Search

Machine learning approaches are increasingly being employed to forecast the key characteristics of strong ground motions, including the challenging classification of Pulse-Like (PL) ground motions. The PL ground motions are characterized by their impulsive nature and have the potential to cause significant damage to structures. The classification of PL ground motions continues to be a significant challenge due to the absence of consensus on their definition and categorization. This paper investigates the potential benefits of several Machine Learning Classifiers (MLCs) algorithms such as decision tree, random forest, logistic regression, naive Bayes, support vector machine, K-nearest neighbor, ensemble model, and artificial neural network models for predicting PL and Non-Pulse-Like (NPL) ground motions. In this regard, a dataset comprising 200 near-fault ground motions records compiled from active tectonic regions like Taiwan, Turkey, Iran, and Japan, was divided into 2 portions, with 75% used to train the model and the remaining 25% used for testing. Plots of performance metrics, confusion matrix, and receiver operating curve indicate that the ensemble classifier outperforms the other classifier with 86.2% accuracy and the lowest misclassification of PL and NPL ground motions. Additionally, the trained MLC has been compared with the existing ground motion classification models to further assess the accuracy of the different classifiers in the present study. [ABSTRACT FROM AUTHOR]

Today, as a result of the development of technology, the production power of companies and the increase in the competition between themselves have led to the emergence of dangers especially for occupational safety. The 21st century, in which industrialization and production techniques have come to the fore, has been a period in which deaths and disabilities have increased because of work accidents caused by machines. In this paper, the number of occupational accidents in Turkey until 2030 was estimated by using an artificial neural network on the Weka package program. While creating the model, the numbers of compulsory insured workers, workplace, work accident, death as a result of a work accident and permanent incapacity for work were used between 1970 and 2021. 30% of the data was used as test data and 70% as training data in the neural network. In the light of the result, the expected number of occupational accidents in 2030 is estimated as 642210. [ABSTRACT FROM AUTHOR]

Forecasting stock markets is an important challenge due to leptokurtic distributions with heavy tails due to uncertainties in markets, economies, and political fluctuations. To forecast the direction of stock markets, the inclusion of leading indicators to volatility models is highly important; however, such series are generally at different frequencies. The paper proposes the GARCH-MIDAS-LSTM model, a hybrid method that benefits from LSTM deep neural networks for forecast accuracy, and the GARCH-MIDAS model for the integration of effects of low-frequency variables in high-frequency stock market volatility modeling. The models are being tested for a forecast sample including the COVID-19 shut-down after the first official case period and the economic reopening period in in Borsa Istanbul stock market in Türkiye. For this sample, significant uncertainty existed regarding future economic expectations, and the period provided an interesting laboratory to test the forecast effectiveness of the proposed LSTM augmented model in addition to GARCH-MIDAS models, which included geopolitical risk, future economic expectations, trends, and cycle industrial production indices as low-frequency variables. The evidence suggests that stock market volatility is most effectively modeled with geopolitical risk, followed by industrial production, and a relatively lower performance is achieved by future economic expectations. These findings imply that increases in geopolitical risk enhance stock market volatility further, and that industrial production and future economic expectations work in the opposite direction. Most importantly, the forecast results suggest suitability of both the GARCH-MIDAS and GARCH-MIDAS-LSTM models, and with good forecasting capabilities. However, a comparison shows significant root mean squared error reduction with the novel GARCH-MIDAS-LSTM model over GARCH-MIDAS models. Percentage decline in root mean squared errors for forecasts are between 39% to 95% in LSTM augmented models depending on the type of economic indicator used. The proposed approach offers a key tool for investors and policymakers. [ABSTRACT FROM AUTHOR]

The smarter world needs more efforts to purposeful manage and usage of technologies, science, artificial intelligence, and artificial neural networks, as their product. One of the main tools to facilitate collecting beneficial information is reviewing the publications of the target domain. To this end, the present paper attempts to categorize recent trends and innovations in the application of artificial neural networks in water quality and pollution research. The most prevalent methods for water pollution and quality prediction modeling during 2011–2020 were BPNN and normal MLP.. Conducting and comparing other analytical methods such as ANN, RBFNN, LSTM, and CNN to find accurate results are in the next orders. Moreover, along with the emerging and development of the internet of things (IoT), it was observed that IoT as a real-time technology for collecting relevant data, which appeared in the water quality analysis since 2016–2017, was used increasingly in 2019 and 2020. Furthermore, reviewed papers revealed that pH, chemical oxygen demand, and biochemical oxygen demand were the most water quality indicators. Regionally, drivers in China were the most investigated sites during the last decade, and then India and Turkey were the second and third place. [ABSTRACT FROM AUTHOR]

This paper covers the estimation of the water levels of Beysehir Lake, located in middle of Turkey, using the artificial intelligence (AI) such as the neural networks (NN) and the fuzzy logic (FL). The study considers the detailed investigation of the effect of the longterm estimate duration on the lake water level estimation. The analysed estimate ranges were 1 day, 30 days, 60 days and 90 days. The lake parameters such as the shortwave radiation, the lake total inflow rate, the lake total outflow rate and the past lake water levels constituted the input layer of the AI configurations. This study clearly showed that the estimate performance of the AI methods decreases with the increasing estimate range. It is also seen that the best estimate performance criteria are obtained by different AI methods for different estimate ranges. It is seen that the Generalized Regression Neural Network (GRNN) showed relatively superior performance compared with the other two artificial neural networks, i.e. the Radial Basis Function (RBF) and the Feed Forward Back Propagation method (FFBP), and the Adaptive Neuro-Fuzzy Inference System (ANFIS) method, for the long estimation ranges such as 60 and 90 days. The second overall best performance was obtained by FFBP. [ABSTRACT FROM AUTHOR]

