The quickhull algorithm for convex hulls
ACM Transactions on Mathematical Software (TOMS)
Selection of relevant features and examples in machine learning
Artificial Intelligence - Special issue on relevance
Wrappers for feature subset selection
Artificial Intelligence - Special issue on relevance
A Comparison of Seven Techniques for Choosing Subsets of Pattern Recognition Properties
IEEE Transactions on Computers
MaZda-A software package for image texture analysis
Computer Methods and Programs in Biomedicine
Editorial: Hybrid intelligent algorithms and applications
Information Sciences: an International Journal
Designing fusers on the basis of discriminants – evolutionary and neural methods of training
HAIS'10 Proceedings of the 5th international conference on Hybrid Artificial Intelligence Systems - Volume Part I
MPEG-7 Visual Descriptors—Contributions for Automated Feature Extraction in Capsule Endoscopy
IEEE Transactions on Circuits and Systems for Video Technology
Computers and Electronics in Agriculture
| Hi-index | 0.00 |
In this paper we study the problem of classification of wireless capsule endoscopy images (WCE). We aim at developing a computer system that would aid in medical diagnosis by automatically detecting images containing pathological alterations in an 8-hour-longWCE video. We focus on three classes of pathologies - ulcers, bleedings and petechia - since they are typical for several diseases of the intestines. The main contribution is the performance evaluation of five feature selection and classification algorithms: minimization of classification error probability, Vector Supported Convex Hull, Support Vector Machines, Radial Basis Function and Perceptron-based Neural Networks, in application to WCE images. Experimental results show that none of the methods ouperforms the others in all tested pathology classes. Instead, a classifier ensemble can be built to accumulate evidence from multiple learning schemes, each specialized in recognition of a single type of abnormality.