- author = "S. Preethy and A. Daniel Das",
- title = "A Genetic Programming Slant on the Way to Record De-Duplication in Repositories",
- journal = "International Journal of Innovations in Engineering and Technology (IJIET)",
- year = "2013",
- volume = "2",
- number = "2",
- pages = "60--64",
- month = apr,
- keywords = "genetic algorithms, genetic programming, de-duplication, computation",
- annote = "The Pennsylvania State University CiteSeerX Archives",
- bibsource = "OAI-PMH server at citeseerx.ist.psu.edu",
- language = "en",
- oai = "oai:CiteSeerX.psu:10.1.1.305.1403",
- rights = "Metadata may be used without restrictions as long as the oai identifier remains attached to it.",
-
URL = "
http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.305.1403",
-
URL = "
http://ijiet.com/wp-content/uploads/2013/05/10.pdf",
- ISSN = "2319-1058",
-
URL = "http://ijiet.com/issues/volume-2-issue-2-april-2013/",
- size = "5 pages",
- abstract = "Several systems that rely on consistent data to offer high-quality services, such as digital libraries and e-commerce brokers, may be affected by the existence of duplicates, quasi replicas, or near-duplicate entries in their repositories. Because of that, there have been significant investments from private and government organisations for developing methods for removing replicas from its data repositories. This is due to the fact that clean and replica-free repositories not only allow the retrieval of higher quality information but also lead to more concise data and to potential savings in computational time and resources to process this data. In this paper, we propose a genetic programming approach to record de- duplication that combines several different pieces of evidence extracted from the data content to find a de-duplication function that is able to identify whether two entries in a repository are replicas or not. As shown by our experiments, our approach outperforms an existing state-of-the-art method found in the literature. Moreover, the suggested functions are computationally less demanding since they use fewer evidence. In addition, our genetic programming approach is capable of automatically adapting these functions to a given fixed replica identification boundary, freeing the user from the burden of having to choose and tune this parameter.",
-
notes = "Department of Information Technology N.P.R.College of
Engineering and Technology, Dindigul, Tamilnadu,
India
Department of Mechanical Engineering N.P.R.College of Engineering and Technology, Dindigul, Tamilnadu, India",