Automotive aftermarket industry is possessed of a wide product portfolio range which is in the 4th rank by its worldwide trade volume. The demand characteristic of automotive aftermarket parts is volatile and uncertain. Nevertheless, the cause-and-effect relationship of automotive aftermarket industry has not been defined obviously heretofore. These conditions bring automotive aftermarket sales forecasting into a challenging process. This paper is composed to determine the relevant external factors for automotive aftermarket sales based on expert reviews and to propose a sales forecasting model for automotive aftermarket industry. Since computational intelligence techniques yield a framework to focus on predictive analytics and prescriptive analytics, an artificial neural network model constructed for Turkey automotive aftermarket industry. Artificial intelligence is a subset of computational intelligence that focused on problems which have complex and nonlinear relationships. The data which have complex and nonlinear relationships could be modelled successfully even though incomplete data in case of implementation of appropriate model. The proposed ANN model for sales forecast is compared with multiple linear regression and revealed a higher prediction performance. [ABSTRACT FROM AUTHOR]

Artificial intelligence (AI) has been widely affecting our lives in many ways for the last ten years. Potential applications of AI are currently being used in many sectors. However, the usage of AI has been very limited in sports science compared to the other sectors. In this study, we developed an artificial neural network model to estimate the market values of the players in the Turkish Super Football League. While the market value was selected as an output, the input values were: minutes played; goals scored; xG: assists; xA; defensive duels won %; tackle success %; shots on target %; Short-middle pass accuracy %; long pass accuracy %; and accuracy of passes to penalty area. After creating a neural network based on the input-output values with high training, validation and testing statistical values, input values were computed with the neural network created and then the output values were estimated. In conclusion, an artificial neural network is becoming one of the important modeling methods in all areas of life. Although the application of artificial neural networks is very limited in sports science, it is one of the suitable science disciplines where there is a lot of statistical data. The methodology proposed in this paper can also be used for talent selection in football. Moreover, it may help stop criticism by TV sports programmes and newspapers because market value estimation is based on fair performance parameters. Further studies are strongly recommended, not only for football but also for other sports disciplines. [ABSTRACT FROM AUTHOR]

Detecting malign cases from thyroid nodule examinations is crucial in healthcare particularly to improve the early detection of such cases. However, malign thyroid nodules can be extremely rare and is hard to find using the traditional rule based or expert‐based methods. For this reason, the solutions backed by Machine Learning (ML) algorithms are key to improve the detection rates of such rare cases. In this paper, we investigate the application of ML in the healthcare domain for the detection of rare thyroid nodules. The utilized dataset is collected from 636 distinct patients in 99 unique days in Turkey. In addition to the texture feature data of the Ultrasound (US), we have also included the scores of different assessment methods created by different health institutions (e.g., Korean, American and European thyroid societies) as additional features. For detection of extremely rare malign cases, we use auto‐encoder based neural network model. Through numerical results, it is shown that the auto‐encoder based model can result in an average Recall score of 0.98 and a Sensitivity score of 1.00 for detecting malign and non‐malign cases from the healthcare dataset outperforming the traditional classification algorithms that are trained after Synthetic Minority Oversampling Technique (SMOTE) oversampling. [ABSTRACT FROM AUTHOR]

This study has two purposes. Firstly, it aims to identify models that best estimate tourism demand. Secondly, it also aims to estimate the demand of Spanish tourists who visit Cappadocia, by using the identified proper models. As international tourism demand continually grows, the importance and magnitude of the tourism sector for the economies of the countries increase. In order to take into account the tourism demand, countries need to be prepared and therefore they want to know about the future demand. However, it is not always possible to know the actual demand and one can only make forecasts in such cases. This paper deals with forecasting international tourism demand, specifically focusing on the Spanish tourist visits in Cappadocia region of Turkey. In accordance with this aim, eight forecasting models are used. The results of the analyses for each model are obtained and the forecasting accuracy examined. It is seen that the Artificial Neural Networks and the Multiple Regression Model outperforms the other models. Finally, limitations of the study and future resarch directions are discussed. [ABSTRACT FROM AUTHOR]

Technological advancements coupled with growing world population require the increasing need of energy. Natural gas is one of the most important usable energy resources. Turkey is with high external dependency on energy as it has its own limited natural and underground energy resources. Thus, in order to effectively and productively use of natural gas purchased from foreign countries and to make reliable and robust energy policies for the years ahead, it is crucial to make a reasonable and plausible prediction for natural gas consumption of Turkey. In this paper, we estimate the natural gas consumption using machine learning techniques on the basis of real monthly data representing natural gas consumption of Turkey between the years 2010 and 2018. The performances of machine learning techniques involving Artificial Neural Networks, Random Forest Tree, Regression, Time Series and Multiple Seasonality Time Series are compared in predicting the natural gas consumption of Turkey. Experimental results show that among the five techniques, artificial neural networks produce the best estimation, having the lowest mean square errors, followed by regression method. Time series shows the worst performance among all the techniques. [ABSTRACT FROM AUTHOR]

