A Crime Warning Model Based on Back-Propagation Neural Network

摘要：

　　This paper presents a mechanism of crime warning based on back-propagation neural network.The crime datasets of authoritative data resource are used to determine the crimerelated features and a crime warning index system is proposed on the basis of crime index extraction principles.Moreover,based on the study of neural network,a back-propagation neural network crime mechanism is established.This crime warning scheme takes the proper value of extracted indices as the input data and use these data to train and modify the error,thus predicting the unknown crime situation.The experimental results show that the extracted crime index system can comprehensively describe the main features of regular crime behavior and the proposed scheme can perform a precise and scientific prediction of district crime situation.

关键词： crime warning index system neural network

作者: Xue-feng Zheng Hao Cheng

作者单位: School of Computer & Communication Engineering,University of Science and Technology Beijing Beijing, China

会议类型: 国际会议

会议名称: 2012 IEEE 14th International Conference on Communication Technology(2012年第十四届通信技术国际会议(ICCT 2012))

会议地点: 成都

会议语种:英文

页码: 1096-1100

在线出版日期: 2012-11-09（万方平台首次上网日期，不代表论文的发表时间）