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

Znaleziono wyników: 61

Liczba wyników na stronie
first rewind previous Strona / 4 next fast forward last
Wyniki wyszukiwania
Wyszukiwano:
w słowach kluczowych:  computational intelligence
help Sortuj według:

help Ogranicz wyniki do:
first rewind previous Strona / 4 next fast forward last
EN
This paper presents a new approach to the existing training of marine control engineering professionals using artificial intelligence. We use optimisation strategies, neural networks and game theory to support optimal, safe ship control by applying the latest scientific achievements to the current process of educating students as future marine officers. Recent advancements in shipbuilding, equipment for robotised ships, the high quality of shipboard game plans, the cost of overhauling, dependability, the fixing of the shipboard equipment and the requesting of the safe shipping and environmental protection, requires constant information on recent equipment and programming for computational intelligence by marine officers. We carry out an analysis to determine which methods of artificial intelligence can allow us to eliminate human subjectivity and uncertainty from real navigational situations involving manoeuvring decisions made by marine officers. Trainees learn by using computer simulation methods to calculate the optimal safe traverse of the ship in the event of a possible collision with other ships, which are mapped using neural networks that take into consideration the subjectivity of the navigator. The game-optimal safe trajectory for the ship also considers the uncertainty in the navigational situation, which is measured in terms of the risk of collision. The use of artificial intelligence methods in the final stage of training on ship automation can improve the practical education of marine officers and allow for safer and more effective ship operation.
EN
Computational Intelligence (CI) is a computer science discipline encompassing the theory, design, development and application of biologically and linguistically derived computational paradigms. Traditionally, the main elements of CI are Evolutionary Computation, Swarm Intelligence, Fuzzy Logic, and Neural Networks. CI aims at proposing new algorithms able to solve complex computational problems by taking inspiration from natural phenomena. In an intriguing turn of events, these nature-inspired methods have been widely adopted to investigate a plethora of problems related to nature itself. In this paper we present a variety of CI methods applied to three problems in life sciences, highlighting their effectiveness: we describe how protein folding can be faced by exploiting Genetic Programming, the inference of haplotypes can be tackled using Genetic Algorithms, and the estimation of biochemical kinetic parameters can be performed by means of Swarm Intelligence. We show that CI methods can generate very high quality solutions, providing a sound methodology to solve complex optimization problems in life sciences.
PL
W artykule dokonano przeglądu metod i modeli prognostycznych dedykowanych średnioterminowemu prognozowaniu obciążeń elektroenergetycznych. Opisano metody modelowania warunkowego i autonomicznego, modele klasyczne, modele inteligencji obliczeniowej i uczenia maszynowego oraz modele oparte na podobieństwie obrazów.
EN
The article reviews the methods and models of the medium-term load forecasting. Methods of conditional and autonomous modeling, classic models, computational intelligence and machine learning models are described, as well as pattern similarity-based models.
EN
Recently, the lungs have been extensively examined as a route for delivering drugs (active pharmaceutical ingredients, APIs) into the bloodstream; this is mainly due to the possibility of the noninvasive administration of macromolecules such as proteins and peptides. The absorption mechanisms of chemical compounds in the lungs are still not fully understood, which makes pulmonary formulation composition development challenging. This manuscript presents the development of an empirical model capable of predicting the excipients’ influence on the absorption of drugs in the lungs. Due to the complexity of the problem and the not-fully-understood mechanisms of absorption, computational intelligence tools were applied. As a result, a mathematical formula was established and analyzed. The normalized root-mean-squared error (NRMSE) and R2 of the model were 4.57%, and 0.83, respectively. The presented approach is beneficial both practically by developing an in silico predictive model and theoretically by gaining knowledge of the influence of APIs and excipient structure on absorption in the lungs.
