Authors:Ezgi GÜNEY; Ozan ÇAKMAK, Çağri KOCAMAN Abstract: The detection and classification of power quality events that disturb the voltage and/or current waveforms in the electrical power distribution networks is very important to generate electrical energy and to deliver this energy to the end-user equipment at an acceptable voltage. Various property extraction methods are used to determine the type of disturbances in the electrical signal. In this study, seven power distortions including voltage sag, voltage swell, voltage harmonics, voltage sag with harmonics, voltage swell with harmonics, flicker, transient signals and pure sine as a reference signal is used. Synthetic data are produced in MATLAB using parametric equations based on TS EN 50160 standard. Four kinds of feature extraction as frequency-amplitude, time-amplitude, geometric mean and standard deviation is made with Stockwell Transform (ST), which is one of the methods used for the feature extraction of the determined GKB. Detection of voltage distortions is interpreted through these properties. 640 simulation data is entered into the classifier by using Support Vector Machines (SVM) and Artificial Neural Networks (ANN) and their classification performance is compared. PubDate: Wed, 02 Mar 2022 00:00:00 +030
Authors:Fatma DEMİRCAN KESKİN; Ural ÇİÇEKLİ, Doğukan İÇLİ Abstract: Today’s manufacturing vision necessitates extracting insights from the data collected in real-time from manufacturing processes. Predicting failures with the predictive analysis of the collected process data and preventing these failures by taking necessary actions before they occur is a key factor in ensuring quality at the desired level, increasing productivity, and reducing costs in production systems. In the literature on predictive analysis of process data, machine learning and deep learning methods have attracted considerable attention, especially in recent years. This study has addressed a multi-class failure classification problem in the plastic extrusion process with a real case study. Classification models have been developed based on Long Short-term Memory (LSTM) as a deep learning method and Multilayer Perceptron (MLP) and Logistic Regression (LR) as machine learning methods to predict the failure categories. In the case study, real data taken from the extrusion process of one of the leading insulation companies operated in Izmir has been used. The final dataset includes actual measurements of seven parameters related to temperature and pressure and failure categories as the target variable. Three failure categories have been identified to define Category 0 (No failure), Category 1 (Filter change), and Category 2 (Feeding failures) states, and coded as 0,1 and 2 in the models, respectively. LSTM, MLP, and LR’s performance to predict the failure categories have been evaluated and compared based on accuracy, precision, recall, and F1 Score measures. LSTM is the highest performing among the three methods, with 100% prediction accuracy for each failure category. On the other hand, LR and MLP have achieved considerable and close results except for Category 1. PubDate: Wed, 02 Mar 2022 00:00:00 +030
Authors:Buket KARATOP; Buşra TAŞKAN, Elanur ADAR Abstract: Determining the strategies that Turkey need to focus at the renewable energy field is aimed in this study. For this, an integrated method called the Fuzzy Sectional SWOT consisting of the Fuzzy AHP and the Sectional SWOT methods was used. Some disadvantages of the traditional SWOT analysis are eliminated with the method used. Firstly, the renewable energy field was divided into 6 sub-sections (hyropower, solar, wind, biomass, hydrogen and geothermal) according to the logic of Sectional SWOT analysis. Then strengths, weaknesses, opportunities and threats for each of these sub-sections were determined using the Sectional SWOT analysis. Weights were found with the Fuzzy AHP method for each of the renewable energy sources and they were prioritized according to these weights. Finally, focus strategies related to renewable energy field for Turkey were obtained with the creation of strategies related to renewable energy sources. Consequently, the focus strategies which should be primarily addressed are related to use of renewable energy potential, social awareness about the renewable energy, government supports and incentives related to the renewable energy, selection of suitable areas for renewable energy plants and domestic production of the constituent parts of renewable energy plants. PubDate: Wed, 02 Mar 2022 00:00:00 +030
Authors:Hakan KOÇAK Abstract: Predicting rainfall is important issue that concerns everyone especially weather forecasters, farmers and those who work in agriculture sector. Although artificial intelligence and machine learning applications, which have gained great momentum in recent years, are applied in precipitation forecasting, as in many other areas, it is still a challenging task to make high-accuracy rainfall prediction. Changes in the precipitation regime due to climate change, the effects of which we have felt more and more in recent years, make this difficult task even more challenging.In this study, the performances obtained by applying 10 classifier algorithms from 5 different categories on the data set were compared. In addition to that, different scenarios were created by removing some of the parameters from the original data set and the performance differences of the classification algorithms for each of the scenarios were noted. The results have shown that the Functions category was the most successful category in 3 of the 4 scenarios and MLP (Multi Layer Perceptron) algorithm which belongs to that category was the most successful classifier with the rate of 84.4%. Also, highest accuracy rates were between 83.4% and 84.8% considering all four scenarios. This shows that removing some of the parameters from the original parameter set does not have a significant impact on the classification accuracy. The study results have shown that machine learning techniques achieved good performance in predicting rainfall and could be used for that purpose. PubDate: Wed, 02 Mar 2022 00:00:00 +030
