Miroslav Kubat

Machine Learning for the Detection of Oil Spills in Satellite Radar Images

During a project examining the use of machine learning techniques for oil spill detection, we encountered several essential questions that we believe deserve the attention of the research community. We use our particular case study to illustrate such issues as problem formulation, selection of evaluation measures, and data preparation. We relate these issues to properties of the oil spill application, such as its imbalanced class distribution, that are shown to be common to many applications. Our solutions to these issues are implemented in the Canadian Environmental Hazards Detection System (CEHDS), which is about to undergo field testing.

Learning When Negative Examples Abound

Existing concept learning systems can fail when the negative examples heavily outnumber the positive examples. The paper discusses one essential trouble brought about by imbalanced training sets and presents a learning algorithm addressing this issue. The experiments (with synthetic and real-world data) focus on 2-class problems with examples described with binary and continuous attributes.

Effective Learning in Dynamic Environments by Explicit Context Tracking

Daily experience shows that in the real world, the meaning of many concepts heavily depends on some implicit context, and changes in that context can cause radical changes in the concepts. This paper introduces a method for incremental concept learning in dynamic environments where the target concepts may be context-dependent and may change drastically over time. The method has been implemented in a system called FLORA3. FLORA3 is very flexible in adapting to changes in the target concepts and tracking concept drift. Moreover, by explicitly storing old hypotheses and re-using them to bias learning in new contexts, it possesses the ability to utilize experience from previous learning. This greatly increases the systems effectiveness in environments where contexts can reoccur periodically. The paper describes the various algorithms that constitute the method and reports on several experiments that demonstrate the flexibility of FLORA3 in dynamic environments.

Decision trees can initialize radial-basis function networks

Successful implementations of radial-basis function (RBF) networks for classification tasks must deal with architectural issues, the burden of irrelevant attributes, scaling, and some other problems. This paper addresses these issues by initializing RBF networks with decision trees that define relatively pure regions in the instance space; each of these regions then determines one basis function. The resulting network is compact, easy to induce, and has favorable classification accuracy.

Brain tumors detection and segmentation in MR images

Display Omitted A fully automatic system for detection of slices that contain tumor in MR images is presented.A fully automatic system for tumor segmentation using single-spectral MR images is presented.A study for evaluating the efficacy of statistical features over Gabor wavelet features is included. Automated recognition of brain tumors in magnetic resonance images (MRI) is a difficult procedure owing to the variability and complexity of the location, size, shape, and texture of these lesions. Because of intensity similarities between brain lesions and normal tissues, some approaches make use of multi-spectral anatomical MRI scans. However, the time and cost restrictions for collecting multi-spectral MRI scans and some other difficulties necessitate developing an approach that can detect tumor tissues using a single-spectral anatomical MRI images. In this paper, we present a fully automatic system, which is able to detect slices that include tumor and, to delineate the tumor area. The experimental results on single contrast mechanism demonstrate the efficacy of our proposed technique in successfully segmenting brain tumor tissues with high accuracy and low computational complexity. Moreover, we include a study evaluating the efficacy of statistical features over Gabor wavelet features using several classifiers. This contribution fills the gap in the literature, as is the first to compare these sets of features for tumor segmentation applications.

Itemset trees for targeted association querying

Association mining techniques search for groups of frequently co-occurring items in a market-basket type of data and turn these groups into business-oriented rules. Previous research has focused predominantly on how to obtain exhaustive lists of such associations. However, users often prefer a quick response to targeted queries. For instance, they may want to learn about the buying habits of customers that frequently purchase cereals and fruits. To expedite the processing of such queries, we propose an approach that converts the market-basket database into an itemset tree. Experiments indicate that the targeted queries are answered in a time that is roughly linear in the number of market baskets, N. Also, the construction of the itemset tree has O(N) space and time requirements. Some useful theoretical properties are proven.

Floating approximation in time-varying knowledge bases

Abstract In this paper a new concept of Floating Approximation is introduced. It is based on Pawlaks theory of Rough Sets and the existence of ‘hidden attributes’ in knowledge representation systems. After explaining the motivation, a simplified algorithm developed and implemented by the author is described. First experience is reported and some ideas for further research are suggested.

Initialization of neural networks by means of decision trees

The performance of neural networks is known to be sensitive to the initial weight setting and architecture (the number of hidden layers and neurons in these layers). This shortcoming can be alleviated if some approximation of the target concept in terms of a logical description is available. The paper reports a successful attempt to initialize neural networks using decision-tree generators. The TBNN (tree-based neural net) system compares very favourably with other learners in terms of classification accuracy for unseen data, and it is also computationally less demanding than the back propagation algorithm applied to a randomly initialized multilayer perceptron. The behavior of the system is first studied for specially designed artificial data. Then, its performance is demonstrated by a real-world application.

AI-based approach to automatic sleep classification

The primary goal of this paper is to introduce the potential of artificial intelligence (AI) methods to researchers in sleep classification. AI provides learning procedures for the construction of a sleep classifier, prescribing how to combine the observed parameters and how to derive the corresponding decision thresholds. A case study reporting a successful application of an automatic induction of decision trees and of a learning vector quantizer to this domain is presented.

Discovering Patterns in EEG-Signals: Comparative Study of a Few Methods

The objective of this paper is to draw the attention of the ML-researchers to the domain of data analysis. The issue is illustrated by an attractive case study—automatic classification of non-averaged EEG-signals. We applied several approaches and obtained best results from a combination of an ID3-like program with Bayesian learning.