[1]黄承宁,李 娟,陈嘉政.基于图神经网络的医疗物资智能调度研究优化[J].计算机技术与发展,2021,31(09):202-207.[doi:10. 3969 / j. issn. 1673-629X. 2021. 09. 034]
　HUANG Cheng-ning,LI Juan,CHEN Jia-zheng.Research and Optimization of Medical Material Intelligent Scheduling Based on Graph Neural Network[J].,2021,31(09):202-207.[doi:10. 3969 / j. issn. 1673-629X. 2021. 09. 034]
点击复制

基于图神经网络的医疗物资智能调度研究优化()
分享到：

《计算机技术与发展》[ISSN:1006-6977/CN:61-1281/TN]

卷:
31
期数:
2021年09期
页码:
202-207
栏目:
应用前沿与综合
出版日期:
2021-09-10

文章信息/Info

Title:
Research and Optimization of Medical Material Intelligent Scheduling Based on Graph Neural Network
文章编号:
1673-629X(2021)09-0202-06
作者:
黄承宁; 李 娟; 陈嘉政
南京工业大学浦江学院,江苏 南京 211222
Author(s):
HUANG Cheng-ning; LI Juan; CHEN Jia-zheng
Nanjing Tech University Pujiang Institute,Nanjing 211222,China
关键词:
智慧医疗; 图神经网络; 智能调度; 数据驱动; 问题建模
Keywords:
intelligent medical; graph neural network; intelligent scheduling; data driven:problem modeling
分类号:
TP39
DOI:
10. 3969 / j. issn. 1673-629X. 2021. 09. 034
摘要:
针对目前动态建模和数据驱动的方法对中长期流量预测的研究存在计算功率消耗大和准确率不够高,不足以预测医疗物资运输中交通流量的不确定性和复杂性的问题,文中把病毒传播用图神经网络提出了一个以解决物资调度时间序列预测问题建模。 以 NGSIM 数据集 IDM 参数和 HighD 数据集等为研究对象,基于 GCN 基于节点的图分类或预测的方法删除了自连接,引入了权重矩阵,同时将输出层替换为对每个节点的功能独立运行的前馈层。 这样可以更好地解耦特征提取和根据提取的特征进行的最终预测。 实验表明,优化的模型更有效捕获全面的时空相关性,将预测误差降低了30% 以上达到最佳基准模型,提升了医疗物资调度效率。
Abstract:
Aiming at the problems that the research on medium and long-term flow prediction by dynamic modeling and data-driven method has high computational power consumption and low accuracy at present, which is not enough to predict the uncertainty and complexity of traffic flow in the transportation of medical supplies,a graph neural network model for virus transmission is proposed to solve the problem of material scheduling time series prediction. Taking the IDM parameters of NGSIM data set and High D data set as there search objects,the GCN based graph classification or prediction method eliminates the self connection,introduces the weight matrix,and replaces the output layer with the feed-forward layer which operates independently for each node’s function. In this way,the feature extraction and the final prediction based on the extracted features can be better decoupled. The experiment shows that the optimized model can capture the overall spatial-temporal correlation more effectively,reduce the prediction error by more than 30% to achieve the optimal benchmark model,and improve the efficiency of medical material scheduling.

相似文献/References:

