典型文献
Combat network link prediction based on embedding learning
文献摘要：
Link prediction of combat networks is of significant military value for precisely identifying the vital infrastructure of the enemy target and optimizing the operational plan of our side. Due to the profound uncertainty in the battleground circum-stances, the acquired topological information of the opponent combat network always presents sparse characteristics. To solve this problem, a novel approach named network embed-ding based combat network link prediction (NECLP) is put for-ward to predict missing links of sparse combat networks. First, node embedding techniques are presented to preserve as much information of the combat network as possible using a low-di-mensional space. Then, we put forward a solution algorithm to predict links between combat networks based on node embed-ding similarity. Last, massive experiments are carried out on a real-world combat network case to verify the validity and prac-ticality of the proposed NECLP. This paper compares six baseline methods, and experimental results show that the NECLP has outstanding performance and substantially outper-forms the baseline methods.
文献关键词：
中图分类号：
作者姓名：
SUN Jianbin;LI Jichao;YOU Yaqian;JIANG Jiang;Ge Bingfeng
作者机构：
College of Systems Engineering,National University of Defense Technology,Changsha 410073,China
文献出处：
引用格式：
[1]SUN Jianbin;LI Jichao;YOU Yaqian;JIANG Jiang;Ge Bingfeng-.Combat network link prediction based on embedding learning)[J].系统工程与电子技术（英文版）,2022(02):345-353
A类：
battleground,opponent,NECLP,ticality
B类：
Combat,prediction,embedding,learning,Link,combat,networks,significant,military,value,precisely,identifying,vital,infrastructure,enemy,target,optimizing,operational,plan,our,side,Due,profound,uncertainty,circum,stances,acquired,topological,information,always,presents,sparse,characteristics,To,solve,this,problem,novel,approach,named,put,missing,links,First,node,techniques,presented,preserve,much,possible,using,low,mensional,space,Then,forward,solution,algorithm,between,similarity,Last,massive,experiments,carried,real,world,case,verify,validity,prac,proposed,This,paper,compares,six,baseline,methods,experimental,results,show,that,has,outstanding,performance,substantially,outper,forms
AB值：
0.550987
相似文献
机标中图分类号，由域田数据科技根据网络公开资料自动分析生成，仅供学习研究参考。
