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 "84.35.+I" wg kryterium: Temat

  Lista filtrów
Wyrównaj
    Wyświetlanie 1-14 z 14
    Tytuł:
    Prediction Primary Radiation Shielding Wall Thickness with Artificial Neural Networks
    Autorzy:
    Akkaş, A.
    Başyiğit, C.
    Necip Kurtarici, M.
    Powiązania:
    https://bibliotekanauki.pl/articles/1399661.pdf
    Data publikacji:
    2013-02
    Wydawca:
    Polska Akademia Nauk. Instytut Fizyki PAN
    Tematy:
    28.41.Qb
    84.35.+i
    Opis:
    In this study, wall thickness for using in primary radiation shielding was determined in different energy ranges using tenth value layer by artificial neural networks. Radiation energy values, tenth value layers and negative logarithm of transmission factor (n) were selected as input parameters and wall shielding thickness values selected as output parameters. Consequently, developed artificial neural networks model outputs were compared with experimental results and it was seen that the results were harmonious.
    Źródło:
    Acta Physica Polonica A; 2013, 123, 2; 171-172
    0587-4246
    1898-794X
    Pojawia się w:
    Acta Physica Polonica A
    Dostawca treści:
    Biblioteka Nauki
    Artykuł
    Tytuł:
    Optical Biopsy Method for Breast Cancer Diagnosis Based on Artificial Neural Network Classification οf Fluorescence Landscape Data
    Autorzy:
    Dramićanin, T.
    Zeković, I.
    Dimitrijević, B.
    Ribar, S.
    Dramićanin, M.
    Powiązania:
    https://bibliotekanauki.pl/articles/1795706.pdf
    Data publikacji:
    2009-10
    Wydawca:
    Polska Akademia Nauk. Instytut Fizyki PAN
    Tematy:
    87.64.kv
    84.35.+i
    87.19.xj
    33.50.-j
    Opis:
    Supervised self-organizing map, a type of artificial neural network, is applied for classification of human breast tissue samples utilizing data obtained from fluorescence landscape measurements. Female breast tissue samples were taken soon after the surgical resection, identified and stored at -80°C until fluorescence measurements. From fluorescence landscapes obtained in UV-VIS region spectral features showing statistically significant differences between malignant and normal samples are identified and further quantified to serve as a training input to neural network. Additional set of samples was used as a test group input to trained network in order to evaluate performance of proposed optical biopsy method. Classification sensitivity of 83.9% and specificity of 88.9% are found.
    Źródło:
    Acta Physica Polonica A; 2009, 116, 4; 690-692
    0587-4246
    1898-794X
    Pojawia się w:
    Acta Physica Polonica A
    Dostawca treści:
    Biblioteka Nauki
    Artykuł
    Tytuł:
    Prediction of Two-Element Cylindrical Electrostatic Lens Parameters Using Dynamic Artificial Neural Network
    Autorzy:
    Isik, A.
    Powiązania:
    https://bibliotekanauki.pl/articles/1189865.pdf
    Data publikacji:
    2015-06
    Wydawca:
    Polska Akademia Nauk. Instytut Fizyki PAN
    Tematy:
    84.35.+i
    07.05.Mh
    41.85.Ne
    Opis:
    Two-element cylindrical electrostatic lens systems allowed to control low energy electron or charged particle beam have great importance. In this context, dynamic artificial neural network using nonlinear autoregressive exogenous model has been utilized to predict optimum linear magnification and overall voltage values for these lens designs. The focusing characteristics of electron beam in two-element cylindrical lens systems are investigated with two different nonlinear autoregressive exogenous based artificial neural network models. First artificial neural network model is employed for predicting of voltage ratios of lenses and magnification values. This model interpolates among the object (P) and image positions (Q) and finally finds optimum voltage ratios and magnification values through training dataset. Due to the deviations of electron trajectories in a real lens system, the spherical aberration effects are also taken into account to determine the optimal lens parameters. Therefore, the second artificial neural network model is constructed for predicting spherical aberration coefficients in image point. For each of artificial neural network models, training, test and validation data set are obtained from SIMION 8.1 ion and electron optics software. Artificial neural network model outputs are compared with the SIMION data and very good agreements are found. While artificial neural network is frequently applied in different fields, this is the first study that uses dynamic artificial neural network to predict the parameters of electrostatic lens. It is believed that this pioneering work will be a guide for the future investigations in lens design systems.
    Źródło:
    Acta Physica Polonica A; 2015, 127, 6; 1717-1721
    0587-4246
    1898-794X
    Pojawia się w:
    Acta Physica Polonica A
    Dostawca treści:
    Biblioteka Nauki
    Artykuł
    Tytuł:
    The Investigation of Electron-Optical Parameters Using Artificial Neural Networks
    Autorzy:
    Isik, A.