• Critical forest management decisions are strongly supported by diameter predictions. • Modern modeling techniques were used for diameter predictions along the tree bole. • Levenberg-Marquardt algorithm was investigated for ANN models construction. • Diameter at 60% of the total height was identified as the best position for calibration. • Using the Levenberg-Marquardt ANN models results in accurate diameter predictions. Critical forest management decisions are strongly supported by the knowledge of forest ecosystems and their features. There is a growing trend towards using models to predict the most accurate yield projections for forest management. In this research area, features of standing trees, such as diameters along the tree bole, are of much interest. This paper is focused on the construction and evaluation of potential modeling approaches for Scots pine stem diameter prediction in north-eastern Turkey, including (1) fixed-effects, (2) mixed-effects, (3) three and five quantile regression, and (4) an artificial neural network modeling techniques. Nonlinear fixed-effects, mixed-effects, and both quantile regression models were based on a variable exponent taper equation, while the Levenberg-Marquardt algorithm was investigated for the artificial neural network (LMANN) models construction. Parameters of the tested models were calibrated by the use of several stem diameter measurements obtained at relative height positions, with models' superior performances in diameter predictions when the information of the additional diameter measured at 60% of total height, was included. Evaluation statistics show that both quantile regression and mixed-effects models improved results as compared to fixed-effects model. Overall, LMANN models achieved the best performance with higher accuracy for the Scots pine stem diameter prediction for the whole tree as well as for sections within the tree based on the ten relative height classes. Similarly to previous findings, the results of this study support that the use of mixed-effects modeling increases flexibility and efficiency of taper equations for stem diameter prediction. Moreover, the LMANN modeling approach was evaluated as superior according to its adequacy in predicting diameters along the tree stem. Therefore, the usage of the LMANNs for the tree stem diameter prediction can be a very useful tool in forest management practice and thus worth consideration. [ABSTRACT FROM AUTHOR]

Highlights • "Seddulbahir," the first Turkish national cyber-firewall system is proposed. • Artificial neural network radial basis function (RBF-NN) approach is used to generate security rules for 21 different attacks from 66 different network service flows. • National Cyber-technologies of developed countries are investigated. • Current state of the Turkey Cyber-infrastructure is highlighted. • Economic Impact of Volumetric DNS attacks on Turkey between 14th-24th December 2015 are exposed. • Required structure of the cyber-technologies to enhance country-wide cyber-security is elaborated. Abstract This research introduces "Seddulbahir," the first Turkish national cyber-firewall system. Proposed as the first of its kind, Seddulbahir resists possible cyber-attack threats against Turkey's internet infrastructure. Seddulbahir uses the artificial neural network radial basis function (RBF-NN) approach to generate rules that can detect 21 different attacks classified as probing, DoS (Denial of Service), U2R (User-to-Root), and R2L (Remote-to-Local) through the analysis of 66 different network service flows and based on three communication protocols. Results indicate that our proposed approach detects abnormal traffic with high efficiency, low cost, and has a wide detection range, providing accurate, flexible, and effective results in contrast to traditional methods. This paper also outlines the current state of cyberspace in Turkey, provides an analysis and detailed model of the latest cyber-attacks generated against Turkey, and investigates the working mechanisms of national cyber firewall systems used by developed countries such as Russia, China, and the United States. [ABSTRACT FROM AUTHOR]

This paper presents findings on performance benchmarking of cellular network operators in Turkey. Benchmarking is based on measurements of standard key performance indicators (KPIs) in one of the metropolitan cities of Turkey, Ankara. Performance benchmarking is formulated by incorporating customer perception by conducting surveys on how important KPIs are from the user's point of view. KPIs are measured, with standard test equipment, by drive test method on specified routes. According to the performance benchmarking results, the GSM and UMTS network operators achieving the best performance were determined in Ankara. Speech qualities of network operators, as the most popular service, were also evaluated by several statistical methods including pdf/cdf analysis and chi-square and Fisher's exact tests. The network operator providing the highest speech quality in Ankara was determined with the methods applied. Overall, the results and approaches on benchmarking of cellular networks in Turkey are reported for the first time in this paper. The approaches proposed in this paper could be adapted to wide-scale benchmarking of services in cellular networks. [ABSTRACT FROM AUTHOR]

This paper studies the performance of an artificial neural network (ANN) with teaching-learning-based optimization (TLBO) for modeling electric energy demand (EED) in Turkey. The ANN with TLBO (ANN-TLBO) was compared to the ANN with backpropagation (ANN-BP) and the ANN with artificial bee colony algorithm (ANN-ABC) models. Gross domestic product, population, import, and export were selected as independent variables in the models. The results reveal that the ANN-TLBO models perform better than the ANN-BP and ANN-ABC models in EED estimation. The average root-mean-square error of the ANN-BP and ANN-ABC models was decreased by 42.3 and 39.3 % using the ANN-TLBO model, respectively. Different scenarios have been studied over a projected 6-year period, from 2013 to 2018, to forecast Turkey's EED. The results of the proposed model give excellent clues with regards to its use in future energy studies. [ABSTRACT FROM AUTHOR]

Abstract: Training neural networks (NNs) is a complex task of great importance in the supervised learning area. However, performance of the NNs is mostly dependent on the success of training process, and therefore the training algorithm. This paper addresses the application of harmony search algorithms for the supervised training of feed-forward (FF) type NNs, which are frequently used for classification problems. In this paper, five different variants of harmony search algorithm are studied by giving special attention to Self-adaptive Global Best Harmony Search (SGHS) algorithm. A structure suitable to data representation of NNs is adapted to SGHS algorithm. The technique is empirically tested and verified by training NNs on six benchmark classification problems and a real-world problem. Among these benchmark problems two of them have binary classes and remaining four are n-ary classification problems. Real-world problem is related to the classification of most frequently encountered quality defect in a major textile company in Turkey. Overall training time, sum of squared errors, training and testing accuracies of SGHS algorithm, is compared with the other harmony search algorithms and the most widely used standard back-propagation (BP) algorithm. The experiments presented that the SGHS algorithm lends itself very well to the training of NNs and also highly competitive with the compared methods in terms of classification accuracy. [Copyright &y& Elsevier]

