Informacja

Drogi użytkowniku, aplikacja do prawidłowego działania wymaga obsługi JavaScript. Proszę włącz obsługę JavaScript w Twojej przeglądarce.

English (EN)·Polski (PL)·Yкраїнський (UK)
Przejdź do strony domowej biblioteki Centralna Biblioteka Wojskowa Link otwiera się w nowym oknie Logo biblioteki Prolib Integro - strona głównaCentralna Biblioteka Wojskowa

Wyszukujesz frazę "Neural Networks" wg kryterium: Temat

  Lista filtrów

Dostawca treści

Wyrównaj
Wyświetlanie 1-25 z 831
Tytuł:
Object classification with artificial neural networks : A comparative analysis
Autorzy:
Domeradzki, Kornel
Niewiadomski, Artur
Powiązania:
https://bibliotekanauki.pl/articles/1819259.pdf
Data publikacji:
2019
Wydawca:
Uniwersytet Przyrodniczo-Humanistyczny w Siedlcach
Tematy:
object classification
neural networks
convolutional neural networks
residual neural networks
Opis:
Object classification is a problem which has attracted a lot of research attention in recent years. Traditional approach to this problem is built on a shallow trainable architecture that was meant to detect handcrafted features. That approach works poorly and introduces many complications in situations where one is to work with more than a couple types of objects in an image with a large resolution. That is why in the past few years convolutional and residual neural networks have experienced a tremendous rise in popularity. In this paper, we provide a review on topics related to artificial neural networks and a brief overview of our research. Our review begins with a short introduction to the topic of computer vision. Afterwards we cover briefly the concepts of neural networks, convolutional and residual neural networks and their commonly used models. Then we provide a comparative performance analysis of the previously mentioned models in a binary and multi-label classification problem. Finally, multiple conclusions are drawn, which are to serve as guidelines for future computer vision systems implementations.
Źródło:
Studia Informatica : systems and information technology; 2019, 1-2(23); 43--56
1731-2264
Pojawia się w:
Studia Informatica : systems and information technology
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
Information Technology of Stock Indexes Forecasting on the Base of Fuzzy Neural Networks
Autorzy:
Tryus, Y.
Antipova, N.
Zhuravel, K.
Zaspa, G.
Powiązania:
https://bibliotekanauki.pl/articles/118277.pdf
Data publikacji:
2017
Wydawca:
Polskie Towarzystwo Promocji Wiedzy
Tematy:
neural networks
fuzzy neural networks
forecasting
stock indexes
Opis:
In this research the information technology for stock indexes forecast on the base of fuzzy neural networks was created. The possibility of its use for multi-parameter short-time stock indexes forecasts, in particular S&P500, DJ, NASDAC was checked. The created information technology is used making several consequential steps. The stock indexes forecast numeral experiment based on real data for period of several years with use of the technology offered was made.
Źródło:
Applied Computer Science; 2017, 13, 1; 29-40
1895-3735
Pojawia się w:
Applied Computer Science
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
The recognition of partially occluded objects with support vector machines, convolutional neural networks and deep belief networks
Autorzy:
Chu, J. L.
Krzyżak, A.
Powiązania:
https://bibliotekanauki.pl/articles/91650.pdf
Data publikacji:
2014
Wydawca:
Społeczna Akademia Nauk w Łodzi. Polskie Towarzystwo Sieci Neuronowych
Tematy:
neural networks
belief networks
convolutional neural networks
artificial neural networks
Deep Belief Network
generative model
Opis:
Biologically inspired artificial neural networks have been widely used for machine learning tasks such as object recognition. Deep architectures, such as the Convolutional Neural Network, and the Deep Belief Network have recently been implemented successfully for object recognition tasks. We conduct experiments to test the hypothesis that certain primarily generative models such as the Deep Belief Network should perform better on the occluded object recognition task than purely discriminative models such as Convolutional Neural Networks and Support Vector Machines. When the generative models are run in a partially discriminative manner, the data does not support the hypothesis. It is also found that the implementation of Gaussian visible units in a Deep Belief Network trained on occluded image data allows it to also learn to effectively classify non-occluded images.
Źródło:
Journal of Artificial Intelligence and Soft Computing Research; 2014, 4, 1; 5-19
2083-2567
2449-6499
Pojawia się w:
Journal of Artificial Intelligence and Soft Computing Research
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
Membership function - ARTMAP neural networks
Autorzy:
Sinčák, P.
Hric, M.
