Wyniki wyszukiwania - Biblioteka Nauki

Ten serwis zostanie wyłączony 2025-02-11.

Nowa wersja platformy, zawierająca wyłącznie zasoby pełnotekstowe, jest już dostępna.
Przejdź na https://bibliotekanauki.pl

Ograniczanie wyników

Znaleziono wyników: 4

Liczba wyników na stronie

Wyniki wyszukiwania

Sortuj według:

Ogranicz wyniki do:

Context Evaluation for Fuzzy Conditional Clustering

100%

Czabański R.

tom Vol. 50, Nr 1

71--79

In this paper an algorithm of fuzzy context evaluation for generalized conditional weighted fuzzy clustering is desribed. To find the unknown context values a preliminary clustering algorithm is employed. The application of several clustering methods in the process of context estimation is presented. An example of the Iris data classification problem is shown to illustrate the advantages of the proposed algorithm.

Extraction of fuzzy rules using deterministic annealing integrated with ε-insensitive learning

100%

Czabański R.

tom Vol. 16, no 3

357-372

A new method of parameter estimation for an artificial neural network inference system based on a logical interpretation of fuzzy if-then rules (ANBLIR) is presented. The novelty of the learning algorithm consists in the application of a deterministic annealing method integrated with ε-insensitive learning. In order to decrease the computational burden of the learning procedure, a deterministic annealing method with a “freezing” phase and ε-insensitive learning by solving a system of linear inequalities are applied. This method yields an improved neuro-fuzzy modeling quality in the sense of an increase in the generalization ability and robustness to outliers. To show the advantages of the proposed algorithm, two examples of its application concerning benchmark problems of identification and prediction are considered.

Fetal state evaluation with fuzzy analysis of newborn attributes using CUDA architecture

51%

Czabański R. , Wróbel J. , Jeżewski J.

tom Vol. 22

125--133

Cardiotocography is a biophysical method of fetal state evaluation involving the recording and analysis of the fetal heart rate (FHR). Since a proper interpretation of the signal is relatively difficult, an automatic classification is often based on computational intelligence methods. The quality of classifiers based on supervised learning algorithms depends on a proper selection of learning data. In case of the fetal state evaluation, the learning is usually based on a set of quantitative parameters of FHR signal and the corresponding reference information determined on the basis of the retrospective analysis of newborn attributes. Values of the single attribute have been used so far as a reference. As a result, a part of information on the actual neonatal outcome has always been lost. The following paper presents a method of the fuzzy reasoning leading to an evaluation of neonatal outcome as a function of three newborn attributes. The fuzzy system was used in the process of a qualitative evaluation of the fetal state based on quantitative analysis of FHR signal using a support vector machine (SVM). In order to improve computational effectiveness, the learning algorithm was implemented in Compute Unified Device Architecture (CUDA). The results of these studies confirm the effectiveness of the proposed method and indicate the possibility of practical usage of the fuzzy system in supervised learning algorithms for the qualitative evaluation of the fetal state.

Evaluation of predictive capabilities of quantitative cardiotocographic signal features

38%

Czabański R. , Jeżewski M. , Roj D. , Szaszkowski Z. , Kupka T. , Wróbel J.

tom Vol. 16

11--17

Cardiotocography (CTG) is the main method of assessment of the fetal state during pregnancy and labour used in clinical practice. It is based on quantitative analysis of fetal heart rate, fetal movements and uterine contractions signals. The evaluation of the CTG signals can be made using criteria recommended by International Federation of Obstetrics and Gynecology. Nevertheless, the diagnosis verification is possible only after the delivery on the basis of newborn assessment. In the proposed work we evaluated the capacity of quantitative analysis of CTG traces in predicting fetal outcome. The relationship between CTG signal features and attributes of fetal outcome was assessed on the basis of ROC curves analysis. The obtained results indicate the adequate predictive capabilities of the selected CTG features especially for fetal outcome assessed with Apgar score and suggest the necessity of applying the criteria for the CTG traces evaluation that are related to the gestational age. Our study also shows the value of the CTG monitoring as a screening procedure providing appropriate confirmation of fetal wellbeing.