Satchidananda Dehuri

A comprehensive survey on functional link neural networks and an adaptive PSO–BP learning for CFLNN

Functional link neural network (FLNN) is a class of higher order neural networks (HONs) and have gained extensive popularity in recent years. FLNN have been successfully used in many applications such as system identification, channel equalization, short-term electric-load forecasting, and some of the tasks of data mining. The goals of this paper are to: (1) provide readers who are novice to this area with a basis of understanding FLNN and a comprehensive survey, while offering specialists an updated picture of the depth and breadth of the theory and applications; (2) present a new hybrid learning scheme for Chebyshev functional link neural network (CFLNN); and (3) suggest possible remedies and guidelines for practical applications in data mining. We then validate the proposed learning scheme for CFLNN in classification by an extensive simulation study. Comprehensive performance comparisons with a number of existing methods are presented.

An improved swarm optimized functional link artificial neural network (ISO-FLANN) for classification

Highlights? A novel HONs for classification task of data mining. ? A novel improved PSO for training FLANN (ISO-FLANN). ? A new complex medical domain dataset is introduced for validating the method. Multilayer perceptron (MLP) (trained with back propagation learning algorithm) takes large computational time. The complexity of the network increases as the number of layers and number of nodes in layers increases. Further, it is also very difficult to decide the number of nodes in a layer and the number of layers in the network required for solving a problem a priori. In this paper an improved particle swarm optimization (IPSO) is used to train the functional link artificial neural network (FLANN) for classification and we name it ISO-FLANN. In contrast to MLP, FLANN has less architectural complexity, easier to train, and more insight may be gained in the classification problem. Further, we rely on global classification capabilities of IPSO to explore the entire weight space, which is plagued by a host of local optima. Using the functionally expanded features; FLANN overcomes the non-linear nature of problems. We believe that the combined efforts of FLANN and IPSO (IPSO + FLANN=ISO-FLANN) by harnessing their best attributes can give rise to a robust classifier. An extensive simulation study is presented to show the effectiveness of proposed classifier. Results are compared with MLP, support vector machine(SVM) with radial basis function (RBF) kernel, FLANN with gradiend descent learning and fuzzy swarm net (FSN).

Application of elitist multi-objective genetic algorithm for classification rule generation

We present an elitist multi-objective genetic algorithm (EMOGA) for mining classification rules from large databases. We emphasize on predictive accuracy, comprehensibility and interestingness of the rules. However, predictive accuracy, comprehensibility and interestingness of the rules often conflict with each other. This makes it a multi-objective optimization problem that is very difficult to solve efficiently. We have proposed a multi-objective genetic algorithm with a hybrid crossover operator for optimizing these objectives simultaneously. We have compared our rule discovery procedure with simple genetic algorithm with a weighted sum of all these objectives. The experimental result confirms that our rule discovery algorithm has a clear edge over simple genetic algorithm.

Predictive and comprehensible rule discovery using a multi-objective genetic algorithm

We present a multi-objective genetic algorithm for mining highly predictive and comprehensible classification rules from large databases. We emphasize predictive accuracy and comprehensibility of the rules. However, accuracy and comprehensibility of the rules often conflict with each other. This makes it an optimization problem that is very difficult to solve efficiently. We have proposed a multi-objective evolutionary algorithm called improved niched Pareto genetic algorithm (INPGA) for this purpose. We have compared the rule generation by INPGA with that by simple genetic algorithm (SGA) and basic niched Pareto genetic algorithm (NPGA). The experimental result confirms that our rule generation has a clear edge over SGA and NPGA.

Evolutionarily optimized features in functional link neural network for classification

In this paper, an adequate set of input features is selected for functional expansion genetically for the purpose of solving the problem of classification in data mining using functional link neural network. The proposed method named as HFLNN aims to choose an optimal subset of input features by eliminating features with little or no predictive information and designs a more compact classifier. With an adequate set of basis functions, HFLNN overcomes the non-linearity of problems, which is a common phenomenon in single layer neural networks. The properties like simplicity of the architecture (i.e., no hidden layer) and the low computational complexity of the network (i.e., less number of weights to be learned) encourage us to use it in classification task of data mining. We present a mathematical analysis of the stability and convergence of the proposed method. Further the issue of statistical tests for comparison of algorithms on multiple datasets, which is even more essential in data mining studies, has been all but ignored. In this paper, we recommend a set of simple, yet safe, robust and non-parametric tests for statistical comparisons of the HFLNN with functional link neural network (FLNN) and radial basis function network (RBFN) classifiers over multiple datasets by an extensive set of simulation studies.

