Rough Sets: Theoretical Aspects of Reasoning about Data
Rough Sets: Theoretical Aspects of Reasoning about Data
On Classifying Mappings Induced by Granular Structures
Transactions on Rough Sets IX
On classification of data by means of rough mereological granules of objects and rules
RSKT'08 Proceedings of the 3rd international conference on Rough sets and knowledge technology
RSCTC'2010 discovery challenge: mining DNA microarray data for medical diagnosis and treatment
RSCTC'10 Proceedings of the 7th international conference on Rough sets and current trends in computing
The extraction method of DNA microarray features based on experimental A statistics
RSKT'11 Proceedings of the 6th international conference on Rough sets and knowledge technology
| Hi-index | 0.00 |
The paradigm of Granular Computing has emerged quite recently as an area of research on its own; in particular, it is pursued within the rough set theory initiated by Zdzisław Pawlak. Granules of knowledge can be used for the approximation of knowledge. Another natural application of granular structures is using them in the classification process. In this work we apply the granular classifier based on rough mereology, recently studied by Polkowski and Artiemjew 8_v1_w4 algorithm in exploration of DNA Microarrays. An indispensable element of the analysis of DNA microarray are the gene extraction methods, because of their high number of attributes and a relatively small number of objects, which in turn results in overfitting during the classification. In this paper we present one of our approaches to gene separation based on modified F statistics. The modification of F statistics, widely used in binary decision systems, consists in an extension to multiple decision classes and the application of a particular method to choose the best genes after their calculation for particular pairs of decision classes. The results of our research, obtained for modified F statistics, are comparable to, or even better than, the results obtained in other methods with data from the Advanced Track of the recent DNA Microarray data mining competition.