![Institutional Repository [SANDBOX]](images/dias.logo.png "Institutional Repository [SANDBOX]"){kind=logo}
Institutional Repository [SANDBOX]
Technical University of Crete
Technical University of Crete
EN
|
EL
| URI: | http://purl.tuc.gr/dl/dias/F56224F2-B5D8-460C-891E-9746A5A0BC09 | ||
| Year | 2006 | ||
| Type of Item | Conference Paper Abstract | ||
| License |
|
||
| Bibliographic Citation | Y. Marinakis and G. Dounias, (2006), “Nearest Neighbor Based Pap Smear Cell Classification Using Tabu Search for Feature Selection”, presented at The Pap Smear Benchmark, Intelligent and Nature Inspired Approaches in Pap Smear Diagnosis, Special Session Proceedings of the NISIS - 2006 Symposium, Tenerife, Spain, 2006. | ||
| Appears in Collections |
The problem of classification consists of using some known objects, usually described by a large vectorof features, to induce a model that classifies others into known classes. Selecting the right set of features forclassification is one of the most important problems in designing a good classifier. In this paper, a tabu search algorithmis proposed for the solution of the feature selection problem. Tabu Search is a well known and effective metaheuristicalgorithm that was first introduced for the solution of combinatorial optimization problems. This algorithm is combinedwith a number of nearest neighbor based classifiers. The algorithm is tested in two sets of data for Pap-Smear CellClassification. The first one consists of 917 images of Pap smear cells and the second set consists of 500 images,classified carefully by cyto-technicians and doctors. Each cell is described by 20 features, and the cells fall into 7classes but a minimal requirement is to separate normal from abnormal cells, which is a 2 class problem.
Copyright © DIAS 2013
