Ograniczanie wyników
Czasopisma help
Autorzy help
Lata help
Preferencje help
Widoczny [Schowaj] Abstrakt
Liczba wyników

Znaleziono wyników: 28

Liczba wyników na stronie
first rewind previous Strona / 2 next fast forward last
Wyniki wyszukiwania
Wyszukiwano:
w słowach kluczowych:  classifier
help Sortuj według:

help Ogranicz wyniki do:
first rewind previous Strona / 2 next fast forward last
EN
In this contribution we want to present the concept of uncertainty area of classifiers and an algorithm that uses uninorms to minimize the area of uncertainty in the pre‐ diction of new objects by complex classifiers.
2
Content available Attribute selection for stroke prediction
EN
Stroke is the third most common cause of death and the most common cause of long-term disability among adults around theworld. Therefore, stroke prediction and diagnosis is a very important issue. Data mining techniques come in handy to help determine the correlations between individual patient characterisation data, that is, extract from the medical information system the knowledge necessary to predict and treat various diseases. The study analysed the data of patients with stroke using eight known classification algorithms (J48 (C4.5), CART, PART, naive Bayes classifier, Random Forest, Supporting Vector Machine and neural networks Multilayer Perceptron), which allowed to build an exploration model given with an accuracy of over 88%. The potential features of patients, which may be factors that increase the risk of stroke, were also indicated.
3
EN
Introduction: Software engineering continuously suffers from inadequate software testing. The automated prediction of possibly faulty fragments of source code allows developers to focus development efforts on fault-prone fragments first. Fault prediction has been a topic of many studies concentrating on C/C++ and Java programs, with little focus on such programming languages as Python. Objectives: In this study the authors want to verify whether the type of approach used in former fault prediction studies can be applied to Python. More precisely, the primary objective is conducting preliminary research using simple methods that would support (or contradict) the expectation that predicting faults in Python programs is also feasible. The secondary objective is establishing grounds for more thorough future research and publications, provided promising results are obtained during the preliminary research. Methods: It has been demonstrated that using machine learning techniques, it is possible to predict faults for C/C++ and Java projects with recall 0.71 and false positive rate 0.25. A similar approach was applied in order to find out if promising results can be obtained for Python projects. The working hypothesis is that choosing Python as a programming language does not significantly alter those results. A preliminary study is conducted and a basic machine learning technique is applied to a few sample Python projects. If these efforts succeed, it will indicate that the selected approach is worth pursuing as it is possible to obtain for Python results similar to the ones obtained for C/C++ and Java. However, if these efforts fail, it will indicate that the selected approach was not appropriate for the selected group of Python projects. Results: The research demonstrates experimental evidence that fault-prediction methods similar to those developed for C/C++ and Java programs can be successfully applied to Python programs, achieving recall up to 0.64 with false positive rate 0.23 (mean recall 0.53 with false positive rate 0.24). This indicates that more thorough research in this area is worth conducting. Conclusion: Having obtained promising results using this simple approach, the authors conclude that the research on predicting faults in Python programs using machine learning techniques is worth conducting, natural ways to enhance the future research being: using more sophisticated machine learning techniques, using additional Python-specific features and extended data sets.
4
EN
Many datasets, especially various historical medical data are incomplete. Various qualities of data can significantly hamper medical diagnosis and are bottlenecks of medical support systems. Nowadays, such systems are often used in medical diagnosis. Even great number of data can be unsuitable when data is imbalanced, missing or corrupted. In some cases these troubles can be overcome by machine learning algorithms designed for predictive modeling. Proposed approach was tested on real medical data and some benchmarks dataset form UCI repository. The liver fibrosis disease from a medical point of view is difficult to treatment and has a significant social and economic impact. Stages of liver fibrosis are diagnosed by clinical observation and evaluations, coupled with a so-called METAVIR rating scale. However, these methods may be insufficient, especially in the recognition of phase of the disease. This paper describes a newly developed algorithm to non-invasive fibrosis stage recognition using machine learning methods – a classification model based on feature projection k-NN classifier. This solution allows extracting data characteristics from the historical data which may be incomplete and may contain imbalance (unequal) sets of patients. Proposed novel solution is based on peripheral blood analysis without using any specialized biomarkers, and can be successfully included to medical diagnosis support systems and might be a powerful tool for effective estimation of liver fibrosis stages.