    Powiązania:
    https://bibliotekanauki.pl/articles/1192484.pdf
    Data publikacji:
    2015-04
    Wydawca:
    Polska Akademia Nauk. Instytut Fizyki PAN
    Tematy:
    41.85.Ne
    07.05.Rm
    84.35.+I
    07.05.Mh
    Opis:
    The optimization of scientific instruments is crucially important to increase the quality of measurements. A major challenge for the development of these experimental tools is the precise determination of focal parameters. Therefore, usage of an innovative technique that meets our requirements is desirable. Among intelligent algorithms, artificial neural network (ANN) has an advantage of obtaining the optical parameters data with high accuracy. One of the most popular geometries used in electrostatic optical devices is geometry with cylinder lenses. In this study, the artificial neural network is applied for the first time to the subject of the magnification parameters of three-element electrostatic cylinder lenses for a wide range of values of the applied voltages. ANN-based optimization has been performed using Matlab/Simulink, and the performance analysis has also been conducted. High-performance results have been achieved using ANN approach. The commercial simulation package SIMION software is used as a data source for artificial neural network results. This approach provides new perspectives for the effective solution for the problems related to electrostatic lenses with different geometries.
    Źródło:
    Acta Physica Polonica A; 2015, 127, 4; 1317-1319
    0587-4246
    1898-794X
    Pojawia się w:
    Acta Physica Polonica A
    Dostawca treści:
    Biblioteka Nauki
    Artykuł
    Tytuł:
    Time Series Artificial Neural Network Approach for Prediction of Optical Lens Properties
    Autorzy:
    Isik, A.
    Isik, N.
    Powiązania:
    https://bibliotekanauki.pl/articles/1398712.pdf
    Data publikacji:
    2016-04
    Wydawca:
    Polska Akademia Nauk. Instytut Fizyki PAN
    Tematy:
    41.85.Ne
    07.05.Tp
    84.35.+I
    07.05.Mh
    Opis:
    Well-designed electrostatic cylindrical lenses are commonly used to control charged particles in atomic and molecular physics instruments such as electron guns and electron microscopes. The most commonly used of these, three-element electrostatic lenses are capable of keeping magnification constant for definite image position. The correct determination of focal and aberration characteristics of these lenses is very important for experimental studies. In this study, motions of electrons in three-element electrostatic cylindrical lenses have been investigated with nonlinear autoregressive exogenous based time series artificial neural network technique. The spherical and chromatic aberrations which affect the beam are also predicted with time series artificial neural network technique. This method is a mathematical model that emulates the biological neural networks. The basic working principle of time series artificial neural network technique is training of network with the known data and then prediction of the unknown data. Simulation results from SIMION 8.1 ray-tracing program are used as training and test data set. According to the results obtained from time series artificial neural network technique technique, a considerably agreement is found between simulation and artificial neural network technique prediction results. The study shows that such an artificial neural network model which has time advantage can be applicable to various electron and ion beam apparatus.
    Źródło:
    Acta Physica Polonica A; 2016, 129, 4; 514-516
    0587-4246
    1898-794X
    Pojawia się w:
    Acta Physica Polonica A
    Dostawca treści:
    Biblioteka Nauki
    Artykuł
    Tytuł:
    Classification of Electron Gun Operation Modes Using Artificial Neural Networks
    Autorzy:
    Isik, N.
    Isik, A.
    Powiązania:
    https://bibliotekanauki.pl/articles/1186983.pdf
    Data publikacji:
    2016-04
    Wydawca:
    Polska Akademia Nauk. Instytut Fizyki PAN
    Tematy:
    41.85.Ne
    07.05.Rm
    84.35.+I
    07.05.Mh
    Opis:
    In electron collision experiments, the seven-element electron gun is commonly used to accelerate and focus an electron beam. The main operation modes of this experimental device are afocal, zoom and broad beam-modes. Each of these operation modes can be used for producing electron beam with desired diameter. In this study, the artificial neural network classification technique (ANN) is used for classification of electron gun operation modes depending on electrostatic lens voltages. For this purpose, we investigate the focusing condition for the first three-element lens. Other ANN is employed for the second four-element lens voltages to find the electron gun operation modes. A comprehensive training data is obtained from SIMION software which uses traditional ray-tracing method. ANNs are trained with this dataset. Moreover, performance evaluations are carried out to determine the classification power of ANNs. High performance values show that the ANN can easily categorize the operation mode of the electron gun as a function of lens voltages. The proposed approach may help to adjust electron gun voltages before collision experiments. It is believed that this study will be a model for the future research in electron collision systems. Network can be trained with experimental data for practical applications.
