Multi-Attributes Web Objects Classification based on Class-Attribute Relation Patterns Learning Approach

The amount of Web data increases with the proliferation of a variety of Web objects, primarily in the form of text, images, video, and music data files. Each of these published objects has some properties that support defining its class properties. Because of their diversity, using these attributes to learn and generate patterns for precise classification is very complicated. Even learning a set of attributes that clearly categorize the categories is very important. Existing attribute learning methods only learn attributes that are closely related to multiple similar objects, but if similar class objects have different attributes, this problem is difficult to learn and classify them. In this paper, a Multi-attributes Web Objects Classification (MA-WOC) based on Class-attribute Relation Patterns Learning Approach is being proposed, which generates a class-attribute with its multi relations patterns. The MA-WOC calculates the relationship probabilities of the attributes and the associated values of the class to understand the degree of association of the construction of classification pattern. To evaluate the effectiveness of the classifier, this will compare to an existing classifier that supports a multi-attribute data set, which shows improvisation of precision with a significant minimum Hamming loss. To evaluate the effectiveness of MA-WOC classification a comparison among the classifiers that are supported to the multi-attribute dataset are being performed to measure the accuracy and hamming loss.

@article{Mourya2018,
  title     = {Multi-Attributes Web Objects Classification based on Class-Attribute Relation Patterns Learning Approach},
  journal   = {International Journal of Advanced Computer Science and Applications},
  volume    = {9},
  number    = {12},
  year      = {2018},
  publisher = {The Science and Information Organization},
  author    = {Sridhar Mourya and P.V.S. Srinivas and M. Seetha},
  doi       = {10.14569/IJACSA.2018.091258},
  url       = {https://doi.org/10.14569/IJACSA.2018.091258}
}