5
EN
The aim of this work is to create a web-based system that will assist its users in the cancer diagnosis process by means of automatic classification of cytological images obtained during fine needle aspiration biopsy. This paper contains a description of the study on the quality of the various algorithms used for the segmentation and classification of breast cancer malignancy. The object of the study is to classify the degree of malignancy of breast cancer cases from fine needle aspiration biopsy images into one of the two classes of malignancy, high or intermediate. For that purpose we have compared 3 segmentation methods: k-means, fuzzy c-means and watershed, and based on these segmentations we have constructed a 25–element feature vector. The feature vector was introduced as an input to 8 classifiers and their accuracy was checked. The results show that the highest classification accuracy of 89.02 % was recorded for the multilayer perceptron. Fuzzy c–means proved to be the most accurate segmentation algorithm, but at the same time it is the most computationally intensive among the three studied segmentation methods.
EN
In this paper, the detection of mines or other objects on the seabed from multiple side-scan sonar views is considered. Two frameworks are provided for this kind of classification. The first framework is based upon the Dempster–Shafer (DS) concept of fusion from a single-view kernel-based classifier and the second framework is based upon the concepts of multi-instance classifiers. Moreover, we consider the class imbalance problem which is always presents in sonar image recognition. Our experimental results show that both of the presented frameworks can be used in mine-like object classification and the presented methods for multi-instance class imbalanced problem are also effective in such classification.
PL
Przedstawiono rozwój konstrukcji klasyfikatorów pulsacyjnych typu KOMAG stosowanych do pozyskiwania żwiru i piasku, z jednoczesnym wydzielaniem zanieczyszczeń organicznych i mineralnych. Zamieszczono wyniki badań laboratoryjnych optymalizujących działanie klasyfikatorów. Opisano czynniki procesowe wpływające na zwiększenie skuteczności wzbogacania w zależności od charakterystyki nadawy (kruszywa).
EN
Progress in development of design of KOMAG pulsating jigs used for utilization of gravel and sand together with separation of organic and mineral impurities is presented in the paper. Results of laboratory tests aiming at optimization of classifiers operation are given. Technological factors, which have an impact on increase of beneficiation efficiency depending on feed (aggregates) characteristics, are discussed.
EN
The estimation of the generalization error of a trained classifier by means of a test set is one of the oldest problems in pattern recognition and machine learning. Despite this problem has been addressed for several decades, it seems that the last word has not been written yet, because new proposals continue to appear in the literature. Our objective is to survey and compare old and new techniques, in terms of quality of the estimation, easiness of use, and rigorousness of the approach, so to understand if the new proposals represent an effective improvement on old ones.
PL
Artykuł przedstawia problematykę nieparametrycznych metod klasyfikacji w odniesieniu do numerycznego modelu obiektu fizycznego. Głównym tematem jest analiza skuteczności algorytmów pod kątem zastosowań w nieniszczącej detekcji uszkodzeń. Szczególną uwagę zwrócono na parametryzację modelu, jako czynnika istotnego przy minimalizacji kosztów procesu uczenia.
EN
The article presents the discussion on nonparametric classification methods in relation to the numerical model of a physical object. The main theme is the analysis of algorithms in applications to non-destructive testing of ferromagnetic materials. The particular attention was given to model parameterization as a significant factor in minimizing the cost of the learning process.
PL
Wymagania ochrony środowiska oraz kryteria efektywności wymuszają na producentach wysoką jakość kruszyw. Klasyfikator pulsacyjny jako wielokrotnie stosowane urządzenie pozwala na spełnienie tych wymagań. W artykule przedstawiono zasadę działania klasyfikatora pulsacyjnego, przedstawiono odmiany rozwiązań konstrukcyjnych oraz przykłady wdrożeń klasyfikatorów. Opisano możliwości zastosowania klasyfikatora z łożem zawiesinowym do rozdziału drobnoziarnistych surowców mineralnych.
EN
Regulations as regards environment protection and effectiveness criteria force the manufacturers to offer high-quality aggregates. Pulsatory jig as repeatedly used device enables meeting mentioned above requirements for minerals. Principle of pulsatory jig operation is presented in the paper. Versions of design solutions and examples of implementations of pulsatory jigs are given. Application possibilities of suspension classifier for separation of fine minerals are described.
11
Content available remote Protein fold classification based on machine learning paradigm – a review
EN
Protein fold recognition using machine learning-based methods is crucial in the protein structure discovery, especially when the traditional sequence comparison methods fail because the structurally-similar proteins share little in the way of sequence homology. Many different machine learning-based fold classification methods have been proposed with still increasing accuracy and the main aim of this article is to cover all the major results in this field.