Vaščák, J.
Powiązania:
https://bibliotekanauki.pl/articles/1931570.pdf
Data publikacji:
2003
Wydawca:
Politechnika Gdańska
Tematy:
pattern recognition principles
classifier design
classification accuracy assessment
contingency tables
backpropagation neural networks
fuzzy BP neural networks
ART and ARTMAP neural networks
modular neural networks
neural networks
Opis:
The project deals with the application of computational intelligence (CI) tools for multispectral image classification. Pattern Recognition scheme is a global approach where the classification part is playing an important role to achieve the highest classification accuracy. Multispectral images are data mainly used in remote sensing and this kind of classification is very difficult to assess the accuracy of classification results. There is a feedback problem in adjusting the parts of pattern recognition scheme. Precise classification accuracy assessment is almost impossible to obtain, being an extremely laborious procedure. The paper presents simple neural networks for multispectral image classification, ARTMAP-like neural networks as more sophisticated tools for classification, and a modular approach to achieve the highest classification accuracy of multispectral images. There is a strong link to advances in computer technology, which gives much better conditions for modelling more sophisticated classifiers for multispectral images.
Źródło:
TASK Quarterly. Scientific Bulletin of Academic Computer Centre in Gdansk; 2003, 7, 1; 43-52
1428-6394
Pojawia się w:
TASK Quarterly. Scientific Bulletin of Academic Computer Centre in Gdansk
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
Distribution of the tree parity machine synchronization time
Autorzy:
Dolecki, M.
Kozera, R.
Powiązania:
https://bibliotekanauki.pl/articles/102097.pdf
Data publikacji:
2013
Wydawca:
Stowarzyszenie Inżynierów i Techników Mechaników Polskich
Tematy:
neural networks
neurocryptography
Opis:
Neural networks’ synchronization by mutual learning discovered and described by Kanter et al. [12] can be used to construct relatively secure cryptographic key exchange protocol in the open channel. This phenomenon based on simple mathematical operations, can be performed fast on a computer. The latter makes it competitive to the currently used cryptographic algorithms. An additional advantage is the easiness in system scaling by adjusting neutral network’s topology, what results in satisfactory level of security [24] despite different attack attempts [12, 15]. With the aid of previous experiments, it turns out that the above synchronization procedure is a stochastic process. Though the time needed to achieve compatible weights vectors in both partner networks depends on their topology, the histograms generated herein render similar distribution patterns. In this paper the simulations and the analysis of synchronizations’ time are performed to test whether these histograms comply with histograms of a particular well-known statistical distribution. As verified in this work, indeed they coincide with Poisson distribution. The corresponding parameters of the empirically established Poisson distribution are also estimated in this work. Evidently the calculation of such parameters permits to assess the probability of achieving both networks’ synchronization in a given time only upon resorting to the generated distribution tables. Thus, there is no necessity of redoing again time-consuming computer simulations.
Źródło:
Advances in Science and Technology. Research Journal; 2013, 7, 18; 20-27
2299-8624
Pojawia się w:
Advances in Science and Technology. Research Journal
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
Distance of the initial weights of tree parity machine drawn from different distributions
Autorzy:
Dolecki, M.
Kozera, R.
Powiązania:
https://bibliotekanauki.pl/articles/102120.pdf
Data publikacji:
2015
Wydawca:
Stowarzyszenie Inżynierów i Techników Mechaników Polskich
Tematy:
neural networks
neurocryptography
Opis:
It is well-known that artificial neural networks have the ability to learn based on the provisions of new data. A special case of the so-called supervised learning is a mutual learning of two neural networks. This type of learning applied to a specific networks called Tree Parity Machines (abbreviated as TPM networks) leads to achieving consistent weight vectors in both of them. Such phenomenon is called a network synchronization and can be exploited while constructing cryptographic key exchange protocol. At the beginning of the learning process both networks have initialized weights values as random. The time needed to synchronize both networks depends on their initial weights values and the input vectors which are also randomly generated at each step of learning. In this paper the relationship between the distribution, from which the initial weights of the network are drawn, and their compatibility is discussed. In order to measure the initial compatibility of the weights, the modified Euclidean metric is invoked here. Such a tool permits to determine the compatibility of the network weights’ scaling in regard to the size of the network. The proper understanding of the latter permits in turn to compare TPM networks of various sizes. This paper contains the results of the simulation and their discussion in the context of the above mentioned issue.