EN
Diagnosis, being the first step in medical practice, is very crucial for clinical decision making. This paper investigates state-of-the-art computational intelligence (CI) techniques applied in the field of medical diagnosis and prognosis. The paper presents the performance of these techniques in diagnosing different diseases along with the detailed description of the data used. This paper includes basic as well as hybrid CI techniques that have been used in recent years so as to know the current trends in medical diagnosis domain. The paper presents the merits and demerits of different techniques in general as well as application specific context. This paper discusses some critical issues related to the medical diagnosis and prognosis such as uncertainties in the medical domain, problems in the medical data especially dealing with time-stamped (temporal) data, and knowledge acquisition. Moreover, this paper also discusses the features of good CI techniques in medical diagnosis. Overall, this review provides new insight for future research requirements in the medical diagnosis domain.
6
Content available remote Zastosowanie modelu uczenia maszynowego do realizacji procesora analogowego
PL
W pracy zaproponowano wykorzystanie, opartego na transformacjach ortogonalnych i biortogonalnych, modelu uczenia maszynowego do syntezy procesora realizującego funkcję dodawania i mnożenia liczb rzeczywistych. Ze względu na cechy bezstratności oraz realizację zasady superpozycji model ten można zakwalifikować jako system kwantowego przetwarzania sygnałów.
EN
The goal of this paper is to present a universal machine learning model using orthogonal and biorthogonal transformations based on Hurwitz-Radon matrices. This model was used to synthesize a processor that performs the function of adding and multiplying real numbers. Due to the lossless features and implementation of the superposition principle, the model can be qualified as a quantum signal processing system.
EN
Conceptual or explanatory models are a key element in the process of complex system modelling. They not only provide an intuitive way for modellers to comprehend and scope the complex phenomena under investigation through an abstract representation but also pave the way for the later development of detailed and higher-resolution simulation models. An evolutionary echo state network-based method for supporting the development of such models, which can help to expedite the generation of alternative models for explaining the underlying phenomena and potentially reduce the manual effort required, is proposed. It relies on a customised echo state neural network for learning sparse conceptual model representations from the observed data. In this paper, three evolutionary algorithms, a genetic algorithm, differential evolution and particle swarm optimisation are applied to optimize the network design in order to improve model learning. The proposed methodology is tested on four examples of problems that represent complex system models in the economic, ecological and physical domains. The empirical analysis shows that the proposed technique can learn models which are both sparse and effective for generating the output that matches the observed behaviour.
8
EN
Games are among problems that can be reduced to optimization, for which one of the most universal and productive solving method is a heuristic approach. In this article we present results of benchmark tests on using 5 heuristic methods to solve a physical model of the darts game. Discussion of the scores and conclusions from the research have shown that application of heuristic methods can simulate artificial intelligence as a regular player with very good results.
EN
The issue of line simplification is one of the fundamental problems of generalisation of geographical information, and the proper parameterisation of simplification algorithms is essential for the correctness and cartographic quality of the results. The authors of this study have attempted to apply computational intelligence methods in order to create a cartographic knowledge base that would allow for non-standard parameterisation of WEA (Weighted Effective Area) simplification algorithm. The aim of the conducted research was to obtain two independent methods of non-linear weighting of multi-dimensional regression function that determines the “importance” of specific points on the line and their comparison to each other. The first proposed approach consisted in the preparation of a set of cartographically correct examples constituting a basis for teaching a neural network, while the other one consisted in defining inference rules using fuzzy logic. The obtained results demonstrate that both methods have great potential, although the proposed solutions require detailed parameterisation taking into account the specificity of geometric variety of the source data.
PL
Prognozowanie zużycia wody jest niezbędnym elementem racjonalnej eksploatacji systemów wodociągowych. W ostatnich latach obserwuje się wzrost zainteresowania numerycznymi metodami do predykcji zużycia wody WDF (ang. Water Demand Forecasting), pozwalającymi sporządzać prognozy krótko-, średnio- i długoterminowe. Opracowane prognozy służą do wspomagania podejmowania decyzji związanych z projektowaniem, rozbudową, konserwacją sieci wodociągowych oraz wdrażania procedur umożliwiających optymalizację pracy pompowni, stacji uzdatniania wód i oczyszczalni ścieków. W artykule opisano zastosowanie metod inteligencji obliczeniowej i uczenia maszynowego do prognozowania wielkości zapotrzebowania na wodę. Przedstawiono wyniki prognozy wykonanej przy użyciu regresji nieliniowej, opartej na wektorach wsparcia SVR (ang. Support Vector Regression) z funkcjami jądrowymi określonymi przez radialne funkcje bazowe RBF (ang. Radial Basis Functions). Poddano analizie wpływ sytuacji meteorologicznej na wielkość poboru wody dla dwóch wrocławskich stref DMA (ang. District Metered Area), różniących się typem zabudowy. Wykazano, że celowe jest uwzględnienie maksymalnej dobowej temperatury powietrza atmosferycznego podczas ustalania wielkości zapotrzebowania na wodę. Dowiedziono, że usuwanie trendów i sezonowości z danych pomiarowych pozwala polepszyć wyniki predykcji. Przedstawiony model prognozowania poborów wody może stanowić jedno z narzędzi usprawniających procesy decyzyjne na poziomie zarządzania i eksploatacji sieci wodociągowych.