EN
Technical diagnostics is concerned with the assessment of technical conditions of the machine through the study of properties of machine processes. Diagnostics is particularly important for factories and ironworks. In paper is presented method of diagnostics of imminent failure conditions of DC machine. This method is based on a study of acoustic signals generated by DC machine. System of sound recognition uses algorithms for data processing, such as Mel Frequency Cepstral Coefficient and classifier based on words. Software to recognize the sounds of DC machine was implemented on PC computer. Studies were carried out for sounds of faultless machine and machine with shorted coils. The results confirm that the system can be useful for diagnostics of dc and ac machines used in metallurgy.
PL
Techniczna diagnostyka zajmuje się oceną stanu technicznego maszyny poprzez badania własności procesów zachodzących w maszynie. Diagnostyka jest szczególnie ważna dla fabryk i hut. W artykule jest przedstawiona metoda diagnostyki stanów przedawaryjnych maszyny prądu stałego. Metoda ta oparta jest na badaniu sygnałów akustycznych generowanych przez maszynę prądu stałego. System rozpoznawania dźwięku wykorzystuje algorytmy przetwarzania danych, takich jak algorytm MFCC i klasyfikator oparty na słowach. Zaimplementowano oprogramowanie do rozpoznawania dźwięków maszyny prądu stałego na komputerze PC. Przeprowadzono badania sygnałów akustycznych maszyny bez uszkodzeń i maszyny ze zwartymi uzwojeniami. Wyniki badań potwierdzają, że system może być przydatny w diagnostyce maszyn prądu stałego i przemiennego używanych w hutnictwie.
14
Content available remote Using machine learning approach for protein fold recognition
EN
Protein fold recognition using machine learning-based methods is crucial in the protein structure discovery, especially when the traditional sequence comparison methods fail because the structurally-similar proteins share little in the way of seąuence homology. Based on the selected machine learning classification methods, we explain the methodology for building classifiers which can be used in the protein fold recognition problem.
PL
Rozpoznawanie typu ufałdowania białka z wykorzystaniem metod uczenia maszynowego ma kluczowe znaczenie w przewidywaniu struktury białka, szczególnie w przypadkach kiedy tradycyjne podejście oparte na podobieństwie łańcuchów nie znajduje zastosowania ze względu na jego znikomą wartość. Na podstawie wybranych algorytmów uczenia maszynowego klasyfikacji w artykule przedstawiono metodykę automatycznego rozpoznawania typu ufałdowania białka.
EN
In this paper, we introduce an optimized method to improve the accuracy of content based image retrieval systems (CBIR). CBIR systems classify the images according to low and higher features.In our research, we improve both feature selection and classifier partition of a CBIR system. Results show great performance of our proposed algorithm.
EN
With the evolution of Internet, the meaning and accessibility of text documents and electronic information has increased. The automatic text categorization methods became essential in the information organization and data mining process. A proper classification of e-documents, various Internet information, blogs, emails and digital libraries requires application of data mining and machine learning algorithms to retrieve the desired data. The following paper describes the most important techniques and methodologies used for the text classification. Advantages and effectiveness of contemporary algorithms are compared and their most notable applications presented.
PL
W pracy szczegółowo omówiono sposób tworzenia macierzowego modelu ewolucji składu ziarnowego materiału w dowolnym układzie mieląco-klasyfikującym. Proponowany model oparty na równaniu bilansu masowego populacji ziaren składa się z trzech macierzy blokowych: macierzy całego układu M, macierzy wejść (nadawy bądź produktu) stopni układu F i macierzy nadawy całego układu F0. Poszczególne elementy macierzy blokowej M opisują ewolucję składu ziarnowego w całym układzie. W macierzy tej zawsze występuje macierz jednostkowa I i macierz zerowa 0, a w zależności od złożoności schematu układu pojawiają się w niej także macierz przejścia P i macierz klasyfikacji C, której elementy można wyznaczyć eksperymentalnie. Występujące w modelu elementy macierzy blokowej F opisują wszystkie gęstości składu ziarnowego wchodzące do danego stopnia układu mieląco-klasyfikującego, zaś elementy macierzy blokowej F0 ujmują gęstość składu ziarnowego nadawy ze źródeł zewnętrznych podawanej do wszystkich stopni układu. W pracy przedstawiono algorytm i trzy przykłady tworzenia macierzy blokowych dla wybranych schematów układu. Zaproponowany model może być wykorzystany w prognozowaniu uziarnienia produktu opuszczającego wybrany stopień układu oraz w modelowaniu procesów przeróbczych.