Źródło:
Advances in Science and Technology. Research Journal; 2015, 9, 26; 137--142
2299-8624
Pojawia się w:
Advances in Science and Technology. Research Journal
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
Searching for optimal size neural networks in Assembler Encoding
Autorzy:
Praczyk, T.
Powiązania:
https://bibliotekanauki.pl/articles/970178.pdf
Data publikacji:
2010
Wydawca:
Polska Akademia Nauk. Instytut Badań Systemowych PAN
Tematy:
evolutionary neural networks
Opis:
Assembler Encoding represents a neural network in the form of a simple program called Assembler Encoding Program. The task of the program is to create the so-called Network Definition Matrix, which maintains all the information necessary to construct a network. To generate the programs and, in consequence, neural networks, evolutionary techniques are used. One of the problems in Assembler Encoding is to determine an optimal number of neurons in a neural network. To deal with this problem a current version of Assembler Encoding uses a solution that is time consuming and hence rather impractical. The paper proposes four other solutions to the problem mentioned. To test them, experiments in a predator-prey problem were carried out. The results of the experiments are included at the end of the paper.
Źródło:
Control and Cybernetics; 2010, 39, 4; 1193-1215
0324-8569
Pojawia się w:
Control and Cybernetics
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
Nonlinear position estimators based on artificial neural networks for low costs manufacturing systems
Autorzy:
Dogruer, C.
Kilic, E.
Dolen, M.
Koku, B.
Powiązania:
https://bibliotekanauki.pl/articles/384449.pdf
Data publikacji:
2007
Wydawca:
Sieć Badawcza Łukasiewicz - Przemysłowy Instytut Automatyki i Pomiarów
Tematy:
neural networks
esimators
Opis:
The accurate contral of CNC machine axis requires relatively expensive direct measurement sensors. In this paper, artificial neural network based position error estimators are comparatively evaluated as a part of a low-cost (but high performance) manufacturing system. Such schemes are very effective when the system is rot subjected to external loads as well as widely changing operating conditions such as ambient temperature.
Źródło:
Journal of Automation Mobile Robotics and Intelligent Systems; 2007, 1, 2; 40-44
1897-8649
2080-2145
Pojawia się w:
Journal of Automation Mobile Robotics and Intelligent Systems
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
Automatic Fault Classification for Journal Bearings Using ANN and DNN
Autorzy:
Narendiranath Babu, T.
Aravind, A.
Rakesh, A.
Jahzan, M.
Rama Prabha, D.
Ramalinga Viswanathan, M.
Powiązania:
https://bibliotekanauki.pl/articles/177579.pdf
Data publikacji:
2018
Wydawca:
Polska Akademia Nauk. Czytelnia Czasopism PAN
Tematy:
journal bearing
fault classification
artificial neural networks
deep neural networks
Opis:
Journal bearings are the most common type of bearings in which a shaft freely rotates in a metallic sleeve. They find a lot of applications in industry, especially where extremely high loads are involved. Proper analysis of the various bearing faults and predicting the modes of failure beforehand are Essentials to increase the working life of the bearing. In the current study, the vibration data of a journal Bering in the healthy condition and in five different fault conditions are collected. A feature extraction metod is employed to classify the different fault conditions. Automatic fault classification is performed using artificial neural networks (ANN). As the probability of a correct prediction goes down for a higher number of faults in ANN, the method is made more robust by incorporating deep neural networks (DNN) with the help of autoencoders. Training was done using the scaled conjugate gradient algorithm and the performance was calculated by the cross entropy method. Due to the increased number of hidden layers in DNN, it is possible to achieve a high efficiency of 100% with the feature extraction method.
Źródło:
Archives of Acoustics; 2018, 43, 4; 727-738
0137-5075
Pojawia się w:
Archives of Acoustics
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
Application of EMD ANN and DNN for Self-Aligning Bearing Fault Diagnosis
Autorzy:
Narendiranath, B. T.
Aravind, A.
Rakesh, A.
Jahzan, M.
Rama, P. D.
