A Hybrid Model for QoS Prediction based on Improved Conditional Variational Autoencoder

As a nonfunctional attribute of Web services, Quality of Service (QoS) is a crucial criterion that researchers utilize to develop personalized service recommendation. The QoS history is thin and contains noisy data because of the network environment and other inevitable factors. In order to increase...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:2022 IEEE Intl Conf on Parallel & Distributed Processing with Applications, Big Data & Cloud Computing, Sustainable Computing & Communications, Social Computing & Networking (ISPA/BDCloud/SocialCom/SustainCom) s. 339 - 346
Hlavní autori: Wu, Mengwei, Lu, Qin, Wang, Yingxue, Wang, Yichao, Chen, Huanyu, Li, Weixiao
Médium: Konferenčný príspevok..
Jazyk:English
Vydavateľské údaje: IEEE 01.12.2022
Predmet:
BiasSVD
Conditional Variational Autoencoder
Correlation coefficient
Independent Sample T-test
Matrix decomposition
Noise measurement
Predictive models
QoS prediction
Quality of service
Service recommendation
Sparse matrices
Web services
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Popis
Shrnutí:As a nonfunctional attribute of Web services, Quality of Service (QoS) is a crucial criterion that researchers utilize to develop personalized service recommendation. The QoS history is thin and contains noisy data because of the network environment and other inevitable factors. In order to increase the effectiveness of Web service recommendation, it is essential to accurately predict the missing QoS values. Therefore, a model for QoS prediction based on improved Conditional Variational Autoencoder is proposed in order to improve the prediction accuracy of missing QoS. The Bias based Singular Value Decomposition (BiasSVD) is employed by the model to pre-populate the initial sparse QoS matrix with missing values. By improved Conditional Variational Autoencoder, the pre-filled matrix is learned and the QoS is reconstructed. Then, the users' plausible similar neighbors are filtered using the Pearson Correlation Coefficient and Independent Sample T-test. The missing QoS is predicted by combining the reconstruction matrix. Last but not least, the experimental results on the actual dataset WSDream demonstrate that the model improves the QoS prediction accuracy to considerable degree.
DOI:10.1109/ISPA-BDCloud-SocialCom-SustainCom57177.2022.00050