---

The significant wave height is a critical parameter in the design and analysis of marine structures, as well as in their operational use. Consequently, predicting this parameter greatly contributes to improving the design and analysis of marine structures. Various modeling approaches for wave characteristics include numerical, empirical, and artificial intelligence models. This study employs the SWAN model, which is a third-generation model for the simulation and estimation of wave characteristics. Furthermore, soft computing models, including individual and hybrid artificial intelligence models such as Adaptive Neuro-Fuzzy Inference System (ANFIS), Support Vector Machine (SVM), and Emotional Artificial Neural Networks (EANN), have been utilized for wave height prediction, using data from the Amirabad buoy for validation purposes. In this research, the model inputs consist of wind speed, while the outputs are the wave heights. The analysis of the different models was carried out using statistical metrics, including bias, root mean square error, coefficient of variation, and coefficient of determination. The evaluation of the models using these statistics indicates an acceptable agreement between the significant wave heights estimated by the SWAN model and the buoy data. Additionally, each of the three artificial intelligence models mentioned demonstrates a relatively accurate capability in predicting wave height. A comparison of the results from the artificial intelligence models revealed that the Support Vector Machine model exhibited higher accuracy than the others. The Support Vector Machine model serves as an alternative method to the SWAN model or other numerical techniques, enhancing modeling outcomes when wave height data is unavailable or lacks the necessary statistical quality.
 

---

Integrated complaints management system designed to give organizations the opportunity to learn from customer feedback information and use information to reduce weaknesses in business performance, efficient use of resources and maintain satisfactory capital base long term relationship with their customers. Therefore in this paper, a model is provided that could clear weak points first, in other words, discover and understand the Working patterns and factors affecting it. Second, it can provide solutions to the problem. As a case study customer relationship management data unit of Ayandeh private Bank is used. This data related to customer complaints in one of the call centers in Tehran. In order to provide a descriptive model, the data is clustered by using data mining tools, optimal clusters based on Davis– Bouldin Indicator is determined and based on the analysis obtained, the architecture of response system is designed. Next, in order to provide a prediction model, support vector machine is used. The result is validated and suggestions to improve complaints management system are presented

---

---

---

In power systems, distance relays are utilized widely as main protection of the high voltage transmission lines, and their safe operation has significant effects on health of the components and stability of the system. Power swing is a phenomenon that can cause mal-operation of the distance relays while there is no fault in the system. In this paper, a protection scheme based on Support Vector Machine (SVM) classifier is proposed for the digital distance relays to distinguish between power swings and faults. In this work, simulations are done on a study system and related train and test patterns are generated to analyze performance of the proposed method. Also, the proper structure of the SVM classifier is investigated using the train and test patterns. The train and test patterns contain information of the different power swing conditions and symmetrical and asymmetrical types of faults. The results of the tests and simulations confirm the efficiency of the proposed protection algorithm

---

Considering that once-through Benson boiler is one of the most crucial equipment of a thermal power plant, occurrence of any fault in its different parts can lead to decrease of the performance of system, and even may cause system damage and endanger the human life. In this paper, due to the high complexity of the system's dynamic equations, we utilized data-based method for diagnosing the faults of the once-through Benson boiler. In order to enhance the fault diagnose (FD) system proficiency and also due to strong interactions between measurements, we decided to utilize six one-class support vector machine (SVM) algorithms to diagnose six major faults of once-through Benson boiler. In the proposed structure, each One-class SVM algorithm has been developed to diagnose one special fault. Finally, we carry out diverse test scenarios in different states of fault occurrence to evaluate the performance of the proposed FD system against the six major faults of the once-through Benson Boiler under conditions of noisy measurement.

 
 

---

In this paper, we proposed a practical method for classifying damages in pipes and plates using ultrasonic guided waves. The A-scan Pulse-Echo lamb wave ultrasonic tests used in this study. Tests accomplished on isotropic 1050 Aluminum with 0.4 mm thickness. Damages studied here were corrosion and crack which is common in pipe lines and steel structures like vehicles body or aerospace structures. This investigation is done in three steps. First step, experimental testing (making standard sample, lamb wave tests), second step, signal processing (window function, normalizing, wavelet function), third step, using the proper algorithm for classification. In first step, 206 ultrasonic lamb wave tests are measured on standard damaged samples (on pipe and plate) and the signals digitalized. After that, these signal processed and classified by classification algorithm. In this the classification algorithm is the support vector machine (SVM). In machine learning, support vector machines are supervised learning models with associated learning algorithms that analyze data and recognize patterns, used for classification and regression analysis. The results show that the corrosion damage can be distinguished from crack damages with 99% accuracy by proposed algorithm.