Powiązania:
https://bibliotekanauki.pl/articles/176889.pdf
Data publikacji:
2018
Wydawca:
Polska Akademia Nauk. Czytelnia Czasopism PAN
Tematy:
self-aligning bearing
fault classification
artificial neural networks
deep neural networks
Opis:
Self-aligning roller bearings are an integral part of the industrial machinery. The proper analysis and prediction of the various faults that may happen to the bearing beforehand contributes to an increase in the working life of the bearing. This study aims at developing a novel method for the analysis of the various faults in self-aligning bearings as well as the automatic classification of faults using artificial neural network (ANN) and deep neural network (DNN). The vibration data is collected for six different faults as well as for the healthy bearing. Empirical mode decomposition (EMD) followed by Hilbert Huang transform is used to extract instantaneous frequency peaks which are used for fault analysis. Time domain and time-frequency domain features are then extracted which are used to implement the neural networks through the pattern recognition tool in MATLAB. A comparative study of the outputs from the two neural networks is also performed. From the confusion matrix, the efficiency of the ANN has been found to be 95.7% and using DNN has been found to be 100%.
Źródło:
Archives of Acoustics; 2018, 43, 2; 163-175
0137-5075
Pojawia się w:
Archives of Acoustics
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
Application of neurocomputing in the parametric identification using dynamic responses of structural elements - selected problems
Identyfikacja parametrów konstrukcji na podstawie dynamicznych odpowiedzi z wykorzystaniem sieci neuronowych - wybrane zagadnienia
Autorzy:
Ziemiański, L.
Miller, B.
Piątkowski, G.
Powiązania:
https://bibliotekanauki.pl/articles/281927.pdf
Data publikacji:
2004
Wydawca:
Polskie Towarzystwo Mechaniki Teoretycznej i Stosowanej
Tematy:
neural networks dynamics
identification
Opis:
Some problems of neurocomputing in the dynamics of structures are presented: 1) damage detection using wave propagation, 2) updating of portal frames finite element models, 3) detection of the void and additional mass in cantilever plates, 4) neural network modelling of an "artificial boundary condition". The analysed problems are related to both data prepared by computational systems and that taken from experimental evidence.
W artykule przedstawiono zastosowanie sieci neuronowych w wybranych zagadnieniach dynamiki konstrukcji: 1) wykrywanie uszkodzeń w elementach prętowych na podstawie propagacji fali, 2) dostrajanie modeli MES ram portalowych, 3) wykrywanie pustki i dodatkowej masy w drgającej płycie wspornikowej, 4) modelowanie "sztucznej granicy" w zagadnieniu propagacji fali. Rozpatrywane problemy dotyczą zarówno modeli numerycznych, jak i eksperymentalnych.
Źródło:
Journal of Theoretical and Applied Mechanics; 2004, 42, 3; 667-693
1429-2955
Pojawia się w:
Journal of Theoretical and Applied Mechanics
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
Enhancing constructive neural network performance using functionally expanded input data
Autorzy:
Bertini, Jr., J. R.
Carmo Nicoletti, do, M.
Powiązania:
https://bibliotekanauki.pl/articles/91786.pdf
Data publikacji:
2016
Wydawca:
Społeczna Akademia Nauk w Łodzi. Polskie Towarzystwo Sieci Neuronowych
Tematy:
constructive neural networks
functional link artificial neural networks
functionally expanded input data
Opis:
Constructive learning algorithms are an efficient way to train feedforward neural networks. Some of their features, such as the automatic definition of the neural network (NN) architecture and its fast training, promote their high adaptive capacity, as well as allow for skipping the usual pre-training phase, known as model selection. However, such advantages usually come with the price of lower accuracy rates, when compared to those obtained with conventional NN learning approaches. This is, perhaps, the reason for conventional NN training algorithms being preferred over constructive NN (CoNN) algorithms. Aiming at enhancing CoNN accuracy performance and, as a result, making them a competitive choice for machine learning based applications, this paper proposes the use of functionally expanded input data. The investigation described in this paper considered six two-class CoNN algorithms, ten data domains and seven polynomial expansions. Results from experiments, followed by a comparative analysis, show that performance rates can be improved when CoNN algorithms learn from functionally expanded input data.
Źródło:
Journal of Artificial Intelligence and Soft Computing Research; 2016, 6, 2; 119-131
2083-2567
2449-6499
Pojawia się w:
Journal of Artificial Intelligence and Soft Computing Research
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
Inversion of fuzzy neural networks for the reduction of noise in the control loop for automotive applications
Autorzy:
Nentwig, M.
Mercorelli, P.