This paper looks into the Greek-Turkish arms race a decade after an earlier contribution to the issue that relied heavily on artificial neural networks. The time period between the two papers contributes to the reliability of the results derived, not just by increasing the number of observations, but also mainly by incorporating the progress made in the realm of artificial intelligence. The focus on the case of both countries unlike the paper mentioned above that dealt with just the Greek side provides ample room for comparative purposes regarding the determinants of defense expenditure on both sides. The results derived in terms of input significance estimation support the findings of the earlier research as indicated above, pointing to the leading role of the demographic preponderance of Turkey over Greece. The paper also points to the fact that 10 years later, Turkey continues to set the arms race rules against its rival by determining the defense expenditure of Greece, whereas the role of the latter in affecting the military spending of Turkey is non-existent. [ABSTRACT FROM AUTHOR]

Renewable energy, especially wind power, is a practicable and promising solution to mitigate the existing dilemma associated with climate change. Efficient and accurate prediction of wind power could guide a variety of decisions for resource management. To improve the accuracy of wind power prediction, most existing studies are multistage, where signal processing methods are first employed to decompose a single time series, and then deep learning methods are utilized for prediction. The aforementioned approaches have shown satisfactory results but tend to involve a burdensome time series decomposition process. To address this problem, this paper proposes a hybrid attention-based deep learning approach to achieve more efficient and accurate wind power prediction. The essential idea behind the proposed approach is to incorporate the cumbersome decomposition process into a hybrid deep learning model consisting of different deep neural networks, where each deep neural network is designed to perform a specific part of the prediction task to maximize its corresponding advantages. Compared with the typical deep learning models for time series prediction, e.g., long short-term memory (LSTM) and gated recurrent units (GRU), the proposed deep learning model has the following two major advantages: (1) the model eliminates the time series decomposition process by time embedding layers to achieve efficient prediction, and (2) the model achieves more powerful high-level temporal feature extraction by leveraging the combination of a convolutional neural network (CNN), multiple stacked bidirectional long short-term memory (Bi-LSTM) networks, and the attention mechanism, thus providing high accuracy prediction. The proposed method is evaluated with a real-world wind power dataset in Turkey, and comparative experiments demonstrate the effectiveness and applicability of the proposed method. [Display omitted] • A hybrid attention-based deep learning model was developed for wind power prediction. • The time embedding layer improves the accuracy and efficiency of the prediction. • The combination of two deep neural networks improves the prediction accuracy. • An attention mechanism reduces the loss of information. • The predicted results are well consistent with the observed dataset. [ABSTRACT FROM AUTHOR]

This paper presents the application of artificial neural networks (ANNs) and regression analysis (RA) for predicting dissolved oxygen concentrations (DO, mg/L) from water quality (WQ) indicators, namely stream water pH and temperature (t, °C). For this purpose, three diverse models are used in our analysis, considering the functional relationship between in situ-measured WQ indicators and DO concentration. The WQ data are semimonthly obtained from nine monitoring sites in the Harsit Stream watershed in the Eastern Black Sea Basin of Turkey, from March 2009 to February 2010. As a result of model prediction, this study proposes a suitable ANN model, including two independent variables to efficiently predict DO concentration from WQ data, with the root mean square error of 0.9442 mg/L and mean absolute error of 0.6965 mg/L. The proposed model predicts the DO concentration better than the RA and the other two ANN models. The results may reduce the time and cost necessary to determine DO concentrations. [ABSTRACT FROM AUTHOR]

Artificial neural network (ANN) is a useful tool that using estimates behavior of the most of engineering applications. In the present study, ANN model has been used to estimate the temperature, efficiency and power of the Photovoltaic module according to outlet air temperature and solar radiation. An experimental system consisted photovoltaic module, heating and cooling sub systems, proportional integral derivative (PID) control unit was designed and built. Tests were realized at the outdoors for the constant ambient air temperatures of photovoltaic module. To preserve ambient air temperature at the determined constant values as 10, 20, 30 and 40 °C, cooling and heating subsystems which connected PID control unit were used in the test apparatus. Ambient air temperature, solar radiation, back surface of the photovoltaic module temperature was measured in the experiments. Obtained data were used to estimate the photovoltaic module temperature, efficiency and power with using ANN approach for all 7 region of the Turkey. The study dealing with this paper not only will beneficial for the limited region but also in all region of Turkey which will be thought established of photovoltaic panels by the manufacturer, researchers and etc. [ABSTRACT FROM AUTHOR]

Abstract: This paper deals with an artificial neural network (ANN) modeling to predict the exergy efficiency of geothermal district heating system under a broad range of operating conditions. As a case study, the Afyonkarahisar geothermal district heating system (AGDHS) in Turkey is considered. The average daily actual thermal data acquired from the AGDHS in the 2009–2010 heating season are collected and employed for exergy analysis. An ANN modeling is developed based on backpropagation learning algorithm for predicting the exergy efficiency of the system according to parameters of the system, namely the ambient temperature, flow rate and well head temperature. Then, the recorded and calculated data conducted in the AGDHS at different dates are used for training the network. The results showed that the network yields a maximum correlation coefficient with minimum coefficient of variance and root mean square values. The results confirmed that the ANN modeling can be applied successfully and can provide high accuracy and reliability for predicting the exergy performance of geothermal district heating systems. [Copyright &y& Elsevier]

