Learning-based techniques could be an alternative approach to solve Dynamic Distributed Constraint Optimization Problems (DDCOPs) and are computationally cheaper than sequential DCOP solvers. This paper, proposes a learning-based solution to solve DDCOPs in which the environment is stochastic due to the presence of multiple agents. In our approach the problem is modelled as a multi-agent Markov Decision Process and then a learning automaton, which is a relatively simple method and requires less qualitative data, is employed to learn how to assign values to variables. The proposed method considers two very important issues namely time step dependency and uncertainty about future events upon which we allocate values to variables. Experimental results reveal that the employed method converges and satisfies the constraints of the optimization problems in comparison to the well-known methods.

Human falling may be due to a violent act, a heart attack or perhaps physical illness. Every year, many old people are being treated for injuries or even die in hospitals which caused by falling. From there, there is a long-standing need for a timely and inexpensive system that automatically identifying a falling person and then alert, which reduces the death rate and increases the likelihood of survival. Due to the low accuracy and a lot of faults in the recognition of the systems released in past years, this paper presented human falling detection by using neuro-fuzzy models and ensemble learning algorithms which presented to solve these problems. This showed the influence of the ensemble learning on performance of neuro-fuzzy models. However, it should be noted that feature selection and extraction methods in processing the dataset have their own impact. In this case, five kinds of feature selection/extraction algorithms are used. Five neuro-fuzzy models are used in this research: normalized radial basis function (NRBF) network, radial basis function (RBF) network, adaptive neuro-fuzzy inference system (ANFIS), local linear model trees (LOLIMOT) and generalized regression neural networks (GRNN). LOLIMOT model, by using correlation based features selection algorithm, reached the highest answer with the accuracy of 0.796. The results of these models are entered into the two ensemble learning algorithms, single majority vote and weighted majority vote, which weighted majority vote algorithm reached an accuracy of 0.87917 by using principal component analysis algorithm, and was the highest answer among of all the models used in this paper.

An inherent difficulty in dynamic distributed constraint optimization problems (dynamic DCOP) is the uncertainty of future events when making an assignment at the current time. This dependency is not well addressed in the research community. This paper proposes a reinforcement-learning-based solver for dynamic distributed constraint optimization. We show that reinforcement learning techniques are an alternative approach to solve the given problem over time and are computationally more efficient than sequential DCOP solvers. We also use the novel heuristic to obtain the correct results and describe a formalism that has been adopted to model dynamic DCOPs with cooperative agents. We evaluate this approach in dynamic weapon target assignment (dynamic WTA) problem, via experimental results. We observe that the system dynamic WTA problem remains a safe zone after convergence while satisfying the constraints. Moreover, in the experiment we have implemented the agents that finally converge to the correct assignment.

Nowadays, a significant amount of studies are devoted to discovering important nodes in graph data. Social networks as graph data have attracted a lot of attention. There are various purposes for discovering the important nodes in social networks such as finding the leaders in them, i.e. the users who play an important role in promoting advertising, etc. Different criteria have been proposed in discovering important nodes in graph data. Measuring a node’s importance by a single criterion may be inefficient due to the variety of graph structures. Recently, a combination of criteria has been used in the discovery of important nodes. In this paper, we propose a system for the Discovery of Important Nodes in social networks using Genetic Algorithms (DINGA). In our proposed system, important nodes in social networks are discovered by employing a combination of eight informative criteria and their intelligent weighting. We compare our results with a manually weighted method, that uses random weightings for each criterion, in four real networks. Our method shows an average of 22% improvement in the accuracy of important nodes discovery.

A large number of real-world issues are among difficult and multi-objective problems. Recently, it has been recognised that the evolutionary algorithms optimise well these types of problems. This paper proposes a novel multi-objective search algorithm that is called the Spacing Multi-Objective Genetic Algorithm (Spacing-MOGA). The innovation of the proposed Spacing-MOGA lies in a new survival selection algorithm called Spacing Distance. This research eliminates some of the disadvantages of other algorithms such as the Non-dominated Sorting Genetic Algorithm II (NSGAII). The proposed Spacing-MOGA is applied to five test benchmark functions and also to the design of I-Beam. Then, the results are compared with other algorithms such as NSGAII, Adaptive Weighted Particle Swarm Optimisation (AWPSO), and Non-dominated Sorting Particle Swarm Optimiser (NSPSO) based on the test metrics: Hypervolume, Spacing, Spread, and Generational Distance. Furthermore, for further demonstration of the ability of the proposed Spacing-MOGA, the experimental results are evaluated by the t-test.

A concept of defining images based on its own approximate ones is proposed here, which is called 'Self-ception'. In this regard, an algorithm is proposed to implement the self-ception for images, which we call it 'Image Self-ception' since we use it for images. We can control the accuracy of this self-ception representation by deciding how many segments or regions we want to use for the representation. Some self-ception images are included in the paper. The video versions of the proposed image self-ception algorithm in action are shown in a YouTube channel (find it by Googling image self-ception).