Powiązania:
https://bibliotekanauki.pl/articles/384669.pdf
Data publikacji:
2009
Wydawca:
Sieć Badawcza Łukasiewicz - Przemysłowy Instytut Automatyki i Pomiarów
Tematy:
neural networks
fuzzy control
inversion of neural networks
automotive control
noise reduction
Opis:
A robust throttle valve control has been an attractive problem since throttle by wire systems were established in the mid-nineties. Control strategies often use a feed-forward controller which use an inverse model; however, mathematical model inversions imply a high order of differentiation of the state variables resulting in noise effects. In general, neural networks are a very effective and popular tool for modelling. The inversion of a neural network makes it possible to use these networks in control problem schemes. This paper presents a control strategy based upon an inversion of a feed-forward trained local linear model tree. The local linear model tree is realized through a fuzzy neural network. Simulated results from real data measurements are presented, and two control loops are explicitly compared.
Źródło:
Journal of Automation Mobile Robotics and Intelligent Systems; 2009, 3, 3; 83-89
1897-8649
2080-2145
Pojawia się w:
Journal of Automation Mobile Robotics and Intelligent Systems
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
Single-ended quality measurement of a music content via convolutional recurrent neural networks
Autorzy:
Organiściak, Kamila
Borkowski, Józef
Powiązania:
https://bibliotekanauki.pl/articles/1849158.pdf
Data publikacji:
2020
Wydawca:
Polska Akademia Nauk. Czytelnia Czasopism PAN
Tematy:
audio data analysis
artefacts detection
convolutional neural networks
recurrent neural networks
classification model
Opis:
The paper examines the usage of Convolutional Bidirectional Recurrent Neural Network (CBRNN) for a problem of quality measurement in a music content. The key contribution in this approach, compared to the existing research, is that the examined model is evaluated in terms of detecting acoustic anomalies without the requirement to provide a reference (clean) signal. Since real music content may include some modes of instrumental sounds, speech and singing voice or different audio effects, it is more complex to analyze than clean speech or artificial signals, especially without a comparison to the known reference content. The presented results might be treated as a proof of concept, since some specific types of artefacts are covered in this paper (examples of quantization defect, missing sound, distortion of gain characteristics, extra noise sound). However, the described model can be easily expanded to detect other impairments or used as a pre-trained model for other transfer learning processes. To examine the model efficiency several experiments have been performed and reported in the paper. The raw audio samples were transformed into Mel-scaled spectrograms and transferred as input to the model, first independently, then along with additional features (Zero Crossing Rate, Spectral Contrast). According to the obtained results, there is a significant increase in overall accuracy (by 10.1%), if Spectral Contrast information is provided together with Mel-scaled spectrograms. The paper examines also the influence of recursive layers on effectiveness of the artefact classification task.
Źródło:
Metrology and Measurement Systems; 2020, 27, 4; 721-733
0860-8229
Pojawia się w:
Metrology and Measurement Systems
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
A phonological encoding of Turkish for neural networks
Autorzy:
Stachowski, Kamil
Powiązania:
https://bibliotekanauki.pl/articles/634635.pdf
Data publikacji:
2015
Wydawca:
Uniwersytet Jagielloński. Wydawnictwo Uniwersytetu Jagiellońskiego
Tematy:
experimental phonology, neural networks, Turkish
Opis:
The paper proposes a multi-dimensional, phonologically-aware numeric encoding of Turkish for use with neural networks. The system is evaluated and compared to PatPho (Li/MacWhinney 2002) in a test in which the network computes the shape of the past tense suffix.
Źródło:
Studia Linguistica Universitatis Iagellonicae Cracoviensis; 2015, 129, 4
2083-4624
Pojawia się w:
Studia Linguistica Universitatis Iagellonicae Cracoviensis
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
The assurance of liquidity in a small enterprise by the application of reverse approach
Autorzy:
Kluge, P. D.
Relich, M.
Bach, I.
Powiązania:
https://bibliotekanauki.pl/articles/118251.pdf
Data publikacji:
2006
Wydawca:
Polskie Towarzystwo Promocji Wiedzy
Tematy:
liquidity
reverse approach
neural networks
Opis:
This paper presents how to assure the desirable liquidity level in a small enterprise with the application of the reverse approach. It is an alternative approach as compared to the ones that have been applied so far and which were based on the setting conditions required to obtain the desirable financial liquidity level. The example analysed in this paper led to the comparison of the conventional approach results with the reverse approach results.
Źródło:
Applied Computer Science; 2006, 2, 2; 117-128
1895-3735
Pojawia się w:
Applied Computer Science
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
Parallel implementation of neural networks with the use of GPGPU technology OpenCL
Autorzy:
Kłyś, M.
Szymczyk, M.
Szymczyk, P.
Gajer, M.