This study deals with the relationship between the current account deficit and the budget deficit in Turkey. Artificial Neural Networks are employed to investigate this relationship. According to the results of the application the twin deficits hypothesis which indicates a positive correlation between the two deficits isn't valid in Turkey. As this paper tries to analyze the factors accounting for the absence of this kind of correlation, it develops a flexible understanding which doesn't refuse a hypothesis or a theory (the twin deficits hypothesis) completely, on the contrary, emphasizes the importance of investigating the conditions in which a hypothesis, theory or a model is valid. [ABSTRACT FROM AUTHOR]

Summary: The Melen Watershed is located in Western Black Sea region of Turkey. Buyuk Melen and Kucuk Melen Rivers are located in this watershed. By 2010 more than 50% of Istanbul’s water demand is supplied from the Buyuk Melen River. This paper presents a new approach using an artificial neural network (ANN) technique to improve precipitation forecast performance. Missing value predictions and the future precipitation value estimations were researched throughout this study. A case study was performed in Bolu and Duzce provinces of Turkey that are located in Black Sea Region. The most crucial objective of this study was to estimate missing values and to generate quantitative forecasts for future precipitation data of Duzce. Monthly average daily precipitation data of Bolu and limited number of Duzce precipitation data were used for this purpose. Ultimately, monthly river flow rate from the Melen Watershed of Turkey was modeled and forecasted through the SWAT Model using the generated precipitation data and other required spatial and temporal data. Results show that there is a considerable relation between the simulated model and observed results. This study also shows that water supply for Istanbul can be managed based on precipitation forecast. [ABSTRACT FROM AUTHOR]

Abstract: The infamous soils of Adapazari, Turkey, that failed extensively during the 46-s long magnitude 7.4 earthquake in 1999 have since been the subject of a research program. Boreholes, piezocone soundings and voluminous laboratory testing have enabled researchers to apply sophisticated methods to determine the soil profiles in the city using the existing database. This paper describes the use of the artificial neural network (ANN) model to predict the complex soil profiles of Adapazari, based on cone penetration test (CPT) results. More than 3236 field CPT readings have been collected from 117 soundings spread over an area of 26km2. An attempt has been made to develop the ANN model using multilayer perceptrons trained with a feed-forward back-propagation algorithm. The results show that the ANN model is fairly accurate in predicting complex soil profiles. Soil identification using CPT test results has principally been based on the Robertson charts. Applying neural network systems using the chart offers a powerful and rapid route to reliable prediction of the soil profiles. [Copyright &y& Elsevier]

The emergence of the effective management of knowledge resources as a key factor in gaining and sustaining competitive advantage presents new challenges to construction firms. Evaluating knowledge management practices is considered one of the most important challenges facing firms in today's business environment. This paper proposes a model for evaluating the knowledge management practices of construction firms. The proposed model incorporates knowledge management concepts and multilayer perceptron (MLP) neural networks to construct an importance-comparative performance analysis (ICPA) map, a simple visual tool that can provide powerful diagnostic information to executives of construction firms. The model evaluates a firm's knowledge management practices, identifies its competitive advantages and disadvantages in each knowledge management practice, and sets priorities for managerial actions to improve knowledge management practices. A real-world case study was conducted by administering a survey to 105 construction firms operating in Turkey and is presented to illustrate the implementation and utility of the proposed model. The case study findings provided preliminary support for the validity of the proposed model. [ABSTRACT FROM AUTHOR]

The use of artificial neural networks (ANN) in geotechnical engineering has gained wide application in Turkey as well as the world during the past ten years. A comprehensive literature survey has shown that applications are concentrated in basic areas such as classification, site characterization, liquefaction, hydraulic conductivity, compaction, consolidation as well as practice comprising the problems of retaining structures, settlement of foundations, pile capacity and modeling of soil behavior where the relation-ship among the several parameters involved is not always thoroughly understood. Several case histories are presented as examples. Latest research shows that artificial neural networks are heading towards unison with fuzzy logic and genetic algorithms and it is certainly superior to the statistical methods . The second part of the paper gives an account of research conducted into estimation of the soil profiles in the city of Adapazari, Turkey. There has been widespread damage and destruction in the city during the Mw=7.4 earthquake in 1999. The damage has largely been blamed on inferior alluvial deposits and parts of the city have been moved to the North where the soil was found to be "sound". The sediments in the city are the products of the meandering river Sakarya which also flooded the region almost biannually. The two processes have resulted in the formation of complex soil profiles and near chaotic profiles are frequent. The silty layers are possibly the source of ground failures, occasionally leading to liquefaction in the absence of sands. A comprehensive soil investigation has been carried out since 1990 by boreholes and cone penetration soundings. The authors have used the rich database available established from previous and current laboratory and field investigations. Out of this voluminous data those pertaining to depths of 2 to 7m have been used for the ANN work, as those depths have been diagnosed as the possible liquefaction zone. Data from 117 CPT sites whose coordinates were known were employed for this study. The 3236 readings of tip resistance and sleeve friction were used to establish the ANN model. The well established Robertson classification chart defines nine types of soil. It requires the normalised values of tip resistance(Qt) and and sleeve friction(Fr) a identify the soil layer. The Qt* and Fr* are further defined to form the spatial distribution by the use of equations. The training matrix even for a limited depth of 5m using the data from 90 CPTU tests came out to be of size 3236x3236, which was difficult to handle. Consequently, thirteen 1800 by 1800 matrices were established (1.60-1.98m, 2.00-2.38m, 2.40-2.78m, 2.80-3.18m, 3.20-3.58m, 3.60-3.98m, 4.00-4.38m, 4.40-4.78m, 4.80-5.18m, 5.20-5.58m, 6.00-6.38m, 6.40-6.78m, 6.80-6.98m). Data from 27 CPTU were used to form the thirteen 540 by 1800 simulation matrices and 1800 by 1800 training matrices. Analyses were carried out on the Matlab 2010a Toolbox7 NNtraintool interface. 60% of the data were employed for Training, 15% for Validation and 15% for Testing. Inspecting the results, it was found that the success rate in estimating the soil profile anywhere in the 26 km² city area was as high as 92%. This is a surprisingly high success rate considering the highly complex and laterally variable soil profiles throughout the city. [ABSTRACT FROM AUTHOR]

