QoS-based service selection is an important issue of service-oriented computing (SOC). A common premise of previous research is that the QoS values of services to target users are supposed all known. However, the real situation is that many of them may be missing. In this paper, we propose an enhanced CF-based QoS prediction approach to predict such missing values. Compared with existing QoS prediction methods, our proposed one has three new features: 1) adding a data normalization process to remove the impact of different QoS scale; 2) using the adjusted Euclidean Distances equation for similarity calculation to improve the prediction accuracy; and 3) using a fusion approach to predict the missing values from two sources(user and service based). An extensive performance study based on a real public dataset is reported to verify its effectiveness.
Yin, Yuyu; Yu, Dongjing; and Li, Ying
"Towards QoS Prediction for Web Services based on Adjusted Euclidean Distances,"
Applied Mathematics & Information Sciences: Vol. 07:
2, Article 5.
Available at: https://digitalcommons.aaru.edu.jo/amis/vol07/iss2/5