Evolutionary artificial neural networks (EANNs) refer to a special class of artificial neural networks (ANNs) in which evolution is another fundamental form of adaptation in addition to learning. Evolutionary algorithms are used to adapt the connection weights, network architecture and learning algorithms according to the problem environment. Even though evolutionary algorithms are well known as efficient global search algorithms, very often they miss the best local solutions in the complex solution space. In this paper, we propose a hybrid meta-heuristic learning approach combining evolutionary learning and local search methods (using 1st and 2nd order error information) to improve the learning and faster convergence obtained using a direct evolutionary approach. The proposed technique is tested on three different chaotic time series and the test results are compared with some popular neuro-fuzzy systems and a recently developed cutting angle method of global optimization. Empirical results reveal that the proposed technique is efficient in spite of the computational complexity.
Several adaptation techniques have been investigated to optimize fuzzy inference systems. Neural network learning algorithms have been used to determine the parameters of fuzzy inference system. Such models are often called as integrated neuro-fuzzy models. In an integrated neuro-fuzzy model there is no guarantee that the neural network learning algorithm converges and the tuning of fuzzy inference system will be successful. Success of evolutionary search procedures for optimization of fuzzy inference system is well proven and established in many application areas. In this paper, we will explore how the optimization of fuzzy inference systems could be further improved using a meta-heuristic approach combining neural network learning and evolutionary computation. The proposed technique could be considered as a methodology to integrate neural networks, fuzzy inference systems and evolutionary search procedures. We present the theoretical frameworks and some experimental results to demonstrate the efficiency of the proposed technique.
Normally a decision support system is build to solve problem where multi-criteria decisions are involved. The knowledge base is the vital part of the decision support containing the information or data that is used in decision-making process. This is the field where engineers and scientists have applied several intelligent techniques and heuristics to obtain optimal decisions from imprecise information. In this paper, we present a hybrid neuro-genetic learning approach for the adaptation a Mamdani fuzzy inference system for the Tactical Air Combat Decision Support System (TACDSS). Some simulation results demonstrating the difference of the learning techniques and are also provided.
The rapid e-commerce growth has made both business community and customers face a new situation. Due to intense competition on one hand and the customer's option to choose from several alternatives business community has realized the necessity of intelligent marketing strategies and relationship management. Web usage mining attempts to discover useful knowledge from the secondary data obtained from the interactions of the users with the Web. Web usage mining has become very critical for effective Web site management, creating adaptive Web sites, business and support services, personalization, network traffic flow analysis and so on. In this paper, we present the important concepts of Web usage mining and its various practical applications. We further present a novel approach 'intelligent-miner' (i-Miner) to optimize the concurrent architecture of a fuzzy clustering algorithm (to discover web data clusters) and a fuzzy inference system to analyze the Web site visitor trends. A hybrid evolutionary fuzzy clustering algorithm is proposed in this paper to optimally segregate similar user interests. The clustered data is then used to analyze the trends using a Takagi-Sugeno fuzzy inference system learned using a combination of evolutionary algorithm and neural network learning. Proposed approach is compared with self-organizing maps (to discover patterns) and several function approximation techniques like neural networks, linear genetic programming and Takagi-Sugeno fuzzy inference system (to analyze the clusters). The results are graphically illustrated and the practical significance is discussed in detail. Empirical results clearly show that the proposed Web usage-mining framework is efficient.
Decision-making is a process of choosing among alternative courses of action for solving complicated problems where multi-criteria objectives are involved. The past few years have witnessed a growing recognition of Soft Computing technologies that underlie the conception, design and utilization of intelligent systems. Several works have been done where engineers and scientists have applied intelligent techniques and heuristics to obtain optimal decisions from imprecise information. In this paper, we present a concurrent fuzzy-neural network approach combining unsupervised and supervised learning techniques to develop the Tactical Air Combat Decision Support System (TACDSS). Experiment results clearly demonstrate the efficiency of the proposed technique.
