Journal:Informatica
Volume 15, Issue 3 (2004), pp. 315–328
Abstract
The problem of post‐processing of a classified image is addressed from the point of view of the Dempster–Shafer theory of evidence. Each neighbour of a pixel being analyzed is considered as an item of evidence supporting particular hypotheses regarding the class label of that pixel. The strength of support is defined as a function of the degree of uncertainty in class label of the neighbour, and the distance between the neighbour and the pixel being considered. A post‐processing window defines the neighbours. Basic belief masses are obtained for each of the neighbours and aggregated according to the rule of orthogonal sum. The final label of the pixel is chosen according to the maximum of the belief function.
Journal:Informatica
Volume 12, Issue 3 (2001), pp. 455–468
Abstract
This paper describes a preliminary algorithm performing epilepsy prediction by means of visual perception tests and digital electroencephalograph data analysis. Special machine learning algorithm and signal processing method are used. The algorithm is tested on real data of epileptic and healthy persons that are treated in Kaunas Medical University Clinics, Lithuania. The detailed examination of results shows that computerized visual perception testing and automated data analysis could be used for brain damages diagnosing.
Journal:Informatica
Volume 12, Issue 1 (2001), pp. 109–118
Abstract
This paper considers the technique to construct the general decision rule for the contradictory expert classification of objects which are described with many qualitative attributes. This approach is based on the theory of multiset metric spaces, and allows to classify a collection of multi-attribute objects and define the classification rule which approximates the set of individual sorting rules.
Journal:Informatica
Volume 11, Issue 2 (2000), pp. 115–124
Abstract
Influence of projection pursuit on classification errors and estimates of a posteriori probabilities from the sample is considered. Observed random variable is supposed to satisfy a multidimensional Gaussian mixture model. Presented computer simulation results show that for comparatively small sample size classification using projection pursuit algorithm gives better accuracy of estimates of a posteriori probabilities and less classification error.
Journal:Informatica
Volume 8, Issue 1 (1997), pp. 139–152
Abstract
ProObj is a Prolog based system for knowledge representation which was strongly influenced by object-oriented and frame-based systems. The paper shortly describes ProObj and then presents a classification mechanism which is based on the ideas of classifiers in KL-ONE like systems.
As a new and very flexible feature we present a user-directed control of classification process. The ProObj classifier gives the user the possibility to guide the classification process by excluding attributes and facets – elements of our representation formalism – from being considered in the classification. By this mechanism we gain a substantial improvement of the efficiency of the classification process. Furthermore, it allows a more flexible and adequate modelling of a knowledge domain. It is possible to build a knowledge base under a particular view where only those attributes of concepts are considered for classification which seem to be relevant for the structure of the domain hierarchy.