Wyniki wyszukiwania - BazTech

1

RBF neural networks for function approximation in dynamic modelling

Nedbalek J.

Journal of KONBiN

|

2008

|

No. 5 (8)

223-232

EN

The paper demonstrates the comparison of Monte Carlo simulation algorithm with neural network enhancement in the reliability case study. With regard to process dynamics, we attempt to evaluate the tank system unreliability related to the initiative input parameters setting. The neural network is used in equation coefficients calculation, which is executed in each transient state. Due to the neural networks, for some of the initial component settings we can achieve the results of computation faster than in classical way of coefficients calculating and substituting into the equation.

PL

W artykule przedstawiono porównanie algorytmu symulacyjnego wykorzystującego metodę Monte Carlo względem rozszerzenia sieci neuronowych na przypadek badania niezawodności obiektów. W odniesieniu do dynamiki procesu, podjęliśmy próbę oceny niepewności (zawodności) układu zbiornika w zależności od początkowych ustawień parametrów wejściowych. Do wyznaczenia współczynników równań wykorzystywane są sieci neuronowe, a proces obliczeniowy jest wykonywany dla każdego stanu przejściowego (nieustalonego). Dzięki zastosowaniu sieci neuronowych, dla pewnych ustawień wartości początkowych jesteśmy w stanie otrzymać wyniki obliczeń szybciej, niż w przypadku zastosowania klasycznej metody wyliczenia współczynników i podstawienia ich do równania wyjściowego.

2

RBFFCA: A Hybrid Pattern Classifier Using Radial Basis Function and Fuzzy Cellular Automata

Maji P., Chaudhuri P.P.

Fundamenta Informaticae

|

2007

|

Vol. 78, nr 3

369-396

EN

A hybrid learning algorithm, termed as RBFFCA, for the solution of classification problems with real valued inputs is proposed. It comprises an integration of the principles of radial basis function (RBF) and fuzzy cellular automata (FCA). The FCA has been evolved through genetic algorithm (GA) formulation to perform pattern classification task. The versatility of the proposed hybrid scheme is illustrated through its application in diverse fields. Simulation results conducted on benchmark database show that the hybrid pattern classifier achieves excellent performance both in terms of classification accuracy and learning efficiency. Extensive experimental results supported with analytical formulation establish the effectiveness of RBFFCA based pattern classifier and prove it as an efficient and cost-effective alternative for the classification problem.

3

Lan interconnection unit based on an artificial neural network

Hamid A.J.

TASK Quarterly : scientific bulletin of Academic Computer Centre in Gdansk

|

2006

|

Vol. 10, No 3

339-346

EN

This paper presents the design of an intelligent interconnection unit based on an artificial neural network (ANN), used when two local area networks (LAN) with different IEEE 802 standard protocols are connected. The proposed ANN is used to activate execution of suitable procedures bridging 802.X LAN and 802.Y LAN.

4

LTF-C: Architecture, Training Algorithm and Applications of New Neural Classifier

Wojnarski M.

Fundamenta Informaticae

|

2003

|

Vol. 54, nr 1

89-105

EN

This paper presents a new model of an artificial neural network solving classification problems, called Local Transfer Function Classifier (). Its architecture is very similar to this of the Radial Basis Function neural network (RBF), however it utilizes an entirely different learning algorithm. This algorithm is composed of four main parts: changing positions of reception fields, changing their sizes, insertion of new hidden neurons and removal of unnecessary ones during the training. The paper presents also results of application to three real-life tasks: handwritten digit recognition, credit approval and cancer diagnosis. was able to solve each of these problems with better accuracy than most popular classification systems. Moreover, was relatively small and fast.