ABSTRACT The paper presents in its initial part fundamental mathematical tools for analysis of retinal images using methods of digital signal processing and enhancement and methods for their registration to monitor changes during the... more
ABSTRACT The paper presents in its initial part fundamental mathematical tools for analysis of retinal images using methods of digital signal processing and enhancement and methods for their registration to monitor changes during the treatment. Blood vessel trees are then extracted to analyse their specific structures to find retina disorders. The proposed graphical user interface is then used for analysis and monitoring of the set of 20 patients observed during the treatment using the optical coherence tomography. Features obtained are then analysed using selected statistical methods to compare features obtained and to propose the method for classification of healthy and diseased patients. The accuracy achieved was 79 %.
The most popular and publicly well-known are the studies using the Body Mass Index (BMI) as a single parameter indicating the degree of obesity (or slimness). However BMI cannot tell anything about the body composition. The Body Impedance... more
The most popular and publicly well-known are the studies using the Body Mass Index (BMI) as a single parameter indicating the degree of obesity (or slimness). However BMI cannot tell anything about the body composition. The Body Impedance Analysis (BIA) represents one of the methods for classification of body composition. As obesity does not refer to excessive body weight but it refers to the condition in which the individual has an excessive amount of body fat it is necessary to know distribution of fat tissue and fat-free mass in the body. The aim of the paper is to present results of our ongoing research focused on the influence of body hydration on the body impedance measurements and also on the influence of the frequency used for the measurement. The performed measurements showed certain influence which must be verified by repeated and extended experiments with greater number and variety of measured subjects.
Research Interests:
Formalization of the work practice using processes is a widely used method throughout various fields of industry. However, their application within the healthcare domain is rather unsuccessful due to the need for high agility, exceptions... more
Formalization of the work practice using processes is a widely used method throughout various fields of industry. However, their application within the healthcare domain is rather unsuccessful due to the need for high agility, exceptions handling, and for working with complex medical knowledge that affects these processes. To overcome these problems the agent paradigm and multi-agent systems can be applied. In this paper we present a novel architecture of a multi-agent system that is able to work with general processes. As an exemplary application of the architecture we describe a critiquing decision support system for healthcare specialists based on formalized medical guidelines.
Research Interests:
... Dynamic Time Warping The Derivative dynamic warping metrics (DDTW) is a modifi-cation of the classical dynamic time warping (DTW) algorithm The DTW algorithm technique allows comparison ... Figure 2 shows an example of time warping... more
... Dynamic Time Warping The Derivative dynamic warping metrics (DDTW) is a modifi-cation of the classical dynamic time warping (DTW) algorithm The DTW algorithm technique allows comparison ... Figure 2 shows an example of time warping measure applied to two ECG beats. ...
1 Dept. of Communications, Informatics and Management, TEI of Epirus, Kostakioi, Artas, Greece 2 Czech Technical University, Gerstner Laboratory, Prague, Czech Republic 3Department of Gynecology and Obstetrics, Porto Faculty of Medicine,... more
1 Dept. of Communications, Informatics and Management, TEI of Epirus, Kostakioi, Artas, Greece 2 Czech Technical University, Gerstner Laboratory, Prague, Czech Republic 3Department of Gynecology and Obstetrics, Porto Faculty of Medicine, Porto, Portugal
Research Interests:
A decision tree is a good classifier with a transparent decision mechanism. Decision-tree building methods usually have problems in splitting the learning samples into more subsets, because of the nature of the tree. If the classification... more
A decision tree is a good classifier with a transparent decision mechanism. Decision-tree building methods usually have problems in splitting the learning samples into more subsets, because of the nature of the tree. If the classification into such subsets is not possible, it is better to put the classification decision on to some other classifier. This leads to the introduction of a null classification, which simply means that no classification is possible in this step. This approach is sensible with evolutionary methods, as they can handle a number of trees simultaneously. In the process of construction, we have to address the problem of whether a classification is sensible. The performance of the proposed model has been tested on several data sets and the results presented on one such data set show its potential
Research Interests:
Measures from the theory of nonlinear dynamics were applied on complex fractionated atrial electrograms (CFAEs) in order to characterize their physiological dynamic behavior. The results were obtained considering 113 short term atrial... more
Measures from the theory of nonlinear dynamics were applied on complex fractionated atrial electrograms (CFAEs) in order to characterize their physiological dynamic behavior. The results were obtained considering 113 short term atrial electrograms (A-EGMs) which were annotated by three experts into four classes of fractionation according to A-EGMs signal regularity. The following measures were applied on A-EGM signals: General Correlation Dimension, Approximate Entropy, Detrended Fluctuation Analysis, Lempel-Ziv Complexity, and Katz-Sevcik, Variance and Box Counting Fractal Dimension. Assessment of disorganization was evaluated by a Kruskal Wallis statistical test. Except Detrended Fluctuation Analysis and Variance Fractal Dimension, the CFAE disorganization was found statistically significant even for low significant level alpha = 0.001. Moreover, the increasing complexity of A-EGM signals was reflected by higher values of General Correlation Dimension of order 1 and Approximate En...
Research Interests:
A robust, automated classification system for polysomnographic (PSG) data targeted to the newborn sleep stage identification is presented. The problem of polysomnographic signal classification is very often difficult because of artifacts... more
A robust, automated classification system for polysomnographic (PSG) data targeted to the newborn sleep stage identification is presented. The problem of polysomnographic signal classification is very often difficult because of artifacts and noise. Furthermore, for each signal, a special classification method for each particular type of segment must be mostly used. This paper proposes fully unsupervised approach using adaptive segmentation, appropriate features extraction and hierarchical clustering (Ward’s minimumvariance method is used). The mutual information concept was applied to results of hierarchical clustering. The proposed procedure was tested on real neonatal data. All sleep states were successfully separated by a combination of EEG, EMG, EOG, PNG and ECG channels.
Research Interests:
The ratio of three newborn’s behavioral states – wakefulness, active sleep and quiet sleep – is an important indicator of the maturity of the newborn brain in clinical practice. This paper presents study undertaken to identify possible... more
The ratio of three newborn’s behavioral states – wakefulness, active sleep and quiet sleep – is an important indicator of the maturity of the newborn brain in clinical practice. This paper presents study undertaken to identify possible improvements in processing of neonatal sleep electroencephalographic recordings. The influence of segmentation, feature extraction and feature selection on the classification accuracy was examined. The total of 97 features was extracted for each EEG channel for each segment. For selection of individual features from different channels, sequential methods were used. Naive Bayes classifier was used for final classification and performance was evaluated through cross validation. Experiments show that the combination of adaptive segmentation and selected features led to better performance. Obtained results may provide a reference for developing or enhancing neonatal sleep EEG classification algorithms. Analysis was performed on real clinical data.