[1]郝晓培,朱建生,单杏花.图神经网络在 12306 黑产用户挖掘的研究[J].计算机技术与发展,2022,32(07):185.[doi:10. 3969 / j. issn. 1673-629X. 2022. 07. 032]
　HAO Xiao-pei,ZHU Jian-sheng,SHAN Xing-hua.Research on Graph Neural Network in 12306 Black Production User Mining[J].,2022,32(09):185.[doi:10. 3969 / j. issn. 1673-629X. 2022. 07. 032]
[2]吴长旺,黄 刚,胡婷婷.融合注意力机制的 GNN 推荐算法[J].计算机技术与发展,2022,32(10):7.[doi:10. 3969 / j. issn. 1673-629X. 2022. 10. 002]
　WU Chang-wang,HUANG Gang,HU Ting-ting.GNN Recommendation Algorithm Fused with Attention Mechanism[J].,2022,32(09):7.[doi:10. 3969 / j. issn. 1673-629X. 2022. 10. 002]
[3]仇亚进,奚雪峰 *,崔志明,等.多跳式机器阅读理解研究进展综述[J].计算机技术与发展,2023,33(02):9.[doi:10. 3969 / j. issn. 1673-629X. 2023. 02. 002]
　QIU Ya-jin,XI Xue-feng *,CUI Zhi-ming,et al.Review on Research Progress of Multi-hop Machine Reading Comprehension[J].,2023,33(09):9.[doi:10. 3969 / j. issn. 1673-629X. 2023. 02. 002]
[4]尹拓凯*,岳文静,陈 志.面向拜占庭攻击的认知用户分类[J].计算机技术与发展,2023,33(04):102.[doi:10. 3969 / j. issn. 1673-629X. 2023. 04. 015]
　YIN Tuo-kai*,YUE Wen-jing,CHEN Zhi.Cognitive User Classification for Byzantine Attack[J].,2023,33(09):102.[doi:10. 3969 / j. issn. 1673-629X. 2023. 04. 015]
[5]高 贵,赵 阳,于舒娟,等.基于 GNN 的文本分类算法研究[J].计算机技术与发展,2023,33(05):138.[doi:10. 3969 / j. issn. 1673-629X. 2023. 05. 021]
　GAO Gui,ZHAO Yang,YU Shu-juan,et al.Research on Text Classification Algorithm Based on GNN[J].,2023,33(09):138.[doi:10. 3969 / j. issn. 1673-629X. 2023. 05. 021]
[6]张 鑫,冼广铭*,梅灏洋,等.基于 Span 方法和多叉解码树的实体关系抽取[J].计算机技术与发展,2023,33(05):152.[doi:10. 3969 / j. issn. 1673-629X. 2023. 05. 023]
　ZHANG Xin,XIAN Guang-ming*,MEI Hao-yang,et al.Entity Relation Extraction Based on Span Method and Multi-fork Decoding Tree[J].,2023,33(09):152.[doi:10. 3969 / j. issn. 1673-629X. 2023. 05. 023]
[7]胡 飞,陈 昊,王 媛,等.基于图网络的 Java 反序列化漏洞检测方法[J].计算机技术与发展,2023,33(05):122.[doi:10. 3969 / j. issn. 1673-629X. 2023. 05. 019]
　HU Fei,CHEN Hao,WANG Yuan,et al.Call Chain Detection Method for Java Deserialization Vulnerability Based on Graph Network[J].,2023,33(09):122.[doi:10. 3969 / j. issn. 1673-629X. 2023. 05. 019]
[8]张 攀,来风刚,周 逸,等.基于多通道注意力图卷积网络的微服务分解[J].计算机技术与发展,2023,33(08):66.[doi:10. 3969 / j. issn. 1673-629X. 2023. 08. 010]
　ZHANG Pan,LAI Feng-gang,ZHOU Yi,et al.Multi-channel Attentional Graph Convolutional Networks for Microservice Extraction[J].,2023,33(09):66.[doi:10. 3969 / j. issn. 1673-629X. 2023. 08. 010]
[9]马 华,姜 伟,陈 明,等.基于图滤波器的符号属性图链路关系预测算法[J].计算机技术与发展,2023,33(09):126.[doi:10. 3969 / j. issn. 1673-629X. 2023. 09. 019]
　MA Hua,JIANG Wei,CHEN Ming,et al.Link Relationship Prediction Algorithm for Attributed and Signed Graphs Based on Graph Filter[J].,2023,33(09):126.[doi:10. 3969 / j. issn. 1673-629X. 2023. 09. 019]

更新日期/Last Update: 2021-09-10