3 in 40 the authors used pcc to compute the

Info icon This preview shows pages 6–9. Sign up to view the full content.

hard to explain the QoS generation in the real-world service invocation. (3) In [ 40 ], the authors used PCC to compute the similarity between two users based on the QoS records. Using PCC and QoS records limits the applicability of their model due to the following two reasons. (i) The sparsity of QoS data is usually very high in real world, so the similarity result is likely to be inaccurate. In the extreme case of \cold-start", such a computation even cannot be conducted. (ii) The time complexity of similarity computation is quadratic to the data size. So such computation increases the running time of the model. In contrast, in our paper, we use the AS to identify similar users and services, without using PCC or QoS records. 616 Y. Yin et al. Int. J. Soft. Eng. Knowl. Eng. 2016.26:611-632. Downloaded from by WEIZMANN INSTITUTE OF SCIENCE on 07/01/16. For personal use only.
Image of page 6

Info icon This preview has intentionally blurred sections. Sign up to view the full version.

3. The Proposed Framework As we mentioned in the service invocation scenario in Fig. 1 (see Sec. 1 ), QoS prediction is required to be the ¯rst step. The second step is to choose the suitable services according to the predicted QoS values. The services with superior QoS values, such as short response time and high throughput, are recommended to users. Our recommen- dation system uses a AS to represent the user networkand service network, andpredicts QoS values for service recommendation. In Fig. 2 , we give the framework of network location-aware service recommendation system. This framework contains our proposed techniques, including network location-aware neighbor selection and location-aware MF model. The framework contains the following components, and is shown in Fig. 2 . . The user-service invocation matrix. It records the known QoS value after a user invokes a service. . The user network component. This component identi¯es the AS and the country where the target user is according to his or her IP address. . The service network component. This component identi¯es the AS according to the WSDL ¯les. . The service network location-aware model. In this component, we construct the neighborhood for each service based on service network, and use the MF model as the base model to build a new model. . The user network location-aware model. In this component, we construct the neighborhood for each user based on user network, and build the second model that can leverage the QoS records of the neighborhood. Fig. 2. The proposed recommendation framework. QoS Prediction for Web Service Recommendation with Network Location-Aware Neighbor Selection 617 Int. J. Soft. Eng. Knowl. Eng. 2016.26:611-632. Downloaded from by WEIZMANN INSTITUTE OF SCIENCE on 07/01/16. For personal use only.
Image of page 7
. The hybrid model component. This component combines components 4 and 5 into a hybrid model to further improve the prediction accuracy. . The recommender component. After the prediction of QoS values, this component recommends those services with superior predicted QoS to target users.
Image of page 8

Info icon This preview has intentionally blurred sections. Sign up to view the full version.

Image of page 9
This is the end of the preview. Sign up to access the rest of the document.
  • Winter '15
  • MAhmoudali
  • Analysis of algorithms, Computational complexity theory, Service system, Expectation-maximization algorithm, Weizmann Institute of Science

{[ snackBarMessage ]}

What students are saying

  • Left Quote Icon

    As a current student on this bumpy collegiate pathway, I stumbled upon Course Hero, where I can find study resources for nearly all my courses, get online help from tutors 24/7, and even share my old projects, papers, and lecture notes with other students.

    Student Picture

    Kiran Temple University Fox School of Business ‘17, Course Hero Intern

  • Left Quote Icon

    I cannot even describe how much Course Hero helped me this summer. It’s truly become something I can always rely on and help me. In the end, I was not only able to survive summer classes, but I was able to thrive thanks to Course Hero.

    Student Picture

    Dana University of Pennsylvania ‘17, Course Hero Intern

  • Left Quote Icon

    The ability to access any university’s resources through Course Hero proved invaluable in my case. I was behind on Tulane coursework and actually used UCLA’s materials to help me move forward and get everything together on time.

    Student Picture

    Jill Tulane University ‘16, Course Hero Intern