This article introduces two Swarm intelligent Algorithms, a group search optimizer (GSO) and an Artificial Fish Swarm Algorithm (AFSA). A single intelligent Algorithm always has both merits in its specific formulation and deficiencies due to its inherent limitations. Therefore, we propose a mixture of these Algorithms to create a new hybrid optimization Algorithm known as the group search-Artificial Fish Swarm Algorithm (GS-AFSA). This Algorithm has been applied to three different discrete truss optimization problems. The optimization results are compared with those obtained using the standard GSO, the AFSA and the quick group search optimizer (QGSO). The proposed GS-AFSA eliminated the shortcomings of GSO regarding falling into the local optimum by taking advantage of AFSA’s stable convergence characteristics and achieving a better convergence rate and convergence accuracy than the GSO and the AFSA. Furthermore, the GS-AFSA has a superior convergence accuracy compared to the QGSO, all while solving a complicated structural optimization problem containing numerous design variables.

Groundwater modeling is essential in aquifer management and planning. Determination of hydraulic parameters in aquifer plays a key role in groundwater modeling, therefore choosing a suitable method for determination these parameters is very important. So far, various methods have been developed to estimate hydraulic parameters of aquifers using in situ pump test measurments. In this research, Artificial Fish Swarm Algorithm (AFSA) was evaluated for estimation of the hydraulic conductivity and storage coefficient parameters in three confined aquifers, using graphic method and Genetic Algorithm (GA). AFSA is one of the Algorithms inspired both from the nature and Swarm intelligence Algorithms. The results obtained by AFSA, graphic method and GA were compared and it was found that the AFSA similar to GA is a proper method for estimation of aquifer hydraulic coefficients and it has a better performace as compared to the graphic method. As, AFSA is not sensitive to initial values of decision variables, it could be useful for estimation parameters of aquifers in which geological characteristics are unknown.

Increasing population and food demand, disproportionate cultivation and annual production of various agricultural products with market needs and low productivity of the agricultural sector and the loss of water and soil resources have made it necessary to determine and implement the country's optimal cropping pattern. In this study, due to the limitations and problems of classical methods in order to reduce processing time and improve the quality of solutions, the Multi-Objective Chaotic Particle Swarm Optimization was used to determine the optimal cultivation pattern of Sistan plain in optimal conditions and deficit irrigation. The results of the Multi-Objective Chaotic Particle Swarm Optimization for the dominant cultures in the region showed that the current cropping pattern of the region is not optimal and with the implementation of the proposed model, the profit per unit area under cultivation will increase. The results of application of deficit irrigation during different growing periods of wheat, barley, alfalfa, sorghum, watermelon and grapes showed that applying deficit irrigation in this plain is not a good strategy and therefore only a full irrigation strategy is recommended. The results of sensitivity analysis of the model showed that at low prices, farmers reaction is less and at higher prices more reaction to price changes and with increasing prices, the program efficiency is lower.

The drought phenomenon is one of the natural disasters, which may occur in all climatic zones and cause serious damages to the environment and human life. So, forecasting this phenomenon may have significant impact on the water resources management and reduce its destructive effects as much as possible. In this study, the multivariate standardized precipitation index (MSPI) was utilized to compute the drought characteristics in the Lighvanchai basin and then the Artificial neural network (ANN) was used to forecast the MSPI values. In order to train the ANN and estimate its optimized weights, the particle Swarm optimization (PSO) Algorithm was applied and its performance was compared with the backpropagation (BP) Algorithm. In this context, different scenarios and structures were considered and then the goodness-of-fit tests were utilized for evaluating the accuracy of them. The results demonstrated that the ANN-PSO model had a better performance than the ANN-BP model for drought forecasting.

Expectations about earning have significant effects on managers and investors’ decisions. Today, one of the measures that are taken in to consideration as an indicator of companies ‘profitability is the concept of earning per share. Also earning per share has major effects on stock price of companies. Hence, fore casting earning per share is of great importance for both investors and managers. The aim of this study is to model earning per share forecast of listed companies in Tehran Stock Exchange (TSE) by using the combination of Artificial neural networks and particle Swarm optimization Algorithm based on univariate and multivariate models. To do this, the data of114 companies among the existing listed ones in Tehran Stock Exchange was usedduring1380-1389(2001-2010).The results showed that univariate model with 78.5% accuracy and multivariate models with 91.7% accuracy, forecast earning per share.

