發(fā)布時(shí)間：2018-05-30 16:21

  本文選題：時(shí)空分析 + BP神經(jīng)網(wǎng)絡(luò)模型　； 參考：《武漢大學(xué)學(xué)報(bào)(信息科學(xué)版)》2017年08期

【摘要】：發(fā)現(xiàn)犯罪時(shí)空分布規(guī)律并預(yù)測(cè)犯罪發(fā)生,是提高警務(wù)策略有效預(yù)防、控制犯罪的重要方法。在分析財(cái)產(chǎn)犯罪時(shí)空規(guī)律的基礎(chǔ)上,利用BP神經(jīng)網(wǎng)絡(luò)模型自動(dòng)學(xué)習(xí)訓(xùn)練各因子與財(cái)產(chǎn)犯罪的非線性關(guān)系,建立了財(cái)產(chǎn)犯罪預(yù)測(cè)模型。針對(duì)BP神經(jīng)網(wǎng)絡(luò)模型易陷入局部最優(yōu)和模型不穩(wěn)定的缺陷,提出了利用遺傳算法(GA)選擇各因子最優(yōu)的初始化權(quán)重和參數(shù),并以此作為BP神經(jīng)網(wǎng)絡(luò)模型的初始化權(quán)重矩陣,通過(guò)對(duì)歷史數(shù)據(jù)的學(xué)習(xí)及訓(xùn)練建立了改進(jìn)后的GA-BP神經(jīng)網(wǎng)絡(luò)模型。利用某市2007~2012年財(cái)產(chǎn)犯罪、人口、GDP、土地利用等35個(gè)綜合影響因子數(shù)據(jù),對(duì)改進(jìn)前后的模型進(jìn)行了預(yù)測(cè)對(duì)比試驗(yàn)。結(jié)果表明,改進(jìn)后的GA-BP神經(jīng)網(wǎng)絡(luò)模型成功克服了BP模型的缺陷,收斂迭代最小次數(shù)從117次改進(jìn)到8次;10次計(jì)算收斂迭代次數(shù)最大誤差從370次提高到5次;模型預(yù)測(cè)精度(RMES)從0.043 0提高到0.019 95。
[Abstract]:It is an important method to improve the police strategy to prevent and control the crime by discovering the temporal and spatial distribution of the crime and predicting the occurrence of the crime. Based on the analysis of temporal and spatial laws of property crime, a property crime prediction model is established by using BP neural network model to automatically learn and train the nonlinear relationship between each factor and property crime. In view of the defects that BP neural network model is prone to fall into local optimum and the model is unstable, the genetic algorithm (GA) is used to select the optimal initialization weights and parameters of each factor, which is used as the initialization weight matrix of BP neural network model. An improved GA-BP neural network model is established by learning and training historical data. Based on the data of 35 comprehensive influencing factors, such as property crime, population GDPand land use in a certain city from 2007 to 2012, a comparative prediction experiment was carried out on the model before and after the improvement. The results show that the improved GA-BP neural network model successfully overcomes the defects of BP model and the minimum number of convergent iterations is improved from 117 times to 8 times from 10 times to 10 times. The prediction accuracy of the model is improved from 0.043 to 0.019 95.
【作者單位】： 華南師范大學(xué)地理科學(xué)學(xué)院;
【基金】：國(guó)家自然科學(xué)基金(41171141)~~
【分類(lèi)號(hào)】：D917

【參考文獻(xiàn)】

相關(guān)期刊論文 前3條

1 徐沖;柳林;周素紅;;DP半島街頭搶劫案件的臨近重復(fù)發(fā)生模式[J];地理研究;2015年02期

2 于紅志;劉鳳鑫;鄒開(kāi)其;;改進(jìn)的模糊BP神經(jīng)網(wǎng)絡(luò)及在犯罪預(yù)測(cè)中的應(yīng)用[J];遼寧工程技術(shù)大學(xué)學(xué)報(bào)(自然科學(xué)版);2012年02期

3 張永懷,劉君華;采用BP神經(jīng)網(wǎng)絡(luò)及其改進(jìn)算法改善傳感器特性[J];傳感技術(shù)學(xué)報(bào);2002年03期

【共引文獻(xiàn)】

相關(guān)期刊論文 前10條

1 陳韋名;曾U喺，

本文編號(hào)：1955943