---

In this study, an application of support vector machine (SVM) for early fault detection in increasing the level of the start-up vessel in a Benson type once-through boiler during load changes is presented. The level increasing in the start-up vessel is happened due to thermal conditions disruption inside the boiler especially while the unit load is ramped-down. In this regard, first, the variables effective on increasing the level of start-up vessel was identified based on experimental data from a power plant unit, then the dimension of input variables was reduced by selecting appropriate features. Experimental results show that the hotwell surfaces’ temperature could be considered as the most appropriate indicator for steam quality deterioration. By comparing the extracted features from healthy and unhealthy conditions, appropriate fault model was developed using SVM with radial basis function (RBF) as the kernel. The performances of fault detection system were evaluated with respect to the similar faults at two different time periods happen in a steam power plant. The obtained results show the accuracy and feasibility of the proposed approach in early detection of faults during the unit’s load variations. Advantages of the proposed technique is preventing false alarm in power plants’ boilers as load changes.

---

In this study, fair comparisons between the empirical mode decomposition, ensemble empirical mode decomposition and discrete wavelet transform with the mother wavelet function of Meyer and Daubechies, were performed for detecting unbalance faults in a rotating machinery. In order to classify the healthy class from the unbalance classes, a support vector machines that was optimized by particle swarm optimization algorithm, was used. A comparison between the performances of optimized and non-optimized of support vector machines were also carried out. In order to obtained the required data, a rotating machinery fault simulator was developed and vibrational signals were acquired at healthy and unbalance fault conditions by accelerometer sensors. By processing the recorded signals and analysing signal to their frequency components, several statistical features were extracted from each frequency component as input support vector machine for the separation of classes. The obtained results indicated that the discrete wavelet transform with the Meyer mother wavelet, higher success rate than other methods for diagnosing unbalance faults.

---

In Carbon monoxide (CO) is one of the main air pollutant parameters in the atmosphere of Tehran, Iran. Generally, it is difficult to predict and control CO concentration because it is essentially nonlinear time-varying system. Recently, in particular, environmental control such as CO concentration level control is regarded as one of the most important factors in environmental protections. This paper describes forecasting and more specifically uncertainty determination of CO concentration during the modeling process using a support vector machine (SVM) technique. Uncertainty of the air pollution modeling studies highly affected the simulation results. In this regards, it is very important to determine the uncertainty of air pollution models due to consequences on health of people exposed to the pollution. Therefore, this research aims to calibrate, verify, and also determine the uncertainty of support vector machine (SVM) in the process of air pollution modeling in the atmosphere of Tehran. To achive this goal, the SVM model was selected to predict arithmetic average of daily measured CO concentration in the atmosphere of Tehran. In this regards, the SVM model was calibrated and verified using six daily air pollutants include particulate matter with diameter equal or less than 10 micrometer (PM10), total hydrocarbons (THC), nitrogen oxides (NOx), methane (CH4), sulfur dioxide (SO2) and ozone (O3) and also six daily meteorological variables include pressure (Press), temperature (Temp), wind direction (WD), wind speed (WS) and relative humidity (Hum). The data was collected from Gholhak station located in the north of Tehran, Iran, during 2004-2005. Thereafter, the best developed SVM model for predicting the CO concentration was chosen based on determination of coefficient (R2). Finally, to determine the SVM uncertainty, the model was run many times with different calibration data. It led to many different results because of the model sensitivity to the selected calibration data. Then, the model uncertainty in the CO prediction process was evaluated using the width of uncertainty band (d-factor) and the percentage of measured data bracketed by the 95 percent prediction uncertainties (95PPU). Generally, the results confirmed the strong performance of the SVM model in predicting CO concentration in the atmosphere of Tehran. The predicted average daily CO concentrations by SVM model had a good agreement with the measured ones in the Gholahak air quality monitoring station. It was found that the determination of coefficient for calibration and validation of SVM model were equal to 0.89 and 0.88, respectively. Furthermore, the results indicated that the SVM model has an acceptable level of uncertainty in prediction of CO concentration in which the level of d-factor and the percentage of measured data bracketed by the 95PPU in the validation step were 0.74 and 76, respectively. Therefore, The obtained results indicated that the SVM model had an acceptable level of uncertainty in prediction of CO concentration. Therefore, it can be concluded that the SVM model is able to predict the CO concentration in the atmosphere of Tehran while it resulted an acceptable level of uncertainty. Finally, due to the proposed methodology is general, the authors suggest to apply it for analyzing the uncertainty of SVM model in other fields of science and engineering.