EN
Predicting water consumption is an important issue at the stage of water systems operation. In recent years, some numerical WDF (Water Demand Forecasting) water consumption prediction systems have been created, which allow to foresee consumption rates for short, medium and long terms. The forecasts support decision-making process concerning the design, expansion and maintenance of water systems and the implementation of procedures optimizing the operation of pumping stations, water treatment and sewage treatment plants. The article describes the use of computational intelligence and machine learning to predict water demand rates. The results of a forecast prepared with the use of nonlinear regression based on Support Vector Regression (SVR) with kernel functions defined by Radial Basis Functions (RBF) are presented. The influence of weather situation on water consumption rates for two District Metered Areas (DMA) in Wrocław, each with different land development conditions, was analysed. It was proved that it is advisable to take the maximum daily temperature into account while estimating water demand rates. It was shown that skipping trends and seasonality in measuring data allows to create better prediction models. The water consumption prediction model presented may be regarded as one of the tools facilitating decision-making processes at management and water system utilisation levels.
PL
Artykuł przedstawia propozycję implementacji wybranych metod sztucznej inteligencji do wspomagania procesu doboru optymalnej receptury stabilizacji gruntu spoiwem hydraulicznym. W pracach laboratoryjnych zastosowano metodę wielokrotnej regresji liniowej i bardziej zaawansowaną metodę wielowarstwowej sieci neuronowej. Parametry algorytmów takich jak stopień wielomianu, liczba neuronów, liczba iteracji dobrano na podstawie roboczych testów. Uczenie programów przeprowadzono na 33 recepturach.
EN
The article presents proposal of implementation of selected methods of artificial intelligence for supporting of optimal recipe selection for soil stabilization with hydraulic binder. In laboratory works multiple linear regression and more advanced multi-layer neural network were applied. Algorithm parameters such as degree of polynomial, number of neural an number of iterations were selected on the base of individual tests. Program learning was conducted on 33 recipes.
12
Content available remote Realizacja pamięci skojarzeniowej z zastosowaniem modelu uczenia maszynowego
PL
W pracy przedstawiono model systemu nauczania maszynowego wykorzystujący transformacje biortogonalne oparte na macierzach Hurwitza-Radona. Uniwersalne właściwości proponowanego modelu nauczania maszynowego zilustrowano przykładem analizy polegającym na rekonstrukcji obrazu na podstawie niepełnych danych.
EN
The paper presents a model of machine learning system using biorthogonal transformations based on Hurwitz-Radon matrices. The universal properties of the proposed machine learning model are illustrated by an example of an image reconstruction analysis based on incomplete data.
13
EN
In this paper neuro-fuzzy approach for medical data processing is considered. Special capacities for methods and systems of Computational Intelligence were introduced for Medical Data Mining tasks, like transparency and interpretability of obtained results, ability to classify nonconvex and overlapped classes that correspond to various diagnoses, necessity to process data in online mode and so on. Architecture based on the multidimensional neo-fuzzy-neuron was designed for situation of many diagnoses. For multidimensional neo-fuzzy-neuron adaptive learning algorithms that are a modification of Widrow-Hoff algorithm were introduced. This system was approbate on nervous system diseases data set from University of California Irvine (UCI) Repository and show high level of classification results.