In this study, Turkey's Carbonization Index (v) depending on the basic energy indicator has determined as an analytical equation. In this paper, artificial neural networks (ANN) which is quite often in recent years and the possibility of applying to many fields, are used to obtain analytical expressions. Carbonization Index is defined the amount of CO2 emissions per energy consumption. This parameter is an important for Turkey because of has signed the Kyoto protocol, February 2009. According to the results, accuracy of the carbonization index formulated empirical was obtained as R²= 1. It is expected that this study will be helpful in demonstrating carbonization index for policy makers. [ABSTRACT FROM AUTHOR]

Abstract: This paper presents three hitherto unused neural network architectures for bankruptcy prediction in banks. These networks are Group Method of Data Handling (GMDH), Counter Propagation Neural Network (CPNN) and fuzzy Adaptive Resonance Theory Map (fuzzy ARTMAP). Efficacy of each of these techniques is tested by using four different datasets pertaining to Spanish banks, Turkish banks, UK banks and US banks. Further t-statistic, f-statistic and GMDH are used for feature selection purpose and the features so selected are fed as input to GMDH, CPNN and fuzzy ARTMAP for classification purpose. In each of these cases, top five features are selected in the case of Spanish dataset and top seven features are selected in the case of Turkish and UK datasets. It is observed that the features selected by t-statistic and f-statistic are identical in all datasets. Further, there is a good overlap in the features selected by t-statistic and GMDH. The performance of these hybrids is compared with that of GMDH, CPNN and fuzzy ARTMAP in their stand-alone mode without feature selection. Ten-fold cross validation is performed throughout the study. Results indicate that the GMDH outperformed all the techniques with or without feature selection. Furthermore, the results are much better than those reported in previous studies on the same datasets in terms of average accuracy, average sensitivity and average specificity. [Copyright &y& Elsevier]

El Niño Southern Oscillation (ENSO) has been linked to climate and hydrologic anomalies throughout the world. This paper presents how ENSO modulates the basic statistical characteristics of streamflow time series that is assumed to be affected by ENSO. For this we first considered hypothetical series that can be obtained from the original series at each station by assuming non-occurrence of El Niño events in the past. Instead those data belonging to El Niño years were simulated by the Radial Based Artificial Neural Network (RBANN) method. Then we compared these data to the original series to see a significant difference with respect to their basic statistical characteristics (i.e., variance, mean and autocorrelation parameters). Various statistical hypothesis testing methods were used for four different scenarios. Consequently if there exist a significant difference, then it can be inferred that the ENSO events modulate the major statistical characteristics of streamflow series concerned. The results of this research were in good agreement with those of the previous studies. [ABSTRACT FROM AUTHOR]

The purpose of this paper is to present an artificial neural network (ANN) based method for the estimation of company success during economic crisis periods. There are a number of studies about recovering the crisis successfully by companies. Success or failure interpretation can be made upon financial indicators of companies for the period before the crisis. These indicators also provide estimation about the success of the companies. In this study, an ANN model is proposed estimating the success of companies after crisis period by means of financial indicators of the companies for the year before 2001 economic crisis of Turkey. A prototype model is designed with regards to homogeneous data set retrieved from the companies facilitating in manufacturing sector. [ABSTRACT FROM AUTHOR]

Abstract: This paper evaluates the effects of long-range transport patterns of air masses to the regional PM profile in a megacity, Istanbul, Turkey. Five-day hourly backward trajectories were obtained by the HYSPLIT model for selected episodic events in 2008. Self Organizing Maps (SOM), a very powerful classification tool, was used to cluster these trajectories. In total, eight cluster groups were obtained. All of the clusters were evaluated with respect to inhalable particulate matter (PM10) concentrations observed in Istanbul for the arrival times of the trajectories. Istanbul is generally under the effect of trajectories in three clusters (1, 2 and 4) (52% of all pre-selected episodic events), which have higher mean concentration values than the mean value of all the samples. These clusters typically make significant PM contributions to Istanbul''s air quality. PM loadings of the trajectories in these clusters were attributed to massive anthropogenic activity over all of Europe and southwestern air flow most likely carrying PM10 atmospheric particles originating from the Saharan Desert and other global dust generation regions located in the northern part of Africa. [Copyright &y& Elsevier]

This paper deals with estimation of the net electricity consumption of Turkey until the year 2012 based on linear regression (LR), nonlinear regression (NLR), and artificial neural networks (ANNs) methods. Installed capacity, gross electricity generation, population and total subscribership are selected as independent variables. Two different scenarios (high and low) are proposed for predicting the future electricity consumption. The LR, NLR and ANN model results are also compared with each other, and the Ministry of Energy and Natural Resources (MENR) projection and literature results. Results show that the performance values of the ANN method are better than the performance values of the LR and NLR models. According to the high and low scenario, and ANN model, Turkey's net electricity consumptions will be 251.1 and 221.07 TWh by the year 2012, respectively. [ABSTRACT FROM AUTHOR]

