evolutionary algorithms

Nowadays, machine learning models are able to make good predictions based on pattern extraction between data. In this study, a neural-fuzzy network (ANFIS) was used to predict the inflow to the reservoirs of a dam namely, the Mahabad dam located in the northwestern part of Iran. A new Harris Hawk (HHO) optimization algorithm was also used to improve the ANFIS (HHO-ANFIS) structure. Monthly precipitation and temperature and inlet flow data to the reservoir one to three months ago were used as input parameters as 6 different input patterns. About 70% of the data was used for training and 30% to test the models. The results showed that the ANFIS model has good accuracy in training data although, for test data, its accuracy was greatly reduced. The development of the HHO-ANFIS model improved the accuracy of the prediction. The patterns with all input parameters had the highest prediction accuracy. In this pattern, values ​​of Root Mean Square Error (RMSE), Mean Absolute Error (MAE), and Nash Sutcliffe Efficiency coefficient (NSE) for test data were 3.9 MCM, 2.41 MCM, and 0.86, respectively. Due to the good performance of the model used, it can be recommended for time series predictions.

Project managers often face different and sometimes conflicting goals in optimizing project resources. In recent years, the demand of the project stakeholders to reduce the total cost of the project and reduce the time and increase its quality have intensified. Therefore, the balance of time, cost, and quality are the project's main goals. These topics lead researchers to develop models that add a quality factor to previous time balance models. This research provides a model for balancing cost, time and, quality, in discrete mode. Of course, since the quality factor is not a quantitative factor-like cost and time factors, and in the real world of projects, quality is a linguistic variable. It is obtained from the point of view of experts, so in this research, the quality of activities is shown as fuzzy numbers. By finding the optimal combination (time, cost, quality) of each activity, this model compresses the activities to reduce the costs of the whole project, while achieving the desired quality. A new metaheuristic algorithm called NHGA is introduced to solve the model, which has a much higher efficiency than GA to solve model, so with a case study, the efficiency of the proposed algorithm and the flexibility of the proposed model for project managers is shown

Nowadays, due to the high uncertainty in estimating precipitation in different geographical areas, the use of computational intelligence methods based on optimization algorithms to accurately estimate daily precipitation has been considered by water engineers. In the present study, the combined Adaptive Neuro Fuzzy Inference System and Wavelet transform (W-ANFIS) method was used as a pre-processor for daily rainfall data to estimate precipitation values. The structure of the W-ANFIS hybrid model was developed using the Fuzzy Clustering Means (FCM) method in the training phase. Moreover, constant coefficients of membership functions applied in the ANFIS model were optimized using four optimization algorithms including Genetic Algorithm (GA), Particle Swarm Optimization (PSO), Differential Evolution (DE), and Ant Colony community (ACO). In the present study, rainfall statistics of Izmir basin in the western part of Turkey were used. Through applying five-time delays in daily rainfall statistics as well as decomposing each time delay in the three levels of wavelet transform, each of the W-ANFIS optimal models had twenty input variables. The results of the statistical analysis for both training and testing stages by the Root Mean Square Error (RMSE) and Mean Absolute Error (MAE) showed that the application of the DE algorithm into W-ANFIS structure had the best performance (RMSE = 22.22 and MAE = 17.11mm) than other combined models with PSO (RMSE = 28.11 and MAE = 24.11 mm), ACO (RMSE = 30.41 and MAE = 26.50 mm), and GA (RMSE = 25.70 and MAE = 18.11 mm).

Rivers accumulate huge amounts of floating debris including the trunk, branches and leaves during the floods, leading to increase the depth of local scour around bridge piers. A large number of the laboratorial and field studies have been performed to understand the mechanism of scouring phenomenon under floating debris. Over two past decades, different types of the artificial intelligence methods have been used to estimate the maximum scour depth around bridges piers. In this study, the Neuro-Fuzzy model based on group method data handling (NF-GMDH) was used to estimate the scour under effect of debris accumulations. The NF-GMDH network was developed using evolutional algorithms: genetic algorithm (GA), particle swarm optimization (PSO), and gravitational search algorithm (GSA). Parameters effective on the maximum scour depth included average velocity of upstream flow of the bridge pier, critical velocity of river bed sediments, depth of flow in section without debris, thickness of submerged debris, debris diameter, average particle size, pier diameter, and channel width. After training and experiencing each NF-GMDH models, the performances of each one was evaluated through statistical parameters. The results showed that the models proposed had better performance compared with emperical relationships. NF-GMDH-PSO (R=0.8413 and RMSE=0.37) and NF-GMDH-GA (R=0.8407 and RMSE=0.3640) had relatively similar performance. Finally, sensitivity analysis indicated that the ratio of pile diameter (D) to mean diameter of bed sediments (d50) has the most influence on determination of maximum scour depth.