    Źródło:
    Acta Physica Polonica A; 2016, 129, 4; 628-630
    0587-4246
    1898-794X
    Pojawia się w:
    Acta Physica Polonica A
    Dostawca treści:
    Biblioteka Nauki
    Artykuł
    Tytuł:
    Computational Modeling of Magnetic Properties and Glass Forming Ability of Bulk Amorphous Materials
    Autorzy:
    Kabaer, M.
    Ovalioglu, H.
    Kucuk, I.
    Powiązania:
    https://bibliotekanauki.pl/articles/1534071.pdf
    Data publikacji:
    2010-11
    Wydawca:
    Polska Akademia Nauk. Instytut Fizyki PAN
    Tematy:
    64.70.pe
    84.35.+i
    75.50.Vv
    75.50.Kj
    Opis:
    A model based on artificial neural network was designed for the simulation and estimation of glass forming ability parameters and saturation magnetization and coercivity of bulk glassy alloys. Its performance is evaluated by the influences of different kinds of alloys and elements on the glass forming ability and magnetic properties. The values of glass forming ability parameters and saturation magnetization and coercivity values estimated by artificial neural network agree well with the experimental values, indicating that the model is reliable and adequate.
    Źródło:
    Acta Physica Polonica A; 2010, 118, 5; 827-828
    0587-4246
    1898-794X
    Pojawia się w:
    Acta Physica Polonica A
    Dostawca treści:
    Biblioteka Nauki
    Artykuł
    Tytuł:
    Detection and Classification of Selected Noise Sources in Long-Term Acoustic Climate Monitoring
    Autorzy:
    Kłaczyński, M.
    Wszołek, T.
    Powiązania:
    https://bibliotekanauki.pl/articles/1490331.pdf
    Data publikacji:
    2012-01
    Wydawca:
    Polska Akademia Nauk. Instytut Fizyki PAN
    Tematy:
    43.60.Lq
    84.35.+i
    43.55.Ka
    Opis:
    Continuous acoustical climate monitoring of the environment raises several problems related to large quantities of the recorded data, which often represents information unrelated to the studied noise source. Manual verification of such data is time-consuming and costly. Therefore, developing effective methods for automatic identification of transport noise sources becomes an important task for the proper determination of noise levels. This paper presents a concept of such method of automatic detection and classification of the noise sources from the air and railway transportation in the acoustic environmental monitoring.
    Źródło:
    Acta Physica Polonica A; 2012, 121, 1A; A-179-A-182
    0587-4246
    1898-794X
    Pojawia się w:
    Acta Physica Polonica A
    Dostawca treści:
    Biblioteka Nauki
    Artykuł
    Tytuł:
    Modelling of Power Loss in Electrical Steels
    Autorzy:
    Kucuk, I.
    Erturk, K.
    Haciismailoglu, M.
    Derebasi, N.
    Powiązania:
    https://bibliotekanauki.pl/articles/1813590.pdf
    Data publikacji:
    2008-01
    Wydawca:
    Polska Akademia Nauk. Instytut Fizyki PAN
    Tematy:
    75.50.Bb
    84.35.+i
    Opis:
    This paper presents a new artificial neural network approach based on loss separation model to compute power loss on different types of electrical steels. The network was trained by a Levenberg-Marquardt algorithm. The results obtained by using the proposed model were compared with a commonly used conventional model. The comparison has shown that the neural network model is in good agreement with experimental data with respect to the conventional model.
    Źródło:
    Acta Physica Polonica A; 2008, 113, 1; 147-150
    0587-4246
    1898-794X
    Pojawia się w:
    Acta Physica Polonica A
    Dostawca treści:
    Biblioteka Nauki
    Artykuł
    Tytuł:
    Neural Approximation of Empirical Functions
    Autorzy:
    Roj, J.
    Powiązania:
    https://bibliotekanauki.pl/articles/1399400.pdf
    Data publikacji:
    2013-09
    Wydawca:
    Polska Akademia Nauk. Instytut Fizyki PAN
    Tematy:
    84.35.+i
    07.05.Mh
    06.20.-f
    06.20.F-
    06.20.fb
    02.60.Ed
    Opis:
    The paper presents the results of simulation studies of selected neural network structures used for non-linear function approximation based on a limited accuracy data. There was performed the analysis of the interdependence of the network structure and the size of the set of learning patterns. The approximation inaccuracy was expressed by the uncertainty interval width. The approximation properties of the neural method were compared with those of the piece-wise linear and polynomial: "cubic" and "spline" methods.
    Źródło:
    Acta Physica Polonica A; 2013, 124, 3; 554-557
    0587-4246
    1898-794X
    Pojawia się w:
    Acta Physica Polonica A
    Dostawca treści:
    Biblioteka Nauki
    Artykuł
    Tytuł:
    Automatic Classification of LFM Signals for Radar Emitter Recognition Using Wavelet Decomposition and LVQ Classifier
    Autorzy:
    Świercz, E.