Discussion about earthquake to reduce its casualties and damages is very important, especially in the Seismicity area like Iran that the occurrence of this natural phenomenon is seen annually. Anomalies detection before earthquake is an important role for earthquake prediction. Ionosphere changes that recognition by remote measurements (such as using global positioning system) are known as earthquake ionospheric precursors. In this study two data sets from the ionospheric total electron content (TEC) derived from the GPS data processing by Bernese software used for two studies, Ahar earthquake, East Azerbaijan (2012/08/11) and Kaki earthquake Bushehr (2013/4/9) and the results were compared with data from global stations. Because of the nonlinear behavior TEC changes in order to predict and detect changes of that, integration of neural network (using multilayer Perceptron (MLP)) with particle Swarm optimization Algorithm (PSO) is used. Particle Swarm optimization Algorithm performance based on the population and can be effective on improving weight estimated by Artificial neural network. By analyzing the causes of ionospheric anomalies such as the geomagnetic field and solar activity and remove them from the process, the results indicate that some of this anomalies caused by the earthquake and using intelligent Algorithms could be useful for the prediction of nonlinear time series. The output of the integration of Artificial neural network and PSO shows that both positive and negative anomalies occur, the anomalies before earthquakes often occur close to the epicenter and in 3 days before the Ahar earthquake and 2 to 6 days before the Kaki earthquake are visible.

Background: Prediction of future climate change is based on output of global climate models (GCMs). However, because of coarse spatial resolution of GCMs (tens to hundreds of kilometers), there is a need to convert GCM outputs into local meteorological and hydrological variables using a downscaling approach. Downscaling technique is a method of converting the coarse spatial resolution of GCM outputs at the regional or local scale. This study proposed a novel hybrid downscaling method based on Artificial neural network (ANN) and particle Swarm optimization (PSO) Algorithm. Materials and Methods: Downscaling technique is implemented to assess the effect of climate change on a basin. The current study aims to explore a hybrid model to downscale monthly precipitation in the Minab basin, Iran. The model was proposed to downscale large scale climatic variables, based on a feed-forward ANN optimized by PSO. This optimization Algorithm was employed to decide the initial weights of the neural network. The National Center for Environmental Prediction and National Centre for Atmospheric Research reanalysis datasets were utilized to select the potential predictors. The performance of the Artificial neural network-particle Swarm optimization model was compared with Artificial neural network model which is trained by Levenberg– Marquardt (LM) Algorithm. The reliability of the models were evaluated by using root mean square error and coefficient of determination (R2). Results: The results showed the robustness and reliability of the ANN-PSO model for predicting the precipitation which it performed better than the ANN-LM. It was concluded that ANN-PSO is a better technique for statistically downscaling GCM outputs to monthly precipitation than ANN-LM. Discussion and Conclusions: This method can be employed effectively to downscale large-scale climatic variables to monthly precipitation at station scale.

In this paper, we propose a novel Algorithm to enhance the noisy speech in the framework of dual-channel speech enhancement. The new method is a hybrid optimization Algorithm, which employs the combination of the conventional q-PSO and the shuffled subSwarms particle optimization (SSPSO) technique. It is known that the q-PSO Algorithm has better optimization performance than standard PSO Algorithm, when dealing with some simple benchmark functions. To improve further the performance of the conventional PSO, the SSPSO Algorithm has been suggested to increase the diversity of particles in the Swarm. The proposed speech enhancement method, called q-SSPSO, is a hybrid technique, which incorporates both q-PSO and SSPSO, with the goal of exploiting the advantages of both Algorithms. It is shown that the new q-SSPSO Algorithm is quite effective in achieving global convergence for adaptive filters, which results in a better suppression of noise from input speech signal. Experimental results indicate that the new Algorithm outperforms the standard PSO, q-PSO, and SSPSO in a sense of convergence rate and SNR-improvement.