摘要
智能巡防系统的支撑要素是警情预测,论文基于神经网络对巡防警情进行预测研究。在分析警情影响因素的基础上结合时间序列确定输入变量,建立神经网络,在Matlab环境下对市公安局提供的警务真实数据进行仿真实验与分析,取得良好预测效果。结果表明该方法与传统时间序列预测方法相比,在预测的精度方面有较大程度提高。
The supporting factor of intelligent patrol system is patrol-warning prediction. In the paper,the prediction of patrol-warning is studied based on neural network. Combined with time series,neural network is established by analyzing the factors that affect patrol-warning records to define the network input variables. According to the real data provided by Taizhou bureau of public security,simulation and analysis are executed based on Matlab,which results in well-accepted prediction effect. The results show that the proposed method improves the prediction accuracy compared with the traditional time series prediction method obviously.
作者
高广银
曹红根
沈杨
GAO Guangyin;CAO Honggen;SHEN Yang(Taizhou Institute of Science&Technology,NUST.,Taizhou 225300;Xinghua E-government Center,Taizhou 225300)
出处
《计算机与数字工程》
2020年第6期1409-1412,共4页
Computer & Digital Engineering
基金
国家自然科学基金项目(编号:61373012)
泰州市科技支撑计划(社会发展)项目(编号:TSD201538)资助。
