WSEAS Transactions on Mathematics archive 

About: WSEAS Transactions on Mathematics archive is an academic journal. The journal publishes majorly in the area(s): Nonlinear system & Boundary value problem. Over the lifetime, 608 publications have been published receiving 2456 citations.

Function approximation using artificial neural networks

Abstract: Function approximation, which finds the underlying relationship from a given finite input-output data is the fundamental problem in a vast majority of real world applications, such as prediction, pattern recognition, data mining and classification. Various methods have been developed to address this problem, where one of them is by using artificial neural networks. In this paper, the radial basis function network and the wavelet neural network are applied in estimating periodic, exponential and piecewise continuous functions. Different types of basis functions are used as the activation function in the hidden nodes of the radial basis function network and the wavelet neural network. The performance is compared by using the normalized square root mean square error function as the indicator of the accuracy of these neural network models.

Theoretical analysis of inverse weibull distribution

Abstract: In this study we present the theoretical analysis of Inverse weibull distribution. This paper presents the flexibility of the Inverse weibull distribution that approaches to different distributions. Here we compare the relevant parameters such as shape, scale parameters by using simulation analysis. Here we present the relationship between shape parameter and other properties such as mean, median, mode, variance, coefficient of variation, coefficient of skewness and coefficient of kurtosis models are shown graphically and mathematically presented.

Optimal operational strategy for hybrid renewable energy system using genetic algorithms

Abstract: Off-grid settlements require efficient, reliable and cost-effective renewable energy as alternative to the power supplied by diesel generator. Techno-economic analysis is required to find the optimum renewable energy system in the long run. This paper reviews the application of genetic algorithms in optimization of hybrid system consisting of pico hydro system, solar photovoltaic modules, diesel generator and battery sets. It is intended to maximize the use of renewable system while limiting the use of diesel generator. Daily load demand is assumed constant for derivation of annual load. Power derived from the hybrid should be able to meet the demand. Local weather data is used and analyzed to assess the technical and economic viability of utilizing the hybrid system. Optimization of the system will be based on the component sizing and the operational strategy. Genetic algorithms programming is used to evaluate both conditions in minimizing the total net present cost for optimum configuration. Manufacturer data for the hybrid components is used in calculation of sizing to represent actual power derivation. Several operation strategies will be considered while forming the vectors for optimum strategy. Random selection of sizing and strategy is used to initiate the solution for the problem which will have the lowest total net present cost. Sensitivity analysis is also performed to optimize the system at different conditions.

A note on the modified Hermitian and skew-Hermitian splitting methods for non-Hermitian positive definite linear systems

Abstract: Comparing the lopsided Hermitian/skew-Hermitian splitting (LHSS) method and Hermitian/skew-Hermitian splitting (HSS) method, a new criterion for choosing the above two methods is presented, which is better than that of Li, Huang and Liu [Modified Hermitian and skew-Hermitian splitting methods for non-Hermitian positive-definite linear systems, Numer. Lin. Alg. Appl., 14 (2007): 217-235].

Improved estimation of state of stochastic systems via invariant embedding technique

Abstract: In the present paper, for constructing the minimum risk estimators of state of stochastic systems, a new technique of invariant embedding of sample statistics in a loss function is proposed. This technique represents a simple and computationally attractive statistical method based on the constructive use of the invariance principle in mathematical statistics. Unlike the Bayesian approach, an invariant embedding technique is independent of the choice of priors. It allows one to eliminate unknown parameters from the problem and to find the best invariant estimator, which has smaller risk than any of the well-known estimators. Also the problem of how to select the total number of the observations optimally when a constant cost is incurred for each observation taken is discussed. To illustrate the proposed technique, examples are given.