The phylogenetic tree construction is to infer the evolutionary relationship between species from the experimental data. However, the experimental data are often imperfect and conflicting each others. Therefore, it is important to extract the motif from the imperfect data. The largest compatible subset problem is that, given a set of experimental data, we want to discard the minimum such that the remaining is compatible. The largest compatible subset problem can be viewed as the vertex cover problem in the graph theory that has been proven to be NP-hard. In this paper, we propose a hybrid Evolutionary Computing (EC) method for this problem. The proposed method combines the EC approach and the algorithmic approach for special structured graphs. As a result, the complexity of the problem is dramatically reduced. Experiments were performed on randomly generated graphs with different edge densities. The vertex covers produced by the proposed method were then compared to the vertex covers produced by a 2-approximation algorithm. The experimental results showed that the proposed method consistently outperformed a classical 2- approximation algorithm. Furthermore, a significant improvement was found when the graph density was small.
In this paper, we present MLEANN (Meta-Learning Evolutionary Artificial Neural Network), an automatic computational framework for the adaptive optimization of artificial neural networks wherein the neural network architecture, activation function, connection weights; learning algorithm and its parameters are adapted according to the problem. We explored the performance of MLEANN and conventionally designed artificial neural networks for function approximation problems. To evaluate the comparative performance, we used three different well-known chaotic time series. We also present the state of the art popular neural network learning algorithms and some experimentation results related to convergence speed and generalization performance. We explored the performance of backpropagation algorithm; conjugate gradient algorithm, quasi-Newton algorithm and Levenberg-Marquardt algorithm for the three chaotic time series. Performances of the different learning algorithms were evaluated when the activation functions and architecture were changed. We further present the theoretical background, algorithm, design strategy and further demonstrate how effective and inevitable is the proposed MLEANN framework to design a neural network, which is smaller, faster and with a better generalization performance.
The purpose of this paper is to point to the usefulness of applying a linear mathematical formulation of fuzzy multiple criteria objective decision methods in organising business activities. In this respect fuzzy parameters of linear programming are modelled by preference-based membership functions. This paper begins with an introduction and some related research followed by some fundamentals of fuzzy set theory and technical concepts of fuzzy multiple objective decision models. Further a real case study of a manufacturing plant and the implementation of the proposed technique is presented. Empirical results clearly show the superiority of the fuzzy technique in optimising individual objective functions when compared to non-fuzzy approach. Furthermore, for the problem considered, the optimal solution helps to infer that by incorporating fuzziness in a linear programming model either in constraints, or both in objective functions and constraints, provides a similar (or even better) level of satisfaction for obtained results compared to non-fuzzy linear programming.
The use of intelligent systems for stock market predictions has been widely established. In this paper, we investigate how the seemingly chaotic behavior of stock markets could be well represented using several connectionist paradigms and soft computing techniques. To demonstrate the different techniques, we considered Nasdaq-100 index of Nasdaq Stock MarketS and the S&P CNX NIFTY stock index. We analyzed 7 year's Nasdaq 100 main index values and 4 year's NIFTY index values. This paper investigates the development of a reliable and efficient technique to model the seemingly chaotic behavior of stock markets. We considered an artificial neural network trained using Levenberg-Marquardt algorithm, Support Vector Machine (SVM), Takagi-Sugeno neuro-fuzzy model and a Difference Boosting Neural Network (DBNN). This paper briefly explains how the different connectionist paradigms could be formulated using different learning methods and then investigates whether they can provide the required level of performance, which are sufficiently good and robust so as to provide a reliable forecast model for stock market indices. Experiment results reveal that all the connectionist paradigms considered could represent the stock indices behavior very accurately.
The aim of our research was to apply well-known data mining techniques (such as linear neural networks, multi-layered perceptrons, probabilistic neural networks, classification and regression trees, support vector machines and finally a hybrid decision tree neural network approach) to the problem of predicting the quality of service in call centers; based on the performance data actually collected in a call center of a large insurance company. Our aim was two-fold. First, to compare the performance of models built using the above-mentioned techniques and, second, to analyze the characteristics of the input sensitivity in order to better understand the relationship between the perform-ance evaluation process and the actual performance and in this way help improve the performance of call centers. In this paper we summarize our findings.