PL
W artykule przedstawiono sposób wprowadzenia funkcji progowej do modelu Relacyjnej Rozmytej Mapy Kognitywnej, wykorzystującego arytmetykę liczb rozmytych. Funkcyjne przetwarzanie liczby rozmytej powoduje deformacje kształtu liczby i jej nośnika. Zaproponowano „geometryczne” podejście do tego problemu, pozwalające zachować niezmienność nośnika oraz utrzymać kształt przetwarzanej liczby rozmytej przy jednoczesnym odpowiednim przesunięciu centrum tej liczby. Metoda została przetestowana na liczbach rozmytych o różnych funkcjach przynależności.
EN
The article describes the method for introducing a threshold function into a model of the Relational Fuzzy Cognitive Map that uses fuzzy numbers arithmetic. Processing the fuzzy number by function causes deformations of the shape if this number and its support. It is proposed a geometrical approach to this problem, allowing to maintain constancy of the support and to keep the shape of the processed fuzzy number with an appropriate shift of the center of this number. The method was tested on fuzzy numbers with different membership functions.
PL
Internet Przedmiotów, Internet Rzeczy, Internet of Things staje się odrębną interdyscyplinarną dziedziną nauki i techniki integrującą takie obszary jak informatykę, telekomunikację, elektronikę i fotonikę, nauki informacyjne, psychologię i socjologię, nauki ekonomiczne, nauki o biznesie i gospodarowaniu. Korzysta z rozwoju tych nauk wprowadzając nową jakość. Część Internetu Przedmiotów dotycząca bezpośrednio człowieka nazywamy Internetem Dotykowym, Internetem Socjalnym, lub Internetem Usługowym. Część Internetu Przedmiotów integrowana z funkcjonalnymi warstwami cywilizacyjnymi nazywamy Internetem Infrastrukturalnym lub Internetem Inteligentnej Infrastruktury. Oba te Internety zostały nazwane przez Cisco, a termin przyjął się szerzej, Internetem Wszystkiego, Internet of Everything IoE. Autor przedstawia ogólniejsze monograficzno-eseistyczne, nieco subiektywne, wprowadzenie do Internetu Rzeczy, także bazujące częściowo na własnych doświadczeniach budowy takiego Internetu dla wielkich eksperymentów badawczych w CERN, GSI, FAIR, w ramach akceleratorowych projektów Europejskich CARE, TIARA, EuCARD, ARIES. Takie i inne doświadczenia badawcze są obecnie nadspodziewanie intensywnie transferowane do życia codziennego i przemysłu. Taki przemysł określamy nawet odrębnym terminem jako Przemysł w wersji 4.0.
EN
Internet of Things – IoT – turns to a strongly defined and separate, interdisciplinary branch of science and technology. It integrates such areas as: informatics, telecommunications, electronics and photonics, information sciences, psychology and sociology, economic sciences, and business sciences. IoT benefits from the development of these sciences introducing its strongly visible own quality. The part of of the IoT which concerns directly human beings is called Tactile Internet, Internet of Tactile Things, Internet of Social Things, Internet of Services, etc. The part of IoT which is integrated with the solid functional layers of our civilization is called Infrastructural Internet, Internet of Infrastructural Things, or just Intelligent Infrastructure. These both Internets were called by Cisco, ant this term was accepted widely, the Internet of Everything or IoE. The author presents here a more general monographic essay, slightly subjective consideration, which is an introduction to the Internet of Things. These considerations are based, at least partly, on own experiences of development and introduction of such Internets for large research experiments in CERN, GSI, FAIR, and in the framework of the European accelerator infrastructural projects like CARE, TIARA, EuCARD, ARIES. Such ones and other research experiences are now surprisingly efficiently transferred to the everyday life and the industry. Such an industry is even given a special version and called Industry 4.0.
EN
Earthquake prediction study is carried out for the region of northern Pakistan. The prediction methodology includes interdisciplinary interaction of seismology and computational intelligence. Eight seismic parameters are computed based upon the past earthquakes. Predictive ability of these eight seismic parameters is evaluated in terms of information gain, which leads to the selection of six parameters to be used in prediction. Multiple computationally intelligent models have been developed for earthquake prediction using selected seismic parameters. These models include feed-forward neural network, recurrent neural network, random forest, multi layer perceptron, radial basis neural network, and support vector machine. The performance of every prediction model is evaluated and McNemar’s statistical test is applied to observe the statistical significance of computational methodologies. Feed-forward neural network shows statistically significant predictions along with accuracy of 75% and positive predictive value of 78% in context of northern Pakistan.
