基于人工神经网络分析成瘾性药物传播  

Analysis of Addictive Drug Transmission Based on Artificial Neural Network

作　　者：孙源 杨赞 徐柯 张仪 李丹 

机构地区：[1]同济大学浙江学院,浙江嘉兴

出　　处：《应用数学进展》2019年第3期407-412,共6页Advances in Applied Mathematics

基　　金：同济大学浙江学院第七届教改项目(项目编号:0118037).

摘　　要：滥用成瘾药物是美国政府必须面对的危机。美国疾病控制中心(CDC)等联邦组织正在努力“拯救生命,防止这种流行病对健康造成负面影响”。国家法医实验室信息系统(NFLIS)发布了一份数据报告,其中涉及“联邦,州和地方法医实验室分析的药物案例中的药物鉴定结果和相关信息”。经过一系列的数据分析和统计图表拟合,根据成瘾性药物每年与相应年份和各州的数量比例,采用BP神经网络算法,以年份后的标准化和成瘾性药物作为输入,以二进制代码后的状态数作为输出,训练,我们可以得出结论:五种状态下最早出现的成瘾药物是B状态。根据我们建立的模型分析,得出结论:有大量药物报告的县可能会推动周边县药物报告的增加,从而导致全州药物报告的增加。The use of addictive drug is a crisis that the U.S.government has to face.Federal organizations such as the Centers for Disease Control(CDC)are struggling to“save lives and prevent negative health effects of this epidemic”.NFLIS publishes a data report,which addresses“drug identification results and associated information from drug cases analyzed by federal,state,and local forensic laboratories.”After a series of data analysis and statistical chart fitting,according to addictive drug quantity proportion of each year with the corresponding year and continents,by the algorithm of BP neural network,with normalized after year and opioids for rate as input,with binary code after the state number as output,training,we can draw the conclusion:the earliest occurrence of addictive drug in five states is B state.According to the analysis of the model established by us,counties with a large number of drug reports are likely to drive the increase of drug reports in surrounding counties,thus leading to the increase of drug reports in the whole state.

关 键 词：BP神经网络 数据拟合 

分 类 号：G6[文化科学—教育学]