本文選題：網(wǎng)絡(luò)安全態(tài)勢 + 正則極限學(xué)習(xí)機(jī)��； 參考：《科技通報(bào)》2017年11期

【摘要】：為了提高網(wǎng)絡(luò)安全態(tài)勢的預(yù)測準(zhǔn)確性,提出一種改進(jìn)布谷鳥搜索算法和正則極限學(xué)習(xí)機(jī)相融合的網(wǎng)絡(luò)安全態(tài)勢預(yù)測模型。首先將一維的網(wǎng)絡(luò)安全態(tài)勢數(shù)據(jù)重構(gòu)成多維時(shí)間序列,然后將訓(xùn)練樣本集輸入到正則極限學(xué)習(xí)機(jī)進(jìn)行學(xué)習(xí),并采用改進(jìn)布谷鳥搜索算法優(yōu)化輸入權(quán)值和隱含層閾值,建立網(wǎng)絡(luò)安全態(tài)勢預(yù)測模型,最后采用Honeynet數(shù)據(jù)集對模型性能進(jìn)行測試。結(jié)果表明,相對于其它網(wǎng)絡(luò)安全態(tài)勢預(yù)測模型,本文模型可更加準(zhǔn)確描述網(wǎng)絡(luò)安全態(tài)勢的變化趨勢,不僅提高了網(wǎng)絡(luò)安全態(tài)勢預(yù)測準(zhǔn)確性,而且加快了建模速度,可以滿足網(wǎng)絡(luò)安全態(tài)勢在線預(yù)測要求。
[Abstract]:In order to improve the accuracy of network security situation prediction, an improved cuckoo search algorithm and a regular limit learning machine are proposed to predict the network security situation. Firstly, the one-dimensional network security situation data is reconstituted into multi-dimensional time series, then the training sample set is input to the regular extreme learning machine for learning, and the improved cuckoo search algorithm is used to optimize the input weights and hidden layer thresholds. Finally, Honeynet dataset is used to test the performance of the model. The results show that compared with other network security situation prediction models, this model can more accurately describe the changing trend of network security situation, not only improve the accuracy of network security situation prediction, but also accelerate the modeling speed. It can meet the requirement of online prediction of network security situation.
【作者單位】： 成都航空職業(yè)技術(shù)學(xué)院機(jī)電工程學(xué)院;四川師范大學(xué)計(jì)算機(jī)學(xué)院;
【基金】：國家自然科學(xué)基金項(xiàng)目(編號(hào)61373163) 四川省教育廳重點(diǎn)項(xiàng)目(編號(hào)17ZA0020)
【分類號(hào)】：TP393.08

【相似文獻(xiàn)】

相關(guān)期刊論文 前1條

1 葉海琴;孟彩霞;;預(yù)測模型推薦方法研究[J];福建電腦;2009年09期

相關(guān)碩士學(xué)位論文 前2條

1 劉洋;基于活動(dòng)規(guī)律的位置預(yù)測研究[D];華中科技大學(xué);2015年

2 潘暢;在線社區(qū)中的用戶行為分析及熱度預(yù)測[D];浙江大學(xué);2017年

，

本文編號(hào)：2013713