毒品检验区块链数据共享融合激励算法  

Data sharing fusion excitation algorithm of drug inspection blockchain

作　　者：姜斌祥 张子枫 杨学鹏 鲜晨 JIANG Bin-xiang;ZHANG Zi-feng;YANG Xue-peng;XIAN Chen(School of Information and Electrical Engineering,Shandong Jianzhu University,Jinan 250101,China;Juvenile Crime&Justice Research Center,China University of Political Science&Law,Beijing 100088,China;Institute of Computational Psychology,Shandong University,Jinan 250101,China;AI Research Institute of Hunan ENHT Technology Co.,Ltd,y Qingdao 266000,China)

机构地区：[1]山东建筑大学信息与电气工程学院,济南250101 [2]中国政法大学青少年犯罪与少年司法研究中心,北京100088 [3]山东大学计算心理学研究院,济南250101 [4]湖南亿恩科技有限公司AI研究院,山东青岛266000

出　　处：《吉林大学学报（工学版）》2022年第5期1117-1127,共11页Journal of Jilin University:Engineering and Technology Edition

基　　金：“十三五”国家重点研发计划项目(2017YFC0803604);山东省重大科技创新工程经费项目(2019JZZY010120)。

摘　　要：提出了一种基于双宽带学习特征层融合与级联决策层融合激励的毒品检验数据多模态共享激励算法,以提高毒品检验实验室对贡检验数据共享积极程度,达到促进检验数据共享为目标。通过每个实验室共享数据的数据量、基于信息熵的共享数据质量和基于参与者的声誉评价,进行多模态融合激励算法研究。仿真实验表明:采取双宽度学习特征层融合和双宽度学习嵌套级联决策层融合的多模态融合激励是有效的。In order to improve the positive degree of drug testing data sharing in drug testing laboratories and achieve the goal of promoting data sharing,a multi-mode incentive algorithm for drug testing data sharing based on the fusion of double broadband learning feature layer and cascade decision layer is proposed. Based on the data volume of shared data in each laboratory,the quality of shared data based on information entropy and the reputation evaluation of participants, the multi-mode fusion incentive algorithm is studied. The simulation results show that the multi-mode fusion excitation based on double width learning feature layer fusion and double width learning cascade decision layer fusion is effective.

关 键 词：毒品检验区块链 数据量 信息熵 声誉评价 多模态 双宽度学习特征层融合 双宽度学习嵌套级联决策层融合 

分 类 号：TP393[自动化与计算机技术—计算机应用技术]