Powiązania:
https://bibliotekanauki.pl/articles/114679.pdf
Data publikacji:
2015
Wydawca:
Stowarzyszenie Inżynierów i Techników Mechaników Polskich
Tematy:
OpenCL
Artificial Neural Networks
GPGPU
Opis:
The article discusses possibilities of implementing a neural network in a parallel way. The issues of implementation are illustrated with the example of the non-linear neural network. Parallel implementation of earlier mentioned neural network is written with the use of OpenCL library, which is a representative of software supporting general-purpose computing on graphics processor units (GPGPU). The obtained results demonstrate that some group of algorithms can be computed faster if they are implemented in a parallel way and run on a multi-core processor (CPU) or a graphics processing unit (GPU). In case of the GPU, the implemented algorithm should be divided into many threads in order to perform computations faster than on a multi-core CPU. In general, computations on a GPU should be performed when there is a need to process a large amount of data with the use of algorithm which is very well suited to parallel implementation.
Źródło:
Measurement Automation Monitoring; 2015, 61, 1; 16-20
2450-2855
Pojawia się w:
Measurement Automation Monitoring
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
The development of Kalman Filter learning technique for Artificial Neural Networks
Autorzy:
Krok, A.
Powiązania:
https://bibliotekanauki.pl/articles/308081.pdf
Data publikacji:
2013
Wydawca:
Instytut Łączności - Państwowy Instytut Badawczy
Tematy:
Artificial Neural Networks
Kalman filter
Opis:
The paper presents an idea of using the Kalman Filtering (KF) for learning the Artificial Neural Networks (ANN). It is shown that KF can be fully competitive or more beneficial method with comparison standard Artificial Neural Networks learning techniques. The development of the method is presented respecting selective learning of chosen part of ANN. Another issue presented in this paper is the author’s concept of automatic selection of architecture of ANN learned by means of KF based on removing unnecessary connection inside the network. The effectiveness of presented ideas is illustrated on the examples of time series modeling and prediction. Considered data came from the experiments and situ measurements in the field of structural mechanics and materials.
Źródło:
Journal of Telecommunications and Information Technology; 2013, 4; 16-21
1509-4553
1899-8852
Pojawia się w:
Journal of Telecommunications and Information Technology
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
Application of genetically evolved neural networks to dynamic terrain generation
Autorzy:
Chomątek, L.
Rudnicki, M.
Powiązania:
https://bibliotekanauki.pl/articles/202394.pdf
Data publikacji:
2011
Wydawca:
Polska Akademia Nauk. Czytelnia Czasopism PAN
Tematy:
evolving neural networks
water erosion
Opis:
Real time terrain generation is a vital part in the development of realistic computer simulations and games. Dynamic terrain generation influences the realism of simulation, because its participants have to adapt to the current environment conditions. Dynamically generated primary terrain is transformed in order to reflect natural phenomena, such as thermal and water erosion, avalanches or glaciers. In this article a possibility of primary terrain transformation with application of artificial neural networks is shown. The networks are trained by evolutionary algorithms to solve a problem of a water erosion phenomenon. Obtained results show that application of such neural networks to this problem can significantly reduce the processing time needed to perform the process of modeling the natural phenomena.
Źródło:
Bulletin of the Polish Academy of Sciences. Technical Sciences; 2011, 59, 1; 3-8
0239-7528
Pojawia się w:
Bulletin of the Polish Academy of Sciences. Technical Sciences
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
The Application of Neural Networks to the Process of Gaining and Consolidating the Knowledge
Autorzy:
Plichta, A.
Powiązania:
https://bibliotekanauki.pl/articles/308445.pdf
Data publikacji:
2012
Wydawca:
Instytut Łączności - Państwowy Instytut Badawczy
Tematy:
e-learning
neural networks
orthography
Opis:
The e-learning course is one of the most efficient and promising didactic policies. It must be grounded on the revision because it was proved that it enhances the longterm memory. However, human mind is not a uniform phenomenon. Each man memorizes and learns in a different manner. The purpose of the intelligent e-learning system presented in this paper is to teach orthography and this system is based on the multilayer neural network. Such structure enables a learner to adjust the crucial period between revisions to personal learning habits and policy.
Źródło:
Journal of Telecommunications and Information Technology; 2012, 1; 90-95
1509-4553
1899-8852
Pojawia się w:
Journal of Telecommunications and Information Technology
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
Multi-layered Bayesian Neural Networks for Simulation and Prediction Stress-Strain Time Series
Autorzy:
Krok, A.
