Combining Dissimilarity-Based One-Class Classifiers
نویسندگان
چکیده
We address a one-class classification (OCC) problem aiming at detection of objects that come from a pre-defined target class. Since the non-target class is ill-defined, an effective set of features discriminating between the targets and non-targets is hard to obtain. Alternatively, when raw data are available, dissimilarity representations describing an object by its dissimilarities to a set of target examples can be used. A complex problem can be approached by fusing information from a number of such dissimilarity representations. Therefore, we study both the combined dissimilarity representations (on which a single OCC is trained) as well as fixed and trained combiners applied to the outputs of the base OCCs, trained on each representation separately. An experiment focusing on the detection of diseased mucosa in oral cavity is conducted for this purpose. Our results show that both approaches allow for a significant improvement in performance over the best results achieved by the OCCs trained on single representations, however, concerning the computational cost, the use of combined representations might be more advantageous.
منابع مشابه
Ensembles of Proximity-Based One-Class Classifiers for Author Verification Notebook for PAN at CLEF 2014
We use ensembles of proximity based one-class classifiers for authorship verification task. The one-class classifiers compare, for each document of the known authorship, the dissimilarity between this document and the most dissimilar other document of this authorship to the dissimilarity between this document and the questioned document. As the dissimilarity measure between documents we use Com...
متن کاملCombining One-Class Classifiers to Classify Missing Data
In the paper a new method for handling with missing features values in classification is presented. The presented idea is to form an ensemble of one-class classifiers trained on each feature, preselected group of features or to compute from features a dissimilarity representation. Thus when any feature values are missing for a data point to be labeled, the ensemble can still make a reasonable d...
متن کاملOPTIMIZED DICTIONARY DESIGN AND CLASSIFICATION USING THE MATCHING PURSUITS DISSIMILARITY MEASURE By RAAZIA MAZHAR A DISSERTATION PRESENTED TO THE GRADUATE SCHOOL OF THE UNIVERSITY OF FLORIDA IN PARTIAL FULFILLMENT OF THE REQUIREMENTS FOR THE DEGREE OF DOCTOR OF PHILOSOPHY
of Dissertation Presented to the Graduate School of the University of Florida in Partial Fulfillment of the Requirements for the Degree of Doctor of Philosophy OPTIMIZED DICTIONARY DESIGN AND CLASSIFICATION USING THE MATCHING PURSUITS DISSIMILARITY MEASURE By Raazia Mazhar May 2009 Chair: Paul D. Gader Co-chair: Joseph N. Wilson Major: Computer Engineering Discrimination-based classifiers diffe...
متن کاملA comprehensive experimental comparison of the aggregation techniques for face recognition
In face recognition, one of the most important problems to tackle is a large amount of data and the redundancy of information contained in facial images. There are numerous approaches attempting to reduce this redundancy. One of them is information aggregation based on the results of classifiers built on selected facial areas being the most salient regions from the point of view of classificati...
متن کاملPrototype selection for dissimilarity-based classifiers
A conventional way to discriminate between objects represented by dissimilarities is the nearest neighbor method. A more efficient and sometimes a more accurate solution is offered by other dissimilarity-based classifiers. They construct a decision rule based on the entire training set, but they need just a small set of prototypes, the so-called representation set, as a reference for classifyin...
متن کامل