An effective quality analysis of XML web data using hybrid clustering and classification approach

An effective quality analysis of XML web data using clustering and classification approach is used in our proposed method. XML is turning into a standard in representation of data, it is attractive to support keyword search in XML database. A keyword search searches for words anyplace in record. It...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Soft computing (Berlin, Germany) Ročník 24; číslo 3; s. 2139 - 2150
Hlavní autoři: Gopianand, M., Jaganathan, P.
Médium: Journal Article
Jazyk:angličtina
Vydáno: Berlin/Heidelberg Springer Berlin Heidelberg 01.02.2020
Springer Nature B.V
Témata:
Algorithms
Artificial Intelligence
Classification
Classifiers
Clustering
Computational Intelligence
Confidentiality
Control
Data models
Design
Engineering
Extensible Markup Language
Feature extraction
Internet service providers
Mathematical Logic and Foundations
Mechatronics
Metadata
Methodologies and Application
Neural networks
Programming languages
Quality assessment
Robotics
Searching
Semantic web
Semantics
Structured Query Language-SQL
Wireless networks
Whale optimization
means clustering
XML web
Keyword search
Neural network
RMSE
Weighted fuzzy
ISSN:1432-7643, 1433-7479
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:An effective quality analysis of XML web data using clustering and classification approach is used in our proposed method. XML is turning into a standard in representation of data, it is attractive to support keyword search in XML database. A keyword search searches for words anyplace in record. It is developed as best worldview for finding data on web. The most imperative prerequisite for the keyword search is to rank the consequences of question so that the most pertinent outcomes show up. Here, we gather more XML documents. Followed by that, feature extraction occurs. Since the selected feature contains both relevant as well as irrelevant features it is essential to filter the irrelevant features. For the purpose of selecting, the relevant features probability-based feature selection method is used. Then for clustering the relevant features on the basis of keywords weighted fuzzy c means clustering algorithm is used. In order to assess the XML data quality, optimal neural network (ONN) classifier is utilized. In this ONN classifier in order to select the optimal weights, whale optimization algorithm is used. Thus, the web pages are effectively ranked. The efficiency of the proposed method is assessed using clustering and classification accuracy, RMSE, and search time. The proposed method is implemented in JAVA.
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:1432-7643
1433-7479
DOI:10.1007/s00500-019-04045-9