Millions of people are diagnosed every year with a chest disease in the world. Chronic obstructive pulmonary and pneumonia diseases are two of the most important chest diseases. And these are very common illnesses in Turkey. In this paper, a comparative study on chronic obstructive pulmonary and pneumonia diseases diagnosis was realized by using neural networks and artificial immune systems. For this purpose, three different neural networks structures and one artificial immune system were used. Used neural network structures in this study were multilayer, probabilistic, and learning vector quantization neural networks. The results of the study were compared with the results of the pervious similar studies reported focusing on chronic obstructive pulmonary and pneumonia diseases diagnosis. The chronic obstructive pulmonary and pneumonia diseases dataset were prepared from a chest diseases hospital’s database using patient’s epicrisis reports. [ABSTRACT FROM AUTHOR]

Abstract: This paper aims to develop methods that are capable of detecting manipulation in the Istanbul Stock Exchange. We take the difference between manipulated stock’s and index’s average daily return, average daily change in trading volume and average daily volatility and used these statistics as explanatory variables. The data in post-manipulation and pre-manipulation periods are used as non-manipulated instances while the data in the manipulation period are used as manipulated instances. Test performance of classification accuracy, sensitivity and specificity statistics for Artificial Neural Networks (ANN) and Support Vector Machine (SVM) are compared with the results of discriminant analysis and logistics regression (logit). We found that the data mining techniques (ANN and SVM) are better suited to detect stock-price manipulation than multivariate statistical techniques (discriminant analysis, logistics regression) as the performances of the data mining techniques in terms of total classification accuracy and sensitivity statistics are better than those of multivariate techniques. We also found that unit change in difference between average daily return of manipulated stock and the index has the largest effect while unit change in difference between average daily change in trading volume of manipulated stock and index has the least effect on multivariate classifiers’ decision functions. [Copyright &y& Elsevier]

In this paper, two soft computing approaches, which are known as artificial neural networks and Gene Expression Programming (GEP) are used in strength prediction of basalts which are collected from Gaziantep region in Turkey. The collected basalts samples are tested in the geotechnical engineering laboratory of the University of Gaziantep. The parameters, “ultrasound pulse velocity”, “water absorption”, “dry density”, “saturated density”, and “bulk density” which are experimentally determined based on the procedures given in ISRM (Rock characterisation testing and monitoring. Pergamon Press, Oxford, 1981) are used to predict “uniaxial compressive strength” and “tensile strength” of Gaziantep basalts. It is found out that neural networks are quite effective in comparison to GEP and classical regression analyses in predicting the strength of the basalts. The results obtained are also useful in characterizing the Gaziantep basalts for practical applications. [ABSTRACT FROM AUTHOR]

One of the most important functions of forests is timber production. The variation in working conditions and places, the complexity and variety of factors affecting the productivity of workers, and the nonlinear relationships among these factors in timber production make it difficult to solve with traditional methods. Today, artificial neural networks (ANN) designed to explain the biological structure of human brain is one of the most commonly used methods in the examination of system behaviors including complex events. In this paper, the affects of factors interacting the felling process on work time by using artificial neural networks (ANN) were identified. The measurement and observation were done in the mountainous forests of The Eastern Black Sea region, Turkey. The felling time, amounts, and the affecting factor measurements were mostly used in The Eastern spruce and beech forests. The data collected were evaluated statistically and the regression equation counting the time according to affective factors were formed. At the end of the study, it was found out that ANN models are more realistic and reliable for different land and working conditions when compared to regression equation based on direct relations in calculating the work time. The ANN models can be used for similar conditions on the planning of felling time, the control of applications and the determination of unit of price for felling workers. [Copyright &y& Elsevier]

Abstract: The objective of this paper is to develop an artificial neural network (ANN) model which can be used to predict daily mean ambient temperatures in Denizli, south-western Turkey. In order to train the model, temperature values, measured by The Turkish State Meteorological Service over three years (2003–2005) were used as training data and the values of 2006 were used as testing data. In order to determine the optimal network architecture, various network architectures were designed; different training algorithms were used; the number of neuron and hidden layer and transfer functions in the hidden layer/output layer were changed. The predictions were performed by taking different number of hidden layer neurons between 3 and 30. The best result was obtained when the number of the neurons is 6. The selected ANN model of a multi-layer consists of 3 inputs, 6 hidden neurons and 1 output. Training of the network was performed by using Levenberg–Marquardt (LM) feed-forward backpropagation algorithms. A computer program was performed under Matlab 6.5 software. For each network, fraction of variance (R 2) and root-mean squared error (RMSE) values were calculated and compared. The results show that the ANN approach is a reliable model for ambient temperature prediction. [Copyright &y& Elsevier]

Abstract: Determinants of house prices in Turkey are examined in this paper using the 2004 Household Budget Survey Data. In property valuation and housing market research, the locational value is usually analyzed by hedonic methods that use multiple regression techniques on large data sets and require a formality based on microeconomic theory in the analyses. Because of potential non-linearity in the hedonic functions, artificial neural network (ANN) is employed in this study as an alternative method. By comparing the prediction performance between the hedonic regression and artificial neural network models, this study demonstrates that ANN can be a better alternative for prediction of the house prices in Turkey. [Copyright &y& Elsevier]

