@article{(Open Science Index):https://publications.waset.org/pdf/10001774,
	  title     = {An Automatic Bayesian Classification System for File Format Selection},
	  author    = {Roman Graf and  Sergiu Gordea and  Heather M. Ryan},
	  country	= {},
	  institution	= {},
	  abstract     = {This paper presents an approach for the classification of
an unstructured format description for identification of file formats.
The main contribution of this work is the employment of data mining
techniques to support file format selection with just the unstructured
text description that comprises the most important format features for
a particular organisation. Subsequently, the file format indentification
method employs file format classifier and associated configurations to
support digital preservation experts with an estimation of required file
format. Our goal is to make use of a format specification knowledge
base aggregated from a different Web sources in order to select file
format for a particular institution. Using the naive Bayes method,
the decision support system recommends to an expert, the file format
for his institution. The proposed methods facilitate the selection of
file format and the quality of a digital preservation process. The
presented approach is meant to facilitate decision making for the
preservation of digital content in libraries and archives using domain
expert knowledge and specifications of file formats. To facilitate
decision-making, the aggregated information about the file formats is
presented as a file format vocabulary that comprises most common
terms that are characteristic for all researched formats. The goal is to
suggest a particular file format based on this vocabulary for analysis
by an expert. The sample file format calculation and the calculation
results including probabilities are presented in the evaluation section.},
	    journal   = {International Journal of Computer and Information Engineering},
	  volume    = {9},
	  number    = {6},
	  year      = {2015},
	  pages     = {1477 - 1482},
	  ee        = {https://publications.waset.org/pdf/10001774},
	  url   	= {https://publications.waset.org/vol/102},
	  bibsource = {https://publications.waset.org/},
	  issn  	= {eISSN: 1307-6892},
	  publisher = {World Academy of Science, Engineering and Technology},
	  index 	= {Open Science Index 102, 2015},
	}