EN
Complex circuit of milling-classify systems are used in different branches of industry, because the required particle size distribution of product can seldom be reached in a single-stage grinding on the same device. The multistage processes of comminution and classification make possible suitable selection of parameters process for variables graining of fed material, mainly through sectioning of devices or change of their size and the types. Grinding material usually contains size fractions, which meet the requirements relating finished product. Then profitable is preliminary distributing material on a few size fractions, so to deal out with them demanded fraction of product, whereas remaining to direct alone or together with fed material to the same or different device. If the number of mills and classifiers in a circuit is large enough, building the model of particle size distribution transformation becomes rather complicated even for the circuit of a given structure. The situation becomes much more complicated, if we want to compare characteristics of all possible circuits, that can be constructed from these mills and classifiers, because the number of possible circuits increases greatly with the increase of number of devices being in the milling-classify system. The method creating matrix model for transformation of particle size distribution in a circuit of arbitrary structure of milling-classify system is presented in the article. The proposed model contains the mass population balance of particle equation, in which are block matrices: the matrix of circuit M, the matrix of inputs F and the matrix of feed F0. The matrix M contains blocks with the transition matrix P, the classification matrix C, the identity matrix I and the zero matrix 0 or elements describing the transformation of particle size distribution in the circuit. The matrix F is the block column matrix, which elements describing all particle size distributions at inputs to the circuit elements. The matrix F0 is the block column matrix, which elements describing particle size distributions in all feeds to the circuit. In paper was discussed this model in details, showed algorithm and three examples formatrix construction for the closed circuit ofmilling-classify systems. In conclusion was affirmed, that presented model makes possible to forecasting particle size distribution of grinding product, which leaving chosen the unit of system. The matrix model can be applied to improving modeling of mineral processing in the different grinding devices.
EN
Paper presents the concept of investigations of signals of armature current of DC motor. Algorithms of signal processing and analysis have been used. System is based on the FFT algorithm and GSDM (Genetic Sparse Distributed Memory). Software of armature current recognition of DC motor was implemented. Studies were carried out for imminent failure conditions of DC motor. The results confirm that the system is useful in diagnostics of electrical motors. System can be used in inspection of metallurgical equipments.
PL
W referacie przedstawiono koncepcję badania sygnałów prądu twornika silnika prądu stałego. Algorytmy przetwarzania i analizy sygnału zostały użyte. System rozpoznawania prądu oparty jest na algorytmie FFT i GSDM (Genetyczna rozrzedzona pamięć rozproszona). Zaimplementowano oprogramowanie do rozpoznawania prądu twornika silnika prądu stałego. Przeprowadzono badania dla stanów przedawaryjnych silnika prądu stałego. Wyniki badań potwierdzają, że system jest przydatny w diagnostyce silników elektrycznych. System może być wykorzystany do kontroli sprzętu hutniczego.
EN
Facial expression recognition is an advanced step for Human Computer Interaction (HCI) systems. Recently, fuzzy techniques are used widely to solve the natural based problems in which ambiguity is an inherent matter. In this paper, a Genetic Algorithm as a novel heuristic process is modeled to optimize the performance of fuzzy system to recognize facial expression from images. In the proposed hybrid model the core of expression recognition system is a Mamdani-type fuzzy rule based system to recognize the emotions; also, a proposed Genetic Algorithm is used with the purpose of making better performance and parameter optimization to improve the accuracy and robustness of the system. Therefore, GA as a training technique sets the fuzzy membership functions under the adverse conditions. To evaluate the system performance, images from FG-Net (FEED) and Cohn-Kanade database were used to obtain the best function parameters. Results showed the hybrid model under the training process not only to increase the accuracy rate of emotion recognition but also to increase the validity of the model in adverse conditions.
EN
This article presents new rules, which can be used to construct a classifier for image areas segmentation. Segmentation is made on upon the colours, which are commonly associated with human skin colour. The new rules of this classifier have been developed on the basis of the analysis and modifications of two other classifiers, which has been described in the literature. Nowadays, such classifiers are commonly used in practice: in photographic equipment, photo-editing software, biological images analysis or in-room person detecting systems.
first rewind previous Strona / 2 next fast forward last
JavaScript jest wyłączony w Twojej przeglądarce internetowej. Włącz go, a następnie odśwież stronę, aby móc w pełni z niej korzystać.