Powiązania:
https://bibliotekanauki.pl/articles/308596.pdf
Data publikacji:
2015
Wydawca:
Instytut Łączności - Państwowy Instytut Badawczy
Tematy:
Bayesian neural networks
Kalman filtering
Opis:
The aim of the paper is to investigate the differences as far as the numerical accuracy is concerned between feedforward layered Artificial Neural Networks (ANN) learned by means of Kalman filtering (KF) and ANN learned by means of the evidence procedure for Bayesian technique. The stress-strain experimental time series for concrete hysteresis loops obtained by the experiment of cyclic loading is presented as considered example.
Źródło:
Journal of Telecommunications and Information Technology; 2015, 3; 45-51
1509-4553
1899-8852
Pojawia się w:
Journal of Telecommunications and Information Technology
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
Data security based on neural networks
Autorzy:
Noaman, K.M.G.
Jalab, H.A.
Powiązania:
https://bibliotekanauki.pl/articles/1964155.pdf
Data publikacji:
2005
Wydawca:
Politechnika Gdańska
Tematy:
data security
cryptography
neural networks
Opis:
The paper is concerned with the study and design of a data security system based on neural networks. Data with different keys were taken as test data, encrypted, decrypted and compared with the original data. The results have confirmed its advantages over other techniques.
Źródło:
TASK Quarterly. Scientific Bulletin of Academic Computer Centre in Gdansk; 2005, 9, 4; 409-414
1428-6394
Pojawia się w:
TASK Quarterly. Scientific Bulletin of Academic Computer Centre in Gdansk
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
Smart sensor for operational load measurements
Inteligentny sensor do pomiaru obciążeń w czasie pracy
Autorzy:
Uhl, T.
Petko, M.
Powiązania:
https://bibliotekanauki.pl/articles/281279.pdf
Data publikacji:
2002
Wydawca:
Polskie Towarzystwo Mechaniki Teoretycznej i Stosowanej
Tematy:
smart sensor
mechatronics
neural networks
Opis:
The important technique enabling machine health monitoring and fault localisation is operational load measurement; however direct measurement is usually difficult or even impossible. The paper deals with the realisation of the idea of developing "smart sensor" which estimates the load based on structure response. In the case study, hardware neural network has been used to obtain the load course from the vibrations in specific points of the structure. The paper covers also problems with prototyping and implementation stages during development of signal processing algorithms with emphasis placed on ASIC/FPGA based hardware platform, for which a methodology of implementation is formulated and validated by practical application to the smart sensor problem. Details of the procedure are presented along with the tools used and results obtained during its realization. Performance of the device during experiment is analysed and, finally, conclusion are shown.
Ważną techniką wykorzystywaną w monitorowaniu stanu technicznego maszyn i lokalizacji uszkodzeń jest pomiar obciążeń w czasie ich pracy. Jednak bezpośredni pomiar jest zwykle trudny albo nawet niemożliwy. Artykuł dotyczy realizacji ideii opracowania "inteligentnego sensora" estymującego obciążenie na podstawie odpowiedzi struktury mechanicznej. W opisanym przykładzie, realizowana sprzętowo sieć neuronowa została zastosowana do otrzymania przebiegu obciążenia na podstawie drgań określonych punktów struktury. Artykuł omawia także problemy związane z prototypowaniem i implementacja algorytmów przetwarzania sygnałów, ze szczególnym uwzględnieniem sytuacji, gdy część sprzętowa oparta jest na układach ASIC/FPGA, dla której opracowano metodologię implementacji, zweryfikowaną poprzez praktyczne zastosowanie do problemu inteligentnego sensora. Pokazano szczegóły tej procedury wraz z zastosowanymi narzędziami i wyniki osiągnięte w trakcie jej realizacji. Przeanalizowano wyniki działania urządzenia podczas eksperymentu i przedstawiono wnioski.
Źródło:
Journal of Theoretical and Applied Mechanics; 2002, 40, 3; 797-815
1429-2955
Pojawia się w:
Journal of Theoretical and Applied Mechanics
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
Application of artificial neural networks to assessment of ship manoeuvrability qualities
Autorzy:
Abramowski, T.