---

Any industry needs an efficient predictive plan in order to optimize the management of resources and improve the economy of the plant by reducing unnecessary costs and increasing the level of safety. Rotating machinery is the most common machinery in industry and the root of the faults in rotatingmachinery is often faulty rolling element bearings. Because of a transitory characteristic vibration of bearing faults, combining Continuous wavelet transforms with envelope analysis is applied for signal proseccing. This paper studies the application of independent component analysis and support vector machines to for automated diagnosis of localized faults in rolling element bearings. The independent component analysis is used for feature extraction and data reduction from original features. The principal components analysis is also applied in feature extraction process for comparison with independent component analysis does. In this paper, support vector machines-based multi-class classification is applied to do faults classification process and utilized a cross-validation technique in order to choose the optimal values of kernel parameters.

---

In recent decades, increasing population density and economic and industrial activities in metropolitan cities has increased traffic volumes and, consequently, increased levels of air pollution. The major source of air pollution in major developing cities is the massive transport of vehicles that use more than standard fuel and energy, and heavy traffic in the streets of these cities is often rooted in problems such as there is a lack of traffic management and traffic culture. One of the important issues in cities and metropolises that face pollution problems and harmful effects is the issue of informing about the future status of air quality and the amount of urban air pollution to the people. This can be achieved through daily or even hourly forecasts of air pollution and preventing people from being exposed to contaminated areas and their irreversible consequences. Therefore, the need to predict the quality of the air and the quantitative estimates of the concentration of pollutants in the aftermath of the equipment makes it felt that in this study, the problem of the predicted hourly concentration of particulate matter (PM2.5) in the district 11 municipalities of Tehran have exceeded 80% of the contaminated days under the influence of this pollutant. The difficulty and uncertainty associated with estimating and predicting the share of road traffic volume at the general level of air quality is the most important factor that can, if properly diagnosed, be very helpful. In order to take into account the effects of varying the volume of different traffic fleets in the process of changes in the concentration of pollutants and air pollution, it is necessary to pay attention to the effects of other influential variables including hydrological variables, geographical variables, etc. To achieve this, The methods of analytic analysis seem to be able to examine all of these effects together and in an omnipresent manner. The method used to predict this study is one of the methods for analyzing neural networks called Support Vector Machine (SVM). Artificial neural networks are important tools in the field of computational intelligence. Different types of artificial neural networks have been introduced, mainly in applications such as classification, clustering, pattern recognition, modeling and approximation of functions (or regression), control, estimation and optimization of the case Are used. Support Vector Machines (SVM) are a special type of neural network that, unlike other types of neural networks (such as multi-layer perceptron MLP and radial base functions of the RBF), instead of minimizing the error, minimize the operational risk of classification or modeling. Slowly This tool is very powerful and can be used in various fields such as classification, clustering and regression. The results of this study showed that SVM models work well in predicting the contribution and time share of road traffic in propagation of particulate matter, and predictions are well-coordinated with observations. It provides the opportunity to be used as an air quality management tool. Variable significance analysis results for SVM models provide this opportunity to be used as a tool for air quality management, in which the sensitivity of models to variations in emissions can be used to evaluate the effectiveness of a The air quality management scenario will test traffic fleet technology, combine the traffic fleet or its volume.

