Imputing Missing Data Analysis in Web Service Quality Dataset for Improving QoS Prediction
By: Gaurav Raj.
Contributor(s): Mahajan, Manish.
Publisher: New Delhi STM Journals 2019Edition: Vol.6(2), May-Aug.Description: 8-22p.Subject(s): Computer EngineeringOnline resources: Click here In: Recent trends in programming languagesSummary: The web services at present have countless options for similar tasks. This wide range in web services induce challenge to choose the best service among all available. QoS prediction is a key of the selection but it is very time-consuming affair. Any prediction strategy relies on accuracy and completeness of available data, especially in case of QOS Prediction. Feedback, throughput and response time are the major attribute that should not be missed and incorrect. So, it's important to identify the missing value in the web service datasets. Therefore, a study of three missing value prediction approaches was undertaken to investigate their performance for missing values in datasets for web service. Benchmarked WS Dream dataset include response time and throughput matrices of web services is selected to analyze the performance of selected approaches. An extensive experiment is performed, and results are collected, which conclude the superiority of MICE approach over other approaches.Item type | Current location | Call number | Status | Date due | Barcode | Item holds |
---|---|---|---|---|---|---|
Articles Abstract Database | School of Engineering & Technology Archieval Section | Not for loan | 2020074 |
The web services at present have countless options for similar tasks. This wide range in web services induce challenge to choose the best service among all available. QoS prediction is a key of the selection but it is very time-consuming affair. Any prediction strategy relies on accuracy and completeness of available data, especially in case of QOS Prediction. Feedback, throughput and response time are the major attribute that should not be missed and incorrect. So, it's important to identify the missing value in the web service datasets. Therefore, a study of three missing value prediction approaches was undertaken to investigate their performance for missing values in datasets for web service. Benchmarked WS Dream dataset include response time and throughput matrices of web services is selected to analyze the performance of selected approaches. An extensive experiment is performed, and results are collected, which conclude the superiority of MICE approach over other approaches.
There are no comments for this item.