Powiązania:
https://bibliotekanauki.pl/articles/258896.pdf
Data publikacji:
2008
Wydawca:
Politechnika Gdańska. Wydział Inżynierii Mechanicznej i Okrętownictwa
Tematy:
neural networks
ship manoeuvrability qualities
Opis:
This paper presents an attempt to applying neural networks for assessment of parameters of standard manoeuvrability tests, i.e. circulation test and zig-zag test. Methodological approach to application of neural networks as well as applied network structures and neuron activation functions are generally presented. Also, results of simulations performed by means of the elaborated networks are given in comparison with test cases selected at random. In order to analyze and reveal general trends, correlation relationships between results from network simulations and test cases were calculated and are presented as well.
Źródło:
Polish Maritime Research; 2008, 2; 15-21
1233-2585
Pojawia się w:
Polish Maritime Research
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
Application of Discriminant Analysis and Neural Networks to Forecasting the Financial Standing of Farms
Wykorzystanie analizy dyskryminacyjnej oraz sieci neuronowych do prognozowania sytuacji finansowej gospodarstw rolniczych z uwzględnieniem czasu
Autorzy:
Kisielińska, Joanna
Powiązania:
https://bibliotekanauki.pl/articles/905048.pdf
Data publikacji:
2009
Wydawca:
Uniwersytet Łódzki. Wydawnictwo Uniwersytetu Łódzkiego
Tematy:
linear discriminant function
neural networks
Opis:
The aim of the research was to determinate a linear discriminant function and neural network that could be applied for financial situation forecasting in polish farms sector. The construction of discriminant models was based on set of financial indicators and the classification criterion was based on the private farm's income. The investigated population was divided into two equal groups with respect to the median value of income. The data was gathered in the period of several years that allowed examine the influence of the time on the quality of discriminant models. Also the set of indicators with large forecasting ability was determined. The data used for the discriminant models was sourced from private farms keeping farm accountancy under auspices the Institute of Agricultural and Food Economics in the years 1992-2002. The calculations was made with help of STATISTICA and data analysis with Excel using VISUAL BASIC FOR APPLICATION.
Celem prezentowanych badań było wyznaczenie liniowej funkcji dyskryminacyjnej oraz sieci neuronowej do tworzenia prognoz sytuacji finansowej gospodarstw rolniczych. Podstawę, konstrukcji modeli dyskryminacyjnych stanowił zestaw wskaźników finansowych, natomiast kryterium klasyfikacji oparte zostało na dochodzie rolniczym. Badaną zbiorowość podzielono na dwie równoliczne klasy. Gospodarstwa osiągające dochód rolniczy mniejszy od mediany (gospodarstwa słabe) zaliczano do klasy I, natomiast o dochodzie od niej większym (gospodarstw dobre) do II. Taki dobór kryterium klasyfikacji wynika z tego, że w przypadku gospodarstw rolniczych problem bankructwa praktycznie nie występuje, wobec czego nie można dla nuli budować typowych modeli ostrzegawczych. Analizy przeprowadzono na podstawie danych pochodzących z kilku lat, co pozwoliło im zbadanie wpływu czasu na jakość uzyskanych modeli dyskryminacyjnych. Chodziło o sprawdzenie, czy model zbudowany dla jednego roku można będzie wykorzystać w lalach kolejnych. Cel dodatkowy polegał na określeniu wskaźników finansowych o największych zdolnościach prognostycznych, czyli takich, których wpływ na wartość funkcji dyskryminacyjnej jest najistotniejszy. Modele dyskryminacyjne utworzono w oparciu o wyniki finansowe gospodarstw rolniczych prowadzących rachunkowość rolną pod kierunkiem Instytutu Ekonomiki Rolnictwa i Gospodarki Żywnościowej w latach 1992-2001. Do obliczeń wykorzystany został pakiet STATISTICA, natomiast obróbkę danych i analizę wyników wykonano w arkuszu kalkulacyjnym EXCEL wykorzystując język VISUAL BASIC FOR APPLICATION.
Źródło:
Acta Universitatis Lodziensis. Folia Oeconomica; 2009, 225
0208-6018
2353-7663
Pojawia się w:
Acta Universitatis Lodziensis. Folia Oeconomica
Dostawca treści:
Biblioteka Nauki
Artykuł
Wyświetlanie 1-25 z 831

Ta witryna wykorzystuje pliki cookies do przechowywania informacji na Twoim komputerze. Pliki cookies stosujemy w celu świadczenia usług na najwyższym poziomie, w tym w sposób dostosowany do indywidualnych potrzeb. Korzystanie z witryny bez zmiany ustawień dotyczących cookies oznacza, że będą one zamieszczane w Twoim komputerze. W każdym momencie możesz dokonać zmiany ustawień dotyczących cookies