Abstract: The performance of neural networks in evaluating and forecasting banking crises have been examined in this paper. An artificial neural network model which works with the banking data belonging to the same date and another artificial neural network model which works with cross sectional banking data have been formed and tested. The optimal topologies of these models have been determined by Taguchi approach which is a design of experiments method. Both models can forecast the values of the output neurons consisting of Non-performing Loans/Total loans, Capital/Assets, Profits/Assets and Equity/Assets ratios by using 25 input neurons consisting of macroeconomic variables, the variables related to the external balanced financial system’s structure, and time with very small errors. Consequently, it has been seen that artificial neural networks which are capable of producing successful solutions for semi-structural and non-structural problems, can be used effectively in evaluating and forecasting banking crises. [Copyright &y& Elsevier]

IIn this paper the capability of two different feed-forward back-propagation neural network algorithms, namely Levenberg-Marquardt and gradient-descent, in solving complex nonlinear problems is utilized for suspended sediment prediction. The monthly streamflow and suspended sediment data from two stations, Palu and Çayağzi, in the Firat Basin in Turkey are used as case studies. The first part of the study involves the prediction of sediment data for the two stations. The second part of the study focuses on the prediction of the downstream station sediment data using upstream data. The effect of the periodicity on model performance is also investigated in each application. [ABSTRACT FROM AUTHOR]

This paper presents an Artificial Neural Network (ANN) model for determining the total radioactivity in Hazar Lake (Sivrice, Turkey). In order to cope with complex calculations and experiments required for the determination of total radioctivity. The proposed ANN system employs the individual training strategy with fixed-weight and supervised models. The simulation demonstrate the feasibility of the neural based model. Compared to the classical methods, the proposed ANN-based model makes the processes much easier. [ABSTRACT FROM AUTHOR]

Predictions of wind energy potential in a given region are based on on-location observations. The time series of these observations would later be analysed and modelled either by a probability density function (pdf) such as a Weibull curve to represent the data or recently by soft computing techniques, such as neural networks (NNs). In this paper, discrete Hilbert transform has been applied to characterize the wind sample data measured on İzmir Institute of Technology campus area which is located in Urla, İzmir, Turkey, in March 2001 and 2002. By applying discrete Hilbert transform filter, the instantaneous amplitude, phase and frequency are found, and characterization of wind speed is accomplished. Authors have also tried to estimate the hourly wind data using daily sequence by Hilbert transform technique. Results are varying. [ABSTRACT FROM AUTHOR]

In this paper, average wind speed and wind power values are estimated using artificial neural networks (ANNs) in seven regions of Turkey. To start with, a network has been set up, and trained with the data set obtained from several stations—each station gather data from five different heights—from each region, one randomly selected height value of a station has been used as test data. Wind data readings corresponding to the last 50 years of relevant regions were obtained from the Turkish State Meteorological Service (TSMS). The software has been developed under Matlab 6.0. In the input layer, longitude, latitude, altitude, and height are used, while wind speeds and related power values correspond to output layer. Then we have used the networks to make predictions for varying heights, which are not incorporated to the system at the training stage. The network has successfully predicted the required output values for the test data and the mean error levels for regions differed between 3% and 6%. We believe that using ANNs average wind speed and wind power of a region can be predicted provided with lesser amount of sampling data, that the sampling mechanism is reliable and adequate. [Copyright &y& Elsevier]

Today, the world's primary energy demand has been met by the burning of fossil-based fuels at a rate of 85%. This dominant use of fossil-based fuels has led to an accelerating increase in the release of greenhouse gases (GHG) all across the world. The largest share in total GHG emissions belongs to the electricity and heat production sector with a rate of 25%. With this viewpoint, this paper is aiming to forecast the GHG emissions (CO 2 , CH 4 , N 2 O, F-gases, and total GHG) using deep learning (DL), support vector machine (SVM), and artificial neural network (ANN) algorithms from the electricity production sector in Turkey. The dataset is supplied from the Turkish Statistical Institute and covers the years 1990–2018. In the study, the last four years (2015–2018) is being forecasted. To evaluate the performance success of the algorithms, five metrics (RMSE, MBE, rRMSE, R2, and MAPE) are discussed in detail. In the results, this research is reporting that all algorithms used in the study are giving separately satisfying results for the forecasting of GHG emissions in Turkey. Based on the forecasting results, it is seen that the highest R2 value for the emissions varies from 0.861 to 0.998 and all results are categorized as "excellent" in terms of rRMSE (all rRMSE values < 10%). Besides, MBE changes between −2.427 and 2.235, and all MAPE values are smaller than 1.2%. Total GHG emission is forecasted in DL algorithm with very satisfied R2, RMSE, MBE, rRMSE, and MAPE of 0.998, 2.046, 0.419, 0.406%, and 0.021%, respectively. On the other hand, CO 2 accounted for 69.05% of total GHG emissions of Turkey in 1990 but rising by 80.48% in the year 2018. In comparison with those of 1990, electricity production and total GHG emissions of Turkey in 2018 increased by 429.7% and 137.4%, respectively. Total GHG emission corresponding to electricity production is calculated to be 0.3813 Mt-total GHG/MWh in 1990 and 0.1709 Mt-total GHG/MWh in 2018. In conclusion, GHG emissions have recently increased at a high rate, but it is noticed that this increase is considerably higher as compared to the increase in energy production for Turkey. • Forecasted the GHG emissions using different machine learning algorithms. • Noticed a good correlation between GHG emissions and electricity production. • Increasing shares of both CO 2 and F-gases among GHG emissions over the years. • Observed an increment of annum 6% for electricity production, annum 3% for GHG emissions in Turkey. • A respectable reduction in the country's total GHG emissions per unit electricity production over the years. [ABSTRACT FROM AUTHOR]