EN
The article features new functions of a dispatching system designed for mining geophysics stations. A number of functions were presented: those enabling to determine and interpret so-called passive tomography maps and those of a new innovative solution which is based on computational intelligence methods for predicting the EPZ energy in each excavation.
PL
W artykule przedstawiono nowe funkcje systemu dyspozytorskiego przeznaczonego dla górniczych stacji geofizycznych. Przedstawiono funkcje związane z możliwością wyznaczania i interpretacji map tomografii pasywnej oraz nowego innowacyjnego rozwiązania polegającego na zastosowaniu metod inteligencji obliczeniowej do prognozowania tzw. energii EPZ w każdym z wyrobisk.
18
Content available Data mining methods for prediction of air pollution
EN
The paper discusses methods of data mining for prediction of air pollution. Two tasks in such a problem are important: generation and selection of the prognostic features, and the final prognostic system of the pollution for the next day. An advanced set of features, created on the basis of the atmospheric parameters, is proposed. This set is subject to analysis and selection of the most important features from the prediction point of view. Two methods of feature selection are compared. One applies a genetic algorithm (a global approach), and the other—a linear method of stepwise fit (a locally optimized approach). On the basis of such analysis, two sets of the most predictive features are selected. These sets take part in prediction of the atmospheric pollutants PM10, SO2, NO2 and O3. Two approaches to prediction are compared. In the first one, the features selected are directly applied to the random forest (RF), which forms an ensemble of decision trees. In the second case, intermediate predictors built on the basis of neural networks (the multilayer perceptron, the radial basis function and the support vector machine) are used. They create an ensemble integrated into the final prognosis. The paper shows that preselection of the most important features, cooperating with an ensemble of predictors, allows increasing the forecasting accuracy of atmospheric pollution in a significant way.
EN
One way to ensure the required technical characteristics of castings is the strict control of production parameters affecting the quality of the finished products. If the production process is improperly configured, the resulting defects in castings lead to huge losses. Therefore, from the point of view of economics, it is advisable to use the methods of computational intelligence in the field of quality assurance and adjustment of parameters of future production. At the same time, the development of knowledge in the field of metallurgy, aimed to raise the technical level and efficiency of the manufacture of foundry products, should be followed by the development of information systems to support production processes in order to improve their effectiveness and compliance with the increasingly more stringent requirements of ergonomics, occupational safety, environmental protection and quality. This article is a presentation of artificial intelligence methods used in practical applications related to quality assurance. The problem of control of the production process involves the use of tools such as the induction of decision trees, fuzzy logic, rough set theory, artificial neural networks or case-based reasoning.
20
Content available remote Przegląd metod uczenia inkrementacyjnego
EN
Classical training methods of computational intelligence models are based on building a knowledge base, assuming that the entire, complete set of learning vectors is available. This assumption is not always met, particularly in issues related to the industry. In the paper we provide an overview of a broad group of algorithms supporting incremental learning which includes: case based on reasoning, kernel methods, and incremental induction of rule-based systems.
PL
Klasyczne metody uczenia modeli inteligencji obliczeniowej opierają się na budowaniu bazy wiedzy, przy założeniu że dostępny jest cały, skończony zbiór przypadków uczących. Założenie to nie zawsze jest spełnione, dlatego też w artykule dokonano przeglądu różnych metod uczenia z możliwością douczania modelu predykcyjnego w miarę napływu nowych danych uczących. Omówiono także metody z rodziny: wnioskowania na podstawie przypadków, modeli bazujących na funkcjach jądrowych oraz systemów regułowych.
first rewind previous Strona / 4 next fast forward last
JavaScript jest wyłączony w Twojej przeglądarce internetowej. Włącz go, a następnie odśwież stronę, aby móc w pełni z niej korzystać.