發(fā)布時(shí)間：2018-08-20 14:14

【摘要】：隨著服務(wù)計(jì)算相關(guān)技術(shù)的不斷普及,Web服務(wù)作為依托于互聯(lián)網(wǎng)之上的重要軟件資源而被廣泛應(yīng)用。在實(shí)際應(yīng)用場(chǎng)景中,Web服務(wù)的可信性成為人們?cè)趯?duì)Web服務(wù)進(jìn)行選擇、推薦時(shí)所需要考慮的重要目標(biāo)。為此,對(duì)Web服務(wù)的可信性進(jìn)行有效的評(píng)估與預(yù)測(cè)便成為服務(wù)應(yīng)用過(guò)程中的重要問(wèn)題。通常,服務(wù)質(zhì)量(quality of service,QoS)是Web服務(wù)可信性的一個(gè)直觀且重要的體現(xiàn),因此通過(guò)對(duì)QoS的綜合分析并在此基礎(chǔ)上實(shí)現(xiàn)對(duì)服務(wù)可信性的預(yù)測(cè)就顯得尤為必要。本文試圖從機(jī)器學(xué)習(xí)的角度來(lái)解決Web服務(wù)可信性的預(yù)測(cè)問(wèn)題,所提出的基于選擇性神經(jīng)網(wǎng)絡(luò)集成的Web服務(wù)可信性預(yù)測(cè)是集合了BP神經(jīng)網(wǎng)絡(luò)、選擇性集成學(xué)習(xí)、粒子群優(yōu)化算法等技術(shù)為一體的解決方案。在該方案中,將已知可信性等級(jí)的Web服務(wù)的QoS數(shù)據(jù)信息對(duì)BP網(wǎng)絡(luò)進(jìn)行訓(xùn)練學(xué)習(xí),生成多個(gè)候選神經(jīng)網(wǎng)絡(luò),隨后采用粒子群優(yōu)化策略對(duì)候選神經(jīng)網(wǎng)絡(luò)的集成權(quán)重進(jìn)行優(yōu)化搜索,按照搜索得到的最優(yōu)集成權(quán)重方案實(shí)現(xiàn)神經(jīng)網(wǎng)絡(luò)的選擇性集成。在技術(shù)實(shí)現(xiàn)過(guò)程中,基于集成權(quán)重編碼的不同,本文提出了兩種集成模式算法,即PSO-SEN算法和QPSO-SEN算法。通過(guò)針對(duì)公開(kāi)數(shù)據(jù)的實(shí)驗(yàn)對(duì)比分析,驗(yàn)證基于選擇性神經(jīng)網(wǎng)絡(luò)集成的Web服務(wù)可信性預(yù)測(cè)方法的可行性和有效性以及參數(shù)對(duì)算法的影響。實(shí)驗(yàn)結(jié)果表明,與其他的典型方法相比,該技術(shù)在預(yù)測(cè)準(zhǔn)確度上具有明顯的優(yōu)勢(shì),且該技術(shù)對(duì)分類器集成方式、種群大小、分類器隱含層節(jié)點(diǎn)數(shù)敏感度較低,具有良好的魯棒性。Web服務(wù)的可信性預(yù)測(cè)有助于用戶在對(duì)眾多功能等價(jià)的Web服務(wù)開(kāi)展服務(wù)選擇時(shí)提供可信性特征的指導(dǎo),以便做出科學(xué)合理的服務(wù)選擇決策。此外,在融合神經(jīng)網(wǎng)絡(luò)、集成學(xué)習(xí)和智能搜索等技術(shù)構(gòu)建混合式預(yù)測(cè)算法的研究也會(huì)對(duì)類似管理決策問(wèn)題提供一定的參考。
[Abstract]:With the popularity of service computing technology, Web services have been widely used as an important software resource based on the Internet. In practical application scenarios, the credibility of Web services has become an important goal that people need to consider when choosing and recommending Web services. Quality of service (QoS) is usually an intuitive and important embodiment of Web service trustworthiness. Therefore, it is necessary to predict the service trustworthiness based on the comprehensive analysis of QoS. In order to solve the problem of predicting Web service trustworthiness, the proposed Web service trustworthiness prediction based on selective neural network ensemble is a solution which integrates BP neural network, selective ensemble learning, particle swarm optimization and other technologies. In this scheme, the QoS data information of Web service with known trustworthiness level is used to BP. The network is trained and trained to generate several candidate neural networks, and then the ensemble weights of the candidate neural networks are optimized by particle swarm optimization strategy. The ensemble weights of the neural networks are optimized according to the optimal ensemble weights. Two integration pattern algorithms, PSO-SEN algorithm and QPSO-SEN algorithm, are proposed to verify the feasibility and effectiveness of the selective neural network ensemble-based Web service credibility prediction method and the influence of parameters on the algorithm by comparing the experimental results with other typical methods. The technology has obvious advantages in prediction accuracy, and it has low sensitivity to classifier integration mode, population size, and the number of hidden nodes in the classifier. It has good robustness. In addition, the research on hybrid prediction algorithm based on neural network, ensemble learning and intelligent search will provide some reference for similar management decision-making problems.
【學(xué)位授予單位】：江西財(cái)經(jīng)大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2017
【分類號(hào)】：TP18;TP393.09

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 沈國(guó)華;黃志球;謝冰;朱羿全;廖莉莉;王飛;劉銀陵;;軟件可信評(píng)估研究綜述:標(biāo)準(zhǔn)、模型與工具[J];軟件學(xué)報(bào);2016年04期

2 李玲;劉敏;成國(guó)慶;;一種基于FAHP的多維QoS局部最優(yōu)服務(wù)選擇模型[J];計(jì)算機(jī)學(xué)報(bào);2015年10期

3 何小霞;譚良;;基于Hadoop的可信Web服務(wù)多維QoS權(quán)重最優(yōu)選擇模型[J];計(jì)算機(jī)科學(xué);2015年04期

4 蔡瓊;丁帥;;軟件服務(wù)化背景下的云服務(wù)可信評(píng)估研究[J];計(jì)算機(jī)應(yīng)用研究;2015年04期

5 孫昌愛(ài);趙敏;何嘯;;一種面向Web服務(wù)的綜合可信性度量模型[J];北京科技大學(xué)學(xué)報(bào);2014年04期

6 王尚廣;孫其博;張光衛(wèi);楊放春;;基于云模型的不確定性QoS感知的Skyline服務(wù)選擇[J];軟件學(xué)報(bào);2012年06期

7 趙強(qiáng)利;蔣艷凰;徐明;;選擇性集成算法分類與比較[J];計(jì)算機(jī)工程與科學(xué);2012年02期

8 胡建強(qiáng);李涓子;廖桂平;;一種基于多維服務(wù)質(zhì)量的局部最優(yōu)服務(wù)選擇模型[J];計(jì)算機(jī)學(xué)報(bào);2010年03期

9 楊曉霜;汪源源;;基于Moore-Penrose逆矩陣的選擇性集成[J];光電工程;2009年11期

10 胡志剛;付毅;肖鵬;胡周君;;基于貝葉斯網(wǎng)絡(luò)的網(wǎng)格QoS可信度評(píng)估方法[J];計(jì)算機(jī)工程;2009年07期

，

本文編號(hào)：2193906