Abhisek Paul

Comparative Study of Radial Basis Function Neural Network with Estimation of Eigenvalue in Image Using MATLAB

Radial Basis Functions (RBFs) are very important in neural network. In this paper various Radial Basis Functions of neural network such as Generalized Inverse Multi Quadratic, Generalized Multi Quadratic and Gaussian are compared with matrix of images. Mathematical calculation, comparative study and simulation of Eigen value of matrix show that Gaussian RBF performs better result and gives lesser error compared to the other Radial Basis Functions of neutral network.

Application of (0, 1)-Matrix in Determination of Graphic Realization of Non-Increasing Positive Integer Sequence

A finite sequence of nonnegative integers is said to be graphical if there exists a finite simple graph, such that the degrees of its vertices corresponds to the terms of the sequence. Such a graph is often termed as a realization of the given degree sequence. In this paper we have proposed an algorithm that determines the realization of a given degree sequence by constructing the adjacency matrix from the given sequence. The input to the algorithm is a non-increasing sequence of positive integers. The output of the algorithm is the decision (graphic or non-graphic), along with the adjacency matrix, provided the sequence is graphical.

Comparative Analysis of Radial Basis Functions with SAR Images in Artificial Neural Network

Radial Basis Functions (RBFs) is used to optimize many mathematical computations. In this paper we have used Gaussian RBF (GRBF), Multi-Quadratic RBF (MQ-RBF), Inverse-Multi-Quadratic RBF (IMQRBF) and q-Gaussian RBF (q-GRBF) to approximate singular values of SAR (Synthetic Aperture Radar) color images. Simulations, mathematical comparisons show that q-Gaussian RBF gives better approximation with respect to the other RBF methods in Artificial Neural Network.

Eigen Value and It’s Comparison with Different RBF Methods by Using MATLAB

Neural network is being used in various research areas in recent time. In this paper we have introduced Radial Basis Function (RBF) of neural network for the analysis of Eigen value. Eigen value is the characteristic value of any given system. We have incorporated various radial basis functions such as Gaussian RBF, Multi-Quadratic RBF and Inverse-Multi-Quadratic RBF in matrix for the calculation of Eigen value. Comparative analysis and simulation results show that Gaussian RBF gives better result compared to the other relevant radial basis functions.

Plateau limit-based tri-histogram equalisation for image enhancement

An adaptive plateau limit-based histogram equalisation algorithm is suggested to enhance digital images. Histogram of the image is clipped with a plateau limit to avoid over enhancement. The plateau limit is derived from the average of the mean and the median intensity values to offer the improved enhancement. Clipped histogram is subdivided into three parts, using histogram subdivision limit parameters that are calculated on the basis of the standard deviation of the image. Histogram of individual sub-image is equalised independently and then combined into a single enhanced image. Experimental results demonstrate that the proposed plateau limit-based tri-histogram equalisation algorithm enhances the image quality. Compared with the other traditional plateau and non-plateau limit-based histogram equalisation algorithms, quantitative and visual quality assessments effectively validate the superiority of the proposed algorithm.

A Cycle Detection-Based Efficient Approach for Constructing Spanning Trees Directly from Nonregular Graphic Sequences

Realization of graphic sequences and finding the spanning tree of a graph are two popular problems of combinatorial optimization. A simple graph that realizes a given nonnegative integer sequence is often termed as a realization of the given sequence. In this paper, we have proposed a method for obtaining a spanning tree directly from a degree sequence by applying cycle detection algorithm, provided the degree sequence is graphic and nonregular. The proposed method is a two-step process. First, we apply an algorithm to check whether the input sequence is realizable through the construction of an adjacency matrix corresponding to the degree sequence. Then we apply the cycle detection algorithm separately to generate the spanning tree from it.

An Efficient Approach for Constructing Spanning Trees by Applying BFS and DFS Algorithm Directly on Non-regular Graphic Sequences

Realization of graphic sequences and finding the spanning tree of a graph are two popular problems of combinatorial optimization. A simple graph that realizes a given non-negative integer sequence is often termed as a realization of the given sequence. In this paper we have proposed a method for obtaining a spanning tree directly from a degree sequence by applying BFS and DFS algorithm separately, provided the degree sequence is graphic and non-regular. The proposed method is a two step process. First we apply an algorithm to check whether the input sequence is realizable through the construction of the adjacency matrix corresponding to the degree sequence. Then we apply the BFS and DFS algorithm separately to generate the spanning tree from it.

An Efficient Way to Determine the Chromatic Number of a Graph Directly from its Input Realizable Sequence

Spectral graph theory is a popular topic in modern day applied mathematics. Spectral graph theoretic techniques are widely used to extract a large variety of information about different properties of a graph from its adjacency matrix. A well known physical property of a graph is its chromatic number. In this paper, we have proposed an efficient approach to determine chromatic number of a graph directly from a realizable sequence. The method involves construction of adjacency matrix corresponding to an input sequence followed by calculation of eigen values to determine the bounds of chromatic number and consequently its chromatic number.

Generating spanning tree of non-regular graphic sequences through a variant of Prim's algorithm

Determining graphic degree sequences and finding the spanning tree of a graph are two popular problems of combinatorial optimization. A simple graph that realizes such a degree sequence is often termed as a realization of the given sequence. In this paper we have proposed a method for generating a spanning tree from a degree sequence, provided the degree sequence is graphic and non-regular. The proposed method first constructs the adjacency matrix corresponding to the degree sequence and then applies a modified version of Prims algorithm to generate the spanning tree from it.

Comparative Analysis of Image Deblurring with Radial Basis Functions in Artificial Neural Network

Radial basis functions are used in many fields of mathematics and image analysis. In this paper, we have used linear RBF, cubic RBF, multi-quadratic RBF, inverse multi-quadratic RBF and Gaussian RBF for the reconstruction of blurred images. Simulations and mathematical comparisons show that Gaussian RBF gives better result with respect to the other RBF methods for images reconstruction in artificial neural network.