---

The aim of this study was to develop and validate qualitative and quantitative models to discriminate different types of maize and also estimate biochemical constituents. Spectral data were taken from the central leaf of randomly-chosen plants grown in field trials in 2011 and 2012. Leaf chlorophyll and protein content and stalk protein content were determined in the same plants. Four different Support Vector Machine (SVM) models were generated and validated in this study. In qualitative models, maize type was designated as dependent variable while Full Spectral (FS) data (400-1,000 nm) and Spectral Indices (SI) data (34 indices/bands) were independent variables. In the two quantitative models (SVMR-FS and SVMR-SI), independent variables were the same, whereas dependent variables were assigned as the quantitatively measured traits. Results showed the qualitative models to be a robust method of classification for distinguishing different maize types, such as High Oil Maize (HOM), High Protein Maize (HPM) and standard (NORMAL) maize genotypes. The SVMC-FS model was superior to SVMC-SI in terms of the genotypic classification of maize plants. Quantitative models with full spectral data gave more robust prediction than the others. The best prediction result (RMSEC= 222.4 µg g^-1, R² for Cal= 0.739, SEP= 213.3 µg g^-1; RPD= 2.04 and r= 0.877) was obtained from the SVMR-FS model developed for chlorophyll content. Indirect estimation models, based on relationships between leaf-based spectral measurements and leaf and stalk protein content, were less satisfactory.

---

In this study, the effects of Farsi gum (0, 1.5% and 3%) coating containing hemp seed oil (0, 0.075% and 0.15%) on mass and volume changes of grape were investigated during storage at 4°C for 28 days. Machine vision system with learning machine methods was used to detect coated grapes from an image and estimate their mass and volume based on the image features (length, width, height and area). Four machine learning models, including linear regression (LR), artificial neural networks (ANN), radial basis function support vector regression (RBF-SVR) and Linear basis function support vector regression (LBF-SVR) were developed to predict the mass and volume of the single grape. The estimated grape mass and volume by these methods was compared statistically with actual values. The mass and volume in all treatments showed a decreasing pattern during the cold storage. The results indicated that mass and volume change decrease with Farsi gum and hemp seed oil increasing. Furthermore, according to the model evaluation results, the prediction performance of RBF-SVR model had achieved better predictive accuracy compared with the results of LR, ANN and LBF-SVR models, with R2 of 0.998 and 0.989 for mass and volume estimation, respectively, which also showed a good agreement between actual and predicted values. These results revealed that SVR model was a promising tool for estimating the mass and volume of grape during storage.

---

In this paper, a new hybrid intelligent method is presented for detecting the bearing faults in the various rotating speeds. The vibration signals are collected in four conditions, including the normal state, the faulty inner race, the faulty outer race, and the faulty bearing element. Firstly, twenty-two statistical features in the time domain and four frequency features, three Wavelet packet decomposition (WPD), and the first five intrinsic mode functions obtained by the empirical mode decomposition (EMD) are extracted from the original signal; finally, the feature vector for each signal sample has 424 features. However, in the high dimensional feature matrix, there may exist the insensitive features to the presence of defects. Therefore, in this study, the compensation distance evaluation technique (CDET) is used to select the optimal features. Then, the selected features are used as the inputs of the support vector machine (SVM) classifier to diagnose the bearing conditions. In the CDET method, there is a threshold indicator that plays a decisive role in choosing the desired attributes. Also, the SVM method has some parameters that need to be set during the fault detection process. Therefore, the particle swarm optimization (PSO) algorithm is used to determine the optimal threshold in the CDET method and the optimal SVM parameters, so that the prediction error of the bearing conditions and the number of the selected features are minimized. The obtained results demonstrate that the selected features are well able to differentiate between different bearing conditions at various speeds. Comparing the results of this paper with other fault detection methods indicates the ability of the proposed method.

