The paper addresses the problém of efficient and adequate representation of functions using two soft computing techniques: fuzzy logic and neural networks. The principle approach to the construction of approximating formulas is discussed. We suggest a generalized definition of the normál forms in predicate BL and ŁII logic and prove conditional equivalence between a formula and each of its normal forms. Some mutual relations between the normál forms will be also established.
The paper deals with a predictive vector quantization of an image
based on a neural network architectures, wliere a vector predictor is iniplernented by three-layer neural network with various hidden nodes and bias units, sigrnoid function as nonlinearity and where vector quantizer is inipleinented by Kohonen self-organizing feature maps, it means the codebook is obtained by neural network clustering algorithm. We have tested aíi influence of a nuinber of hidden nodes, various convergention rates of a learning algorithm and a presence of the sigrnoid function to a rnean square prediction error. Next we háve studied an influence of codebook size to a rnean sciuare quantization error, that means a performance of predictive vector quantization system for various bit rates. The image of Lena of size 512 X 512 pels was coded for various bit rates, where we háve ušed onedirnensional and two-dimensional vector prediction of the blocks of pels.
The applicability of neural networks for the evaluation of the lifetime of semiconductor devices is demonstrated. The neural network based method can be used as a general tool for modeling. The commonly used main-acceleratingparameter models could be obtained by the neural net reducing. The neural network based method is attractive also due to the neural net ability to process "noisy" data. The method should find wide applications in degradation modeling.
In this paper, neural network based cryptology is performed. The system consists of two stages. In the first stage, neural network-based pseudo-random numbers (NPRNGs) are generated and the results are tested for randomness using National Institute of Standard Technology (NIST) randomness tests. In the second stage, a neural network-based cryptosystem is designed using NPRNGs. In this cryptosystem, data, which is encrypted by non-linear techniques, is subject to decryption attempts by means of two identical artificial neural networks (ANNs). With the first neural network, non-linear encryption is modeled using relationbuilding functionality. The encrypted data is decrypted with the second neural network using decision-making functionality.
Slow fluctuating radar targets have shown to be very difficult to classify by means of neural networks. This paper deals with the application of time-frequency decompositions for improving the performance of neural networks for this kind of targets. Several topics, such as dimensionality reduction of the time-frequency representations and the optimum value of SNR for training are discussed. The proposed detector is compared with a single neural network for radar detection, showing that he performance is improved for slow fluctuating radar targets, especially for low values of the probability of false alarm.
The genus Trichoderma acts as an important antagonist against phytopathogenic fungi. This paper proposes a software-based identification tool for recognition of different species of Trichoderma. The method uses the morphological features for identification. Morphological-based species recognition is common method for identifying fungi, but regarding the similarity of morphological features among different species, their manual identification is difficult, time-consuming and may bring about faulty results. In this paper it is intended to identify different species of Trichoderma by means of neural network. For this purpose, 14 characteristics are used including 5 macroscopic and 9 microscopic characteristics. After quantifying qualitative features and training a multilayer perceptron neural network with quantified data, 25 species of Trichoderma are recognized by using the network. Totally, identification of Trichoderma species as one useful fungus is achieved by using the trained network.
We present a neural network application to the diagnosis of vocal and voice disorders. These disorders normally cause changes in the voice signal, so we use acoustic parameters extracted from the voice as inputs for the neural network. The selected neural network structure is Multilayer Feedforward. In this paper, we focus our application on the classification between pathologic and non-pathologic voices. The performance of the neural network is very good, 100 % correct in the test. Furthermore, having used neural network techniques to reduce the initial nuniber of inputs (35), we conclude that only two acoustic parameters are needed for the classification between normal and pathological voices. The application can be a very useful diagnostic tool because it is non-invasive, makes it possible to develop an automatic computer-based diagnosis system, reduces the cost and tirne of the diagnosis, is objective and can also be useful for evaluation of surgical, pharmacological and rehabilitation processes. Finally, we discuss the lirnitation of our work and possible future research.
In this paper, for a class of the complex nonlinear system control problems, based on the two-person zero-sum game theory, combined with the idea of approximate dynamic programming(ADP), the constrained optimization control problem is solved for the nonlinear systems with unknown system functions and unknown time-varying disturbances. In order to obtain the approximate optimal solution of the zero-sum game, the multilayer neural network is used to fit the evaluation network, the execution network and the disturbance network of ADP respectively. The Lyapunov stability theory is used to prove the uniform convergence, and the system control output converges to the neighborhood of the target reference value. Finally, the simulation example verifies the effectiveness of the algorithm.
In this paper, we examine the use of Neural Network Regression (NNR) and alternative forecasting techniques in financial forecasting models and financial trading models. In both types of applications, NNR models results are benchmarked against simpler alternativě approaches to ensure that there is indeed added value in the use of these more complex models.
The idea to use a nonlinear nonparametric approach to predict financial variables is intuitively appealing. But whereas some applications need to be assessed on traditional forecasting accuracy criteria such as root mean squared errors, others that deal with trading financial markets need to be assessed on the basis of financial criteria such as risk adjusted return. Accordingly, we develop two different types of applications. In the first one, using monthly data from April 1993 through June 1999 from a UK financial institution, we develop alternativě forecasting models of cash flows and cheque values of four of its major customers. These models are then tested out-of-sample over the period July 1999-April 2000 in terms of forecasting accuracy.
In the second series of applications, we develop financial trading models for four major stock market indices (S&P500, FTSEIOO, EUROSTOXX50 and NIKKEI225) using daily data from 31 January 1994 through 4 May 1999 for in-sample estimation and leaving the period 5 May 1999 through 6 June 2000 for out-of-sample testing. In this case, the trading models developed are not assessed in terms of forecasting accuracy, but in terms of trading efficiency via the use of a simulated trading strategy.
In both types of applications, for the periods and time series concerned, we clearly show that the NNR models do indeed add value in the forecasting process.
In this paper a sieve bootstrap scheme, the Neural Network Sieve bootstrap, for nonlinear time series is proposed. The approach, which is non parametric in its spirit, does not have the problems of other nonparametric bootstrap techniques such as the blockwise schemes. The procedure performs similarly to the AR-Sieve bootstrap for linear processes while it outperforms the AR-Sieve and the moving block bootstrap for nonlinear processes, both in terms of bias and variability.