[1]任婧雯,董朝轶,朱美佳,等.基于条件互信息的动态贝叶斯法探明生物神经元网络连接结构[J].中国医学物理学杂志,2021,38(6):773-779.[doi:DOI:10.3969/j.issn.1005-202X.2021.06.021]
　REN Jingwen,DONG Chaoyi,et al.Identification of biological neuron network connection structures by dynamic Bayesian network method based on conditional mutual information[J].Chinese Journal of Medical Physics,2021,38(6):773-779.[doi:DOI:10.3969/j.issn.1005-202X.2021.06.021]
点击复制

基于条件互信息的动态贝叶斯法探明生物神经元网络连接结构()
分享到：

《中国医学物理学杂志》[ISSN:1005-202X/CN:44-1351/R]

卷:
38卷
期数:
2021年第6期
页码:
773-779
栏目:
医学生物物理
出版日期:
2021-06-29

文章信息/Info

Title:
Identification of biological neuron network connection structures by dynamic Bayesian network method based on conditional mutual information
文章编号:
1005-202X（2021）06-0773-07
作者:
任婧雯1; 2; 董朝轶1; 2; 朱美佳1; 2; 白鹏辉1; 2; 赵肖懿1; 2; 马爽1; 2; 贾婷婷1; 2
1.内蒙古工业大学电力学院， 内蒙古 呼和浩特 010080； 2.内蒙古机电控制重点实验室， 内蒙古 呼和浩特 010051
Author(s):
REN Jingwen1;  2;  DONG Chaoyi1;  2;  ZHU Meijia1;  2;  BAI Penghui1;  2;  ZHAO Xiaoyi1;  2;  MA Shuang1;  2;  JIA Tingting1;  2
1. School of Electric Power, Inner Mongolia University of Technology, Hohhot 010080,China 2. Inner Mongolia Key Laboratory of Electromechanical Control, Hohhot 010051, China
关键词:
生物神经网络; 贝叶斯网络; 条件互信息; 积分点火模型
Keywords:
Keywords: biological neural network Bayesian network conditional mutual information integrate-and-fire model
分类号:
R318；Q612
DOI:
DOI:10.3969/j.issn.1005-202X.2021.06.021
文献标志码:
A
摘要:
准确辨识生物神经元网络（BNN）连接结构对于进一步理解其网络行为与功能，构建具有生物真实性、结构更加优化的人工智能网络具有重要意义。本文提出基于条件互信息的动态贝叶斯网络法，以探明BNN的连接结构。首先，利用积分点火原理构造脉冲神经元网络，经过网络仿真后得到多通道动态响应数据；然后，针对该数据集，计算神经元节点间的条件互信息，通过与对给定阈值δ进行比较，判断节点间的连接情况；最后，辨识出动态贝叶斯网络的连接结构。实验结果表明基于条件互信息的动态贝叶斯网络法对于BNN具有较高的辨识正确率。
Abstract:
Abstract: The accurate identification of biological neural network (BNN) connection structures helps to further understand their network behaviors and functions, and contributes to constructing biologically realistic artificial intelligent networks with more optimized structures. Dynamic Bayesian network method based on conditional mutual information is proposed for accurately identifying the connection structures of BNN. Spike neural network is firstly constructed by integrate-and-fire principle, and the multi-channel dynamic response data are obtained after network simulation. Based on the obtained data set, the conditional mutual information between neuron nodes are calculated, and the connection between nodes is assessed by comparing the calculated results with the given threshold δ. Finally, dynamic Bayesian network connection structures are identified. The experimental results reveal that dynamic Bayesian network method based on conditional mutual information has a high identification accuracy for BNN.

相似文献/References:

[1]马建川,种银保,郎朗,等.基于故障树与贝叶斯网络的呼吸机故障智能诊断[J].中国医学物理学杂志,2021,38(9):1129.[doi:10.3969/j.issn.1005-202X.2021.09.015]
　MA Jianchuan,CHONG Yinbao,LANG Lang,et al.Intelligent fault diagnosis of ventilator based on fault tree and Bayesian network[J].Chinese Journal of Medical Physics,2021,38(6):1129.[doi:10.3969/j.issn.1005-202X.2021.09.015]
[2]陆言,龚晓亮,谢非,等.基于复杂网络的秀丽隐杆线虫神经系统性质研究进展[J].中国医学物理学杂志,2022,39(11):1431.[doi:DOI:10.3969/j.issn.1005-202X.2022.11.018]
　LU Yan,GONG Xiaoliang,XIE Fei,et al.Advances in research of properties of the neural system in Caenorhabditis elegans based on complex network[J].Chinese Journal of Medical Physics,2022,39(6):1431.[doi:DOI:10.3969/j.issn.1005-202X.2022.11.018]

备注/Memo

备注/Memo:
【收稿日期】2021-02-21 【基金项目】国家自然科学基金（61863029, 61364018）；内蒙古自然科学基金杰出青年培育基金（2016JQ07）；内蒙古自治区高等学校“青年科技英才计划”（NJYT-15-A05） 【作者简介】任婧雯，硕士研究生，研究方向：复杂生物网络建模、仿真与网络结构辨识，E-mail: rjw_94@163.com 【通信作者】董朝轶，博士，教授，研究方向：复杂生物网络建模、仿真与网络结构辨识等，E-mail: dongchaoyi@hotmail.com
更新日期/Last Update: 2021-06-29