---

Groundwater is the most reliable source of supply for potable water and supports a wide array of economic and environmental services. There is a significant concern that groundwater levels are declining due to intense aquifer use. The sustainable management of groundwater resources requires good planning and concerted efforts. To manage groundwater resources, it is necessary to predict the groundwater levels and its fluctuations. The prediction groundwater level can guide water managers and engineers effectively. On the other hand, there are multifarious types of equipment for measuring levels of groundwater. Sophisticated water level loggers or divers can measure the groundwater level automatically. Sounding devices with acoustic and light signals are also used to check groundwater levels. The use of devices for measuring the level of groundwater is time-consuming and costly. To reduce the time and cost of the groundwater level measuring process, many methods of Artificial Intelligence (AI) have been utilized for estimating the groundwater level. Among the AI methods, SVMs has great ability in predicting non-linear hydrological processes. Support vector machines (SVMs) is as an intelligent computational method for predicting hydrological processes. Recently, (SVMs) have been successfully applied in classification problems, regression and predicting; as techniques of machine learning, statistics and mathematical analysis. The SVM is based on the structural risk minimization (SRM), which can escape from various difficulties, such as the necessity of a large number of control parameters and a local minimum in artificial neural networks (ANNs). The weighted least squares support vector machines (WLSSVM) was first introduced by Suykens et al., and has proved to be much more robust in several fields, especially for noise mixed data, than least squares version of SVM (LSSVM). Their powerful scientific research provides motivation for employing WLSSVM method in estimating groundwater level. The accurate value of WLSSVM parameters  effect on the estimation, these optimal parameters can be achieved optimization algorithms. Therefore, weighted least square support vector machine (WLS-SVM) model was coupled with particle swarm optimization (PSO) and gravitational search algorithm (GSA) as metaheuristic algorithms for estimating well water level. In this study, an attempt has been made to use the hybrid model with high accuracy to estimate the groundwater level. In order to estimate the groundwater level, ten wells data in Bagheyn plain of Kerman province is considered during ten-year time series. The estimated value obtained by the WLSSVM-PSO and WLSSVM-GSA models are compared with the observed value, and showed the estimated results have nearly coincidence with observed values. Numerical results show the merits of the suggested technique for groundwater level simulation. In order to verify the hybrid learning machine metaheuristic model, Mean Absolute Error (MAE), Root Mean Squared Error (RMSE), Average Absolute Error (AAE), and Model Efficiency (EF) are computed, and these statistical indicators stand on the good acceptable range, and find WLSSVM-GSA is more accurate than WLSSVM-PSO. The results demonstrate that the new hybrid WLSSVM-GSA model has high efficiency and accuracy with observed values, and the modelling method is an innovative and powerful idea in estimating well water level.

---

In recent decades, the science of structural health monitoring has played a key role in preventing damage and extending the life of structures. To conduct behavioral assessment, it is desirable to use tools that achieve sufficient accuracy with low cost. The processing of behavioral data requires methods that are able to identify and correctly troubleshoot different levels of damage from existing information.
Nowadays, sensors are used to measure the behavior of structures including deformations and displacements and even deflections, but these sensors have some weak points. For example, Risk of damage to the sensor, pointwise and one-dimensional measuring, their data is difficult to analyze and using multiple or high-tech sensors becomes expensive.  
Optical behavior measurement and close-range photogrammetric operations have recently received attention due to their low cost and good accuracy. This method has some advantages like Indirect contact with objects, high-speed image capture, easy access to convenient digital cameras, low viewing costs, and the ability to process composite and instant data with easy operation. In addition, the high flexibility of this method in measuring accuracy and design capability to achieve predetermined accuracy is an important feature of this tool.
Analytical methods are based on rules or equations that provide a clear definition of the problem. These methods work well in the cases which the rules are accurately clear and defined but there are many practical cases for which the rules are not known or it is very difficult to discover that calculations cannot be performed using analytical methods.
Neural network is a generalizable model, which is based on the experience of a set of training data and therefore free of explicit law. Neural networks have the ability to collect, store, analyze, and process large amounts of data from numerical analyzes or experiments. Therefore, they have the ability to predict and build diagnostic models to solve various engineering problems and tasks
In this paper, an attempt has been made to use this method to measure and troubleshoot laboratory model of a scaled suspension bridge that has a relatively complex behavior. For this purpose, the structure was subjected to uniform static loading in three step levels with three states: healthy and damaged in the deck and cables. Damages were created quite intentionally in the laboratory model, and from the information obtained, a database of bridge behavior in various situations was created. In order to assess the feasibility of using different methods in data processing and troubleshooting, first the data in the database were used in a simple linear method (direct comparison) and training in algorithms of machine learning methods. After that, deliberate damage was done again in the laboratory structure to allow testing the efficiency and accuracy of different methods. Finally, the accuracy, precision, and stability of the data processing methods of the support vector machine and artificial neural network were compared.
The results showed that by object bundle justification of two-dimensional optical behaver measurement with close-range photogrammetry, a guaranteed accuracy of 0.0021 mm could be achieved. Using intensity image processing seems helpful to ease the calculation. Using high number of nodes in hidden layer makes it more difficult and time-consuming to train the neural network. In the first level of processing, the detection of the presence or absence of damage was associated with the complete superiority of neural networks with 100% accuracy and in the second level, the detection of the affected area, depending on the type of processing, the neural network with hyperbolic tangent transfer function archived 93% accuracy and the support vector machine archived 68% of the accuracy.

