅助的多任务混合声音事件检测方法
Environment-assisted Multi-task Learning for Polyphonic Acoustic Event Detection
计算机科学, 2020, 47(1): 159-164. https://doi.org/10.11896/jsjkx.190200365
[13] 赵志刚, 周根贵, 李虎雄.
复杂加权供应链网络攻击策略和鲁棒性研究
Study on Attack Strategy and Robustness of Complex Weighted Supply Chain Network
计算机科学, 2019, 46(8): 138-144. https://doi.org/10.11896/j.issn.1002-137X.2019.08.023
[14] 唐倩文, 陈良育.
基于复杂网络理论的Java开源系统演化分析
Analysis of Java Open Source System Evolution Based on Complex Network Theory
计算机科学, 2018, 45(8): 166-173. https://doi.org/10.11896/j.issn.1002-137X.2018.08.030
[15] 杜伟静, 赵峰, 高锋阳.
基于EEMD-RobustICA和Prony算法的谐波和间谐波检测方法
Harmonic and Inter-harmonic Detection Method Based on EEMD-RobustICA and Prony Algorithm
计算机科学, 2018, 45(11A): 564-568.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!