《電子技術(shù)應(yīng)用》
您所在的位置:首頁 > 通信與網(wǎng)絡(luò) > 設(shè)計應(yīng)用 > 基于深度殘差神經(jīng)網(wǎng)絡(luò)的博彩網(wǎng)頁識別算法設(shè)計
基于深度殘差神經(jīng)網(wǎng)絡(luò)的博彩網(wǎng)頁識別算法設(shè)計
2022年電子技術(shù)應(yīng)用第2期
張 聰,張 恒,張立坤,趙 彤,鄧桂英
中國互聯(lián)網(wǎng)絡(luò)信息中心 技術(shù)研發(fā)部,北京100190
摘要: 互聯(lián)網(wǎng)對人民群眾的生活和工作產(chǎn)生了重要影響,然而網(wǎng)絡(luò)空間中隱藏著大量有害的博彩網(wǎng)站或賭博網(wǎng)站,很容易給網(wǎng)民造成損失和困擾,甚至可能擾亂社會秩序,因而研究對此類網(wǎng)站進行高效識別的方法具有重要意義。提出利用深度殘差神經(jīng)網(wǎng)絡(luò)解決博彩類網(wǎng)頁識別問題,基于深度殘差網(wǎng)絡(luò)的原理設(shè)計了算法GamblingRec。經(jīng)驗證,算法準確率達到了95.16%,正樣本召回率為93.21%,表明基于深度殘差神經(jīng)網(wǎng)絡(luò)的方法能夠用于博彩類網(wǎng)頁識別,并能達到較高的識別性能。
中圖分類號: TN91
文獻標識碼: A
DOI:10.16157/j.issn.0258-7998.211757
中文引用格式: 張聰,張恒,張立坤,等. 基于深度殘差神經(jīng)網(wǎng)絡(luò)的博彩網(wǎng)頁識別算法設(shè)計[J].電子技術(shù)應(yīng)用,2022,48(2):15-18.
英文引用格式: Zhang Cong,Zhang Heng,Zhang Likun,et al. Gambling web page recognition algorithm design based on deep residual neural network[J]. Application of Electronic Technique,2022,48(2):15-18.
Gambling web page recognition algorithm design based on deep residual neural network
Zhang Cong,Zhang Heng,Zhang Likun,Zhao Tong,Deng Guiying
Technological Research and Development Department,China Internet Network Information Center(CNNIC),Beijing 100190,China
Abstract: The Internet has an important impact on people′s life and work. However, there are a large number of harmful gambling websites hidden in cyberspace, which is easy to cause losses and troubles to netizens, it can even disturb society order. Therefore, it is of great significance to study the efficient recognition method of such websites. In this paper, the deep residual neural network is used to solve the problem of gambling web page recognition, and the algorithm GamblingRec is designed based on principle of deep residual network. The results show that the accuracy of GamblingRec reaches 95.16%, and the positive sample recall rate is 93.21%,which indicates that the method based on deep residual neural network can be applied for gambling web page recognition, and can achieve high recognition performance.
Key words : convolutional neural network;residual network;gambling;web page classification;ResNet

0 引言

    隨著互聯(lián)網(wǎng)技術(shù)的高速發(fā)展,我國網(wǎng)民人數(shù)持續(xù)增長,根據(jù)《第47次中國互聯(lián)網(wǎng)絡(luò)發(fā)展?fàn)顩r統(tǒng)計報告》的數(shù)據(jù),截至2020年12月,我國網(wǎng)民人數(shù)已達到9.89億[1],毫無疑問,互聯(lián)網(wǎng)已經(jīng)成為人們?nèi)粘I畈豢苫蛉钡囊徊糠?。然而,虛擬的網(wǎng)絡(luò)空間中隱藏著大量有害的博彩類型網(wǎng)站,極易給參與者造成經(jīng)濟損失,設(shè)計有效方法對博彩類網(wǎng)站進行識別具有重要意義。

1 相關(guān)工作

    博彩網(wǎng)站識別相當(dāng)于對網(wǎng)頁進行分類,預(yù)測其為博彩網(wǎng)頁或其他類型網(wǎng)頁。付順順[2]采用FastText[3]算法和Bootstrap[4]集成算法,利用網(wǎng)站文本數(shù)據(jù),提高了識別速度并減輕了正常網(wǎng)站和博彩網(wǎng)站數(shù)據(jù)不均衡問題。唐喆[5]等人采用SVM[6]算法并提取不同的文本特征,實現(xiàn)對網(wǎng)頁的分類。




本文詳細內(nèi)容請下載:http://ihrv.cn/resource/share/2000003959。




作者信息:

張  聰,張  恒,張立坤,趙  彤,鄧桂英

(中國互聯(lián)網(wǎng)絡(luò)信息中心 技術(shù)研發(fā)部,北京100190)




wd.jpg

此內(nèi)容為AET網(wǎng)站原創(chuàng),未經(jīng)授權(quán)禁止轉(zhuǎn)載。