---

Accurate precipitation forecasts are much attractive due to their complexity. This study aimed to use the hybrid Seasonal Autoregressive Integrated Moving Average (SARIMA) model and machine learning techniques such as Artificial Neural Networks (ANN) and Support Vector Machines (SVM) to improve precipitation forecasts. Time variation analysis and time series decomposition were the two concepts applied to construct the hybrid models. The performance of the two concepts was evaluated with monthly precipitation time series of two stations in northern Iran. Time variation analysis of time series was conducted with the clustering analysis, which increased the accuracy of forecasting with 20.99% decrease in the geometric mean error ratio for the two stations. SVM model decreased the forecasted error compared to ANN in the internal process of time variation analysis. Average of Mean Relative Error (MRE) were MRE_SVM= 0.72, MRE_ANN= 0.89, and Mean Absolute Error (MAE) in the two stations were MAE_SVM= 18.02 and MAE_ANN= 23.88. Therefore, SVM outperformed the ANN model. Comparison of the two hybrid models indicated that more accurate results belonged to the concept of time series decomposition (the decrease in root mean square error from time variation to time series decomposition concepts was 13.35%). Extracting the pattern of data with SARIMA-based hybrid model with time series decomposition improved the precipitation forecasting. Configurations related to nonlinear components of time series with time steps of residual had good performance (the average of agreement index was 0.9). The results suggest that the hybrid model can be a valuable and effective tool for decision processes, and time series decomposition to linear and nonlinear components has a better performance.
 

---

One of the information needed for all planning problems and specifically transportation planning is to have accurate prediction about the future. Traffic variables prediction is one of the efficient tools in travel demand management. Using this tool and advanced traveler information systems (ATIS), the predicted traffic variables are informed to the users and transportation system operators to make plans and set policies. In this study, the average speed and traffic volume of the Karaj to Chalus suburban road with the high variation of traffic variables in the north of Iran is predicted. The Karaj to Chalous road is part of the route from Tehran as the capital of Iran to the country's northern coast. Along the Karaj to Chalous road, three parallel roads, with different lengths, connect Tehran with the cities of the north. In general, finding the pattern of non-mandatory trips is more complicated than mandatory trips. Generally, the predictive methods are divided into three groups, naïve, parametric and non-parametric methods. Among the various predictive models, the SARIMA as a parametric model and the artificial neural network and the support vector machine as nonparametric models are employed. In the data pre-processing step, the variables affecting the average speed and traffic volume are extracted and added to the dataset as predictor variables. These variables are related to time, calendar, holidays, weather, and roads blockage. Also, because of the importance of the maximum and minimum values of traffic speed and volume, as critical values and rare events, models are evaluated with emphasis on the prediction of rare events compared to normal values. The results show that, for the test data, the lowest root mean square error of predicting the average traffic speed and traffic volume are obtained using artificial neural network and support vector machine models equals 139 vehicles per hour and 5 kilometers per hour, respectively. In terms of R² of prediction-observation plot, the performance of SARIMA for predicting the average speed and traffic volume is the same for the test dataset. In contrast the R² of hourly traffic volume prediction is higher for the training data. The R² of artificial neural network model and the support vector machine for traffic volume prediction is higher than traffic speed prediction. The lowest root mean square error of predicting the first and fourth quartile of the observed average traffic speed values is obtained by support vector machine models and artificial neural network, respectively. Also, predicting the first quartile and fourth quartile of the observed traffic volume values by the support vector machine model is more accurate than two other models. Using predicted traffic parameters and providing them to travelers and transportation agencies by intelligent transportation systems leads to make a balance between travel demand and travel supply in the near future which is the main aim of this study. Travelers can have a better personal plan for their future trips based on these predictions. Also, the transportation agencies are more prepared to deal with critical traffic situations and can prevent traffic congestion.