Distributed database systems provide a new data processing and storage technology for decentralized organizations of today. Query optimization, the process to generate an optimal execution plan for the posed query, is more challenging in such systems due to the huge search space of alternative plans incurred by distribution. As finding an optimal execution plan is computationally intractable, using stochastic-based algorithms has drawn the attention of most researchers. In this paper, for the first time, a multi-colony ant algorithm is proposed for optimizing join queries in a distributed environment where relations can be replicated but not fragmented. In the proposed algorithm, four types of ants collaborate to create an execution plan. Hence, there are four ant colonies in each iteration. Each type of ant makes an important decision to find the optimal plan. In order to evaluate the quality of the generated plan, two cost models are used—one based on the total time and the other on the response time. The proposed algorithm is compared with two previous genetic-based algorithms on chain, tree and cyclic queries. The experimental results show that the proposed algorithm saves up to about 80 % of optimization time with no significant difference in the quality of generated plans compared with the best existing genetic-based algorithm.

In this paper, image segmentation of graylevel images is performed by mult ilevel thresholding.The optimal thresholds for this purpose are found by maximizing the between-class variance (the Otsu's criterion).The optimization (maximizat ion) is conducted by a novel nature-inspired search algorith m, which is called Galaxy-based Search Algorith m or Gb SA.The p roposed Gb SA is a metaheuristic for continuous optimizat ion.It resemb les the spiral arms of some galaxies to search for the optimal thresholds.The Gb SA also uses a modified Hill Climbing algorith m as a local search.The GbSA also utilizes chaos for improving its performance, which is imp lemented by the logistic map.Experimental results show that the Gb SA finds the optimal or very near optimal thresholds in all runs of the algorithm.

In this paper, the K-means algorithm for data clustering is improved by the swarm-based nature-inspired optimisation algorithm, the intelligent water drops (IWD) algorithm. The K-means algorithm is an iterative algorithm in which the number of clusters is given in advance. Although the K-means is fast to converge, it is sensitive to the initial conditions. As a result, it is often trapped in local optimums. The IWD algorithm, which mimics the actions and reactions between natural water drops in real rivers, is modified to implicitly embed in itself the main processes of the K-means algorithm. The modified algorithm called IWD-KM is tested with several well-known datasets for clustering, and its performance is compared with the K-means algorithm. The experimental results show the superiority of the proposed IWD-KM algorithm.

Numerical Computation is widely used in engineering problems. In this paper, it is shown that many Numerical Computation problems can be expressed by one or few artificial neurons. Then, the task of solving each of the problems is converted to the task of training the neurons in order to find the weights of the neurons. The weights of the neurons contain the solution to the problem at hand. As a result, to solve a Numerical Computation problem, there is no need to develop special algorithms for the problem. Experimental results demonstrate that this novel approach is successful in solving several different Numerical Computation problems and may pave the way to tackle other Numerical Computation problems by using only neural networks without developing specific algorithms

In this paper, a hybrid algorithm based on modified intelligent water drops algorithm and learning automata for solving Steiner tree problem is proposed. Since the Steiner tree problem is NP-hard, the aim of this paper is to design an algorithm to construct high quality Steiner trees in a short time which are suitable for real time multicast routing in networks. The global search and fast convergence ability of the intelligent water drops algorithm make it efficient to the problem. To achieve better results, we used learning automata for adjusting IWD parameters. IWD has several parameters. The appropriate selections of these parameters have large effects on the performance and convergence of the algorithm. Experimental results on the OR-library test cases show that the proposed algorithm outperforms traditional heuristic algorithms and other iteration based algorithms with faster convergence speed.

In this paper, the Intelligent Water Drops (IWD) algorithm is augmented with a mutation-based local search to find the optimal values of numerical functions. The proposed algorithm called the IWD-CO (IWD for continuous optimization) is tested with six different benchmark functions. The experimental results are satisfactory, which encourage further researches in this regard.

Emotion recognition plays an effective and important role in Human-Computer Interaction (HCI). Recently, various approaches to emotion recognition have been proposed in the literature, but they do not provide a powerful approach to recognize emotions from Partially Occluded Facial Images.In this paper, we propose a new method for Emotion Recognition from Facial Expression using Fuzzy Inference System (FIS). This novel method is even able to recognize emotions from Partially Occluded Facial Images. Moreover, this research describes new algorithms for facial feature extraction that demonstrate satisfactory performance and precision. In addition, one of the main factors that have an important influence on the final precision of fuzzy inference systems is the membership function parameters. Therefore, we use a Genetic Algorithm for parameter-tuning of the membership functions. Experimental results report an average precision rate of 93.96% for Emotion Recognition of six basic emotions, which is so promising. (C) 2011 Published by Elsevier Ltd.

