TP-Miner:基于生物启发计算的警用流动人口分析系统  

TP-Miner:Transient Population Analysis System Based on Bio-inspired Computation

作　　者：彭京[1] 唐常杰[1] 程温泉[2] 叶尚玉[1] 方全心[2] 石葆梅[2] 

机构地区：[1]四川大学计算机学院 [2]成都市公安局科技处,四川成都610017

出　　处：《四川大学学报（工程科学版）》2006年第5期128-135,共8页Journal of Sichuan University (Engineering Science Edition)

基　　金：国家自然科学基金资助项目(6047307160473051);四川省重点科技计划资助项目(04SG1640)

摘　　要：目前对流动人口的管理仅停留在数据查询比对和简单统计上,缺少对数据的深层次分析,难以对决策指挥提供支持。针对流动人口的分析问题,提出了构建一个基于生物启发计算的智能分析系统,用于发现流动人口中各类人员的流动模式以及流动人口的趋势性问题,找出异常的流动信息和模式。该系统综合运用了前沿的生物启发计算技术———基于多层染色体基因表达式编程算法、重叠基因表达进化算法、基于概念相似度神经网络分类模型和层次距离计算的聚类算法搭建了一个警用流动人口的分析平台。同时根据实际需求,提出了一种新的基于智能分析结果的分级报警模型。实验表明系统具有较高的性能和实用性。Current management systems of transient population only support data query and simple statistics, and dont have any function of deep data analysis. So it is difficult to help people making decision. A new intelligent analysis model based on bio-inspired computing in transient population analysis was proposed. It can be used to find the trend of transient population, and find the outlier information or model of transient population. The system integrates new frontline bio-inspired computing technologies, including Multi-layer Chromosomes Gene Expression Programming, Evolutionary Algorithm Based on Overlapped Gene Expression, Similarity Artificial Neural Network Reduction Method, and Hierarchy Distance Computing Based Clustering Algorithm,and creates a transient population analysis platform based on the technologies mentioned above. A new hierarchy alarm model based on intelligent analysis result was also proposed. The extensive experiments showed that the system has high performance and practicality.

关 键 词：生物启发计算 流动人口 概念相似度 人工神经网络 数据挖掘 

分 类 号：TP311[自动化与计算机技术—计算机软件与理论]