Multi-Objective Evolutionary Algorithms for Knowledge Discovery from Databases

Data Mining (DM) is the most commonly used name to describe such computational analysis of data and the results obtained must conform to several objectives such as accuracy, comprehensibility, interest for the user etc. Though there are many sophisticated techniques developed by various interdisciplinary fields only a few of them are well equipped to handle these multi-criteria issues of DM. Therefore, the DM issues have attracted considerable attention of the well established multiobjective genetic algorithm community to optimize the objectives in the tasks of DM. The present volume provides a collection of seven articles containing new and high quality research results demonstrating the significance of Multi-objective Evolutionary Algorithms (MOEA) for data mining tasks in Knowledge Discovery from Databases (KDD). These articles are written by leading experts around the world. It is shown how the different MOEAs can be utilized, both in individual and integrated manner, in various ways to efficiently mine data from large databases.

A Novel Particle Swarm Optimization Algorithm for Multi-Objective Combinatorial Optimization Problem

The Combinatorial problems are real world decision making problem with discrete and disjunctive choices. When these decision making problems involve more than one conflicting objective and constraint, it turns the polynomial time problem into NP-hard. Thus, the straight forward approaches to solve multi-objective problems would not give an optimal solution. In such case evolutionary based meta-heuristic approaches are found suitable. In this paper, a novel particle swarm optimization based meta-heuristic algorithm is presented to solve multi-objective combinatorial optimization problems. Here a mapping method is considered to convert the binary and discrete values (solution encoded as particles) to a continuous domain and update it using the velocity and position update equation of particle swarm optimization to find new set of solutions in continuous domain and demap it to discrete values. The performance of the algorithm is compared with other evolutionary strategy like SPEA and NSGA-II on pseudo-Boolean discrete problems and multi-objective 0/1 knapsack problem. The experimental results confirmed the better performance of combinatorial particle swarm optimization algorithm.

Genetic Feature Selection for Optimal Functional Link Artificial Neural Network in Classification

This paper proposed a hybrid functional link artificial neural network (HFLANN) embedded with an optimization of input features for solving the problem of classification in data mining. The aim of the proposed approach is to choose an optimal subset of input features using genetic algorithm by eliminating features with little or no predictive information and increase the comprehensibility of resulting HFLANN. Using the functionally expanded selected features, HFLANN overcomes the non-linearity nature of problems, which is commonly encountered in single layer neural networks. An extensive simulation studies has been carried out to illustrate the effectiveness of this method over to its rival functional link artificial neural network (FLANN) and radial basis function (RBF) neural network.

Multi-objective Classification Rule Mining Using Gene Expression Programming

In this paper, the classification rule-mining problem is considered as a multi-objective problem rather than a uni-objective one. Metrics like predictive accuracy and comprehensibility, used for evaluating a rule can be thought of as different criteria of this problem. Predictive accuracy measures the accuracy of the rules extracted from the dataset where as, comprehensibility is measured by the number of attributes involved in the rule and tries to quantify the understandability of the rule. Using these measures as the objectives of rule mining problem, this paper uses gene expression programming to extract some useful and understandable rule. The discovered rule/knowledge is expressed in the form of IF-THEN high-level statement. Gene expression programming recently been introduced as one of the components of evolutionary algorithms and its attributes like simple linear representation and easy to implement, motivate us to use for mining classification rule with multiple objectives. It is often criticized when applied to classification rule mining with multiple objectives, because of the amount of computational resources it requires. However, we believe that it has a lot of potential to perform global search by exploring a large space. The rule antecedent part may contain different combinations of predictor attributes while the consequent part contains only the goal attribute. The searching process is guided by a fitness function considering both predictive accuracy and comprehensibility. Experiments with several benchmark datasets have generated rules for each class with acceptable predictive accuracy and comprehensibility.

Survey: Multi-criterion Pareto based particle swarm optimized polynomial neural network for classification: A review and state-of-the-art

In this paper, we proposed a multi-objective Pareto based particle swarm optimization (MOPPSO) to minimize the architectural complexity and maximize the classification accuracy of a polynomial neural network (PNN). To support this, we provide an extensive review of the literature on multi-objective particle swarm optimization and PNN. Classification using PNN can be considered as a multi-objective problem rather than as a single objective one. Measures like classification accuracy and architectural complexity used for evaluating PNN based classification can be thought of as two different conflicting criterions. Using these two metrics as the criteria of classification problem, the proposed MOPPSO technique attempts to find out a set of non-dominated solutions with less complex PNN architecture and high classification accuracy. An extensive experimental study has been carried out to compare the importance and effectiveness of the proposed method with the chosen state-of-the-art multi-objective particle swarm optimization (MOPSO) algorithm using several benchmark datasets. A comprehensive bibliography is included for further enhancement of this area.