In this paper, the newly introduced swarm-based optimisation algorithm called intelligent water drops (IWDs) algorithm is adjusted to optimise a modified Otsu’s criterion for automatic multilevel thresholding. The proposed algorithm simply called IWD-AMLT is tested with several grey-level images and its performance is assessed by the peak signal to noise ratio (PSNR) measure. The thresholded images obtained by the IWD-AMLT have high qualities according to the subjective judgement and the PSNR values.

In this paper, image segmentation of gray-level images is performed by multilevel thresholding. The optimal thresholds for this purpose are found by maximizing the between-class variance (the Otsu's criterion). The optimization is conducted by a newly-developed nature-inspired metaheuristic called "Galaxy-based Search Algorithm" or the GbSA. The proposed GbSA resembles the spiral arms of some galaxies to search for the optimal thresholds. The GbSA also uses a modified Hill Climbing algorithm as a local search. The experimental results show that the GbSA finds the optimal or very near optimal thresholds in all runs of the algorithm.

An adaptive hierarchical structure called “Binary Tree TASOM” (BTASOM) is proposed, which resembles a binary natural tree having nodes composed of Time Adaptive Self-Organizing Map (TASOM) networks. The standard TASOM is almost as slow as the standard SOM and has a fixed number of neurons. The BTASOM is proposed to make the TASOM fast and adaptive in the number of its neurons. The BTASOM is the first proposed hierarchical structure that uses a binary tree topology with TASOM networks. The number of levels of the BTASOM and the number of its nodes are adaptive to the accuracy demanded by the application through user-defined parameters. Two versions of the BTASOM are used here: the first version in which every node has only one neuron, and the second version in which every node has exactly two neurons. Both versions are tested with different distributions, stationary and nonstationary, for data representation. The experiments show that the BTASOM can work with both stationary and nonstationary environments while increasing the adaptability and speed of the standard TASOM. Several performance measures demonstrate the superiority of the proposed BTASOM in comparison with some other hierarchical SOM-based networks for clustering and input space approximation.

In this paper, the principal components analysis (PCA) is formulated as a continuous optimisation problem. Then, a novel metaheuristic inspired from nature is employed to explore the search space for the optimum solution to the PCA problem. The new metaheuristic is called 'galaxy-based search algorithm' or 'GbSA'. The GbSA imitates the spiral arm of spiral galaxies to search its surrounding. This spiral movement is enhanced by chaos to escape from local optimums. A local search algorithm is also utilised to adjust the solution obtained by the spiral movement of the GbSA. Experimental results demonstrate that the proposed GbSA for the PCA or GbSA-PCA is a promising tool for the PCA estimation.

— this paper proposed Iris Recognition based on covariance of discrete wavelet using Competitive Neural Network (LVQ). A set of Edge of Iris profiles are used to build a covariance matrix by discrete wavelet transform using Neural Network. It is found that this method for Iris Recognition design offers good class discriminacy. This method can discriminate noisy Image very well. Simulation results are very promising.

In this chapter we focus on three bio-inspired algorithms and their combinations with fuzzy rule based systems. Rule Based systems are widely being used in decision making, control systems and forecasting. In the real world, much of the knowledge is imprecise and ambiguous but fuzzy logic provides for systems better presentations of the knowledge, which is often expressed in terms of the natural language. Fuzzy rule based systems constitute an extension of classical Rule-Based Systems, because they deal with fuzzy rules instead of classical logic rules. Since bio-inspired optimization algorithms have been shown effective in improving the tuning the parameters and learning the Fuzzy Rule Base, our major objective is to represent the application of these algorithms in improving the Knowledge Based Systems with focus on Rule-Base Learning. We first introduce the Evolutionary Computation and Swarm Intelligence topics as a subfield of Computational Intelligence dealing with Combinatorial Optimization problems. Then, three following bio-inspired algorithms, i.e. Genetic Algorithms, Ant Colony Optimization, and Particle Swarm Optimization are explained and their application in improving the knowledge Based Systems are presented.

In this paper, a modified max-min ant system, called dynamic max-min ant system (DMAS) is proposed to solve the travelling salesman problem (TSP). The proposed algorithm updates the value of τmin, the lower bound of pheromone trails during its run. In addition, the used parameters for the DMAS are adjusted to improve the performance of the method. Furthermore, a local search based on 2-Opt is adjoined to the DMAS and the results are reported. Moreover, the DMAS is applied to some standard TSPs and its results are compared to some previous works. Results show that the proposed method outperforms several other well-known population-based methods in many cases. Also, in some standard problems, the proposed method improves the shortest known tour lengths. Moreover, experiments show that the standard deviation of tour lengths that are found by DMAS is very small, which exhibits the stability of the proposed algorithm.