    Powiązania:
    https://bibliotekanauki.pl/articles/1505216.pdf
    Data publikacji:
    2011-04
    Wydawca:
    Polska Akademia Nauk. Instytut Fizyki PAN
    Tematy:
    84.40.Ua
    84.35.+i
    Opis:
    The paper presents a novel approach, based on the wavelet decomposition and the learning vector quantisation algorithm, to automatic classification of signals with linear frequency modulation, generated by radar emitters. The goal of radar transmitter classification is to determine the particular transmitter, from which a signal originated, using only the just received waveform. To categorise a current linear frequency modulation signal to the particular transmitter, the discrete wavelet decomposition of the received signal is accomplished in order to get a representative set of features with good classification properties. The learning vector quantisation algorithm with a previously defined set of features as an input of the learning vector quantisation neural net is proposed as the intelligent classification algorithm, which combines competitive learning with supervision. After the learning process, the learning vector quantisation algorithm is ready to perform the classification process for different data than data used in the learning stage. Simulation results show the high classification accuracy for experimentally chosen wavelets and suggested architecture of the learning vector quantisation classifier.
    Źródło:
    Acta Physica Polonica A; 2011, 119, 4; 488-494
    0587-4246
    1898-794X
    Pojawia się w:
    Acta Physica Polonica A
    Dostawca treści:
    Biblioteka Nauki
    Artykuł
    Tytuł:
    Gas Sensing Supported by Pattern Recognition
    Autorzy:
    Tyszkiewicz, C.
    Szpakowski, A.
    Pustelny, T.
    Powiązania:
    https://bibliotekanauki.pl/articles/1807758.pdf
    Data publikacji:
    2009-09
    Wydawca:
    Polska Akademia Nauk. Instytut Fizyki PAN
    Tematy:
    02.50.Sk
    07.07.Df
    84.35.+i
    Opis:
    The system composed of the array of eight semiconductor, chemoresistive gas sensors was used for the classification of hydrogen, methane and carbon oxide gaseous samples. The classification task was performed by pattern recognition methods applied to the multivariate response of the array. The pattern recognition scheme used for classification uses a feature subset selection algorithm coupled with an objective function designed for clustering and a multilayer perceptron classifier.
    Źródło:
    Acta Physica Polonica A; 2009, 116, 3; 419-421
    0587-4246
    1898-794X
    Pojawia się w:
    Acta Physica Polonica A
    Dostawca treści:
    Biblioteka Nauki
    Artykuł
    Tytuł:
    A Neural Network Model of an Ising Spin Glass
    Autorzy:
    Wilson, K. F.
    Goossens, D. J.
    Powiązania:
    https://bibliotekanauki.pl/articles/2013998.pdf
    Data publikacji:
    2000-05
    Wydawca:
    Polska Akademia Nauk. Instytut Fizyki PAN
    Tematy:
    75.10.-b
    75.10.Nr
    84.35.+i
    Opis:
    The behaviour of an Ising spin glass (S=1/2) with infinite range interactions is modelled using a numerical simulation based on a neural network. Thermodynamic variables are defined on the network, and are found to obey the Thouless-Anderson-Palmer theory when the applied magnetic field is zero. When a magnetic field is applied along the spin direction, complex field-dependent behaviour appears, including a state in which the Edwards-Anderson order parameter is independent of temperature below the critical temperature.
    Źródło:
    Acta Physica Polonica A; 2000, 97, 5; 983-986
    0587-4246
    1898-794X
    Pojawia się w:
    Acta Physica Polonica A
    Dostawca treści:
    Biblioteka Nauki
    Artykuł
    Tytuł:
    Signal Processing and Analysis of Pathological Speech Using Artificial Intelligence and Learning Systems Methods
    Autorzy:
    Wszołek, W.
    Izworski, A.
    Izworski, G.
    Powiązania:
    https://bibliotekanauki.pl/articles/1400072.pdf
    Data publikacji:
    2013-06
    Wydawca:
    Polska Akademia Nauk. Instytut Fizyki PAN
    Tematy:
    43.70.+I
    84.35.+i
    Opis:
    In this paper, selected results are presented of research which is carried on for over a decade and covers valuation of chosen signal processing methods suitable to analyze and valuate pathological speech. This valuation is necessary during solving many medical diagnostics problems and when planning therapy and rehabilitation of certain types of diseases. All presented examples are used in clinical practice in the area of dentistry, dental surgery, otolaryngology and most of all, in phoniatrics and speech correction.
    Źródło:
    Acta Physica Polonica A; 2013, 123, 6; 995-1000
    0587-4246
    1898-794X
    Pojawia się w:
    Acta Physica Polonica A
    Dostawca treści:
    Biblioteka Nauki
    Artykuł
      Wyświetlanie 1-14 z 14

      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