Authors:Emrullah SONUÇ; Esra ÖZCAN Abstract: Liquid raw iron is produced by using coke, sinter and other iron ore materials in the blast furnace facilities of an iron and steel factory with a basic oxygen furnace. The next step after the production, is the steelmaking process, and just before that, the liquid raw iron is processed in the desulfurization plant in order to reduce the available sulfur content by a certain amount. The purpose of this process, called desulphurization, is to achieve the target sulfur value by adding some desulfurization reagents. Different methods are used to determine the amount of material to be added. There are many studies in which basic and data-based models are applied in this desulphurization process. However, the use of artificial intelligence techniques in this area is quite limited. In this study, the material (magnesium, lime, fluorite) ratios in the desulfurization process were predicted by machine learning techniques. This problem is a regression problem and six different methods (Linear Regression, K-Nearest Neighbor, Decision Trees, Random Forest, XGBoost, Artificial Neural Networks) are tested on the dataset. The data used in the study belonged to the year 2020 and were taken from the desulfurization plant. 80% of the data is used for training and 20% for testing. Accuracy and Mean Absolute Percentage Error (MAPE) were used as evaluation criteria. According to the results obtained, Artificial Neural Network model obtained 85%, 95.4% and 80.14% accuracy for magnesium, lime and fluorite, respectively. The MAPE values are 14.99, 4.59 and 19.85, respectively, which shows that the model makes a successful prediction. PubDate: Wed, 02 Mar 2022 00:00:00 +030
Authors:Salih Serkan KALELİ; Mehmet BAYĞIN, Abdullah NARALAN Abstract: This study aims to examine, regulate, and update the land transportation of the Erzurum Metropolitan Municipality (EMM), Turkey using computerized calculation techniques. In line with these targets, some critical information has been obtained for study: the number of buses, the number of expeditions, the number of bus lines, and the number and maps of existing routes belonging to EMM. By using the information that has been obtained, this study aims at outlining specific outputs according to the input parameters, such as determining the optimal routes, the average travel, and the journey time. Once all of these situations were considered, various optimization algorithms were used to get the targeted outputs in response to the determined input parameters. In addition, the study found that the problem involved in modeling the land transport network of the EMM is in line with the so-called “traveling salesman problem,” which is a scenario about optimization often discussed in the literature. This study tried to solve this problem by using the genetic algorithm, the clonal selection algorithm, and the DNA computing algorithm. The location data for each bus stops on the bus lines selected for the study were obtained from the EMM, and the distances between these coordinates were obtained by using Google Maps via a Google API. These distances were stored in a distance matrix file and used as input parameters in the application and then were put through optimization algorithms developed initially on the MATLAB platform. The study’s results show that the algorithms developed for the proposed approaches work efficiently and that the distances for the selected bus lines can be shortened. PubDate: Wed, 02 Mar 2022 00:00:00 +030
Authors:Fatma BOZYİĞİT; Onur DOĞAN, Deniz KILINÇ Abstract: Customer feedback is one of the most critical parameters that determine the market dynamics of product development. In this direction, analyzing product-related complaints helps sellers to identify the quality characteristics and consumer focus. There have been many studies conducted on the design of Machine Learning (ML) systems to address the causes of customer dissatisfaction. However, most of the research has been particularly performed on English. This paper contributes to developing an accurate categorization of customer complaints about package food products, written in Turkish. Accordingly, various ML algorithms using TF-IDF and word2vec feature representation strategies were performed to determine the category of complaints. Corresponding results of Linear Regression (LR), Naive Bayes (NB), k Nearest Neighbour (kNN), Support Vector Machine (SVM), Random Forest (RF), and Extreme Gradient Boosting (XGBoost) classifiers were provided in related sections. Experimental results show that the best-performing method is XGBoost with TF-IDF weighting scheme and it achieves %86 F-measure score. The other considerable point is word2vec based ML classifiers show poor performance in terms of F-measure compared to the TF-IDF term weighting scheme. It is also observed that each experimented TF-IDF based ML algorithm gives a more successful prediction performance on the optimal subsets of features selected by the Chi Square (CH2) method. Performing CH2 on TF-IDF features increases the F-measure score from 86% to 88% in XGBoost. PubDate: Wed, 02 Mar 2022 00:00:00 +030
Authors:Ebru AYDINDAĞ BAYRAK; Pınar KIRCI, Tolga ENSARİ, Engin SEVEN, Mustafa DAĞTEKİN Abstract: Cancer is one of the most important diseases that cause the death of many people around the world. Especially, breast cancer is one of the most common diseases among women. For this reason, any development related to the diagnosis of cancer is critical for people to live healthy lives. Today, the use of machine learning methods makes great contributions to studies for the early diagnosis and prediction of cancer disease. In this study, five different machine learning methods such as k-Nearest Neighbor, Support Vector Machines, Naive Bayes, Decision Trees, and Artificial Neural Networks were applied on two other breast cancer datasets on the Kaggle platform. The obtained results were compared by giving accuracy values and confusion matrix values. The highest accuracy values were obtained in Artificial Neural Networks (ANN) method with an accuracy rate of 98.2456% in the first breast cancer dataset and 93.8596% in the second breast cancer dataset. PubDate: Wed, 02 Mar 2022 00:00:00 +030
Authors:Tuba KOC; Pelin AKIN Abstract: Education is the foundation of economic, social, and cultural development for every individual and society as a whole. Students are accepted to secondary education institutions with the high school entrance examination made by the Ministry of National Education in Turkey. In this study, the success rates of the students who took the high school entrance examination in Turkey's 81 provinces in 2019 were handled with the machine learning regression and beta regression model. The present paper aimed to model, predict, and explain students' success rates using variables such as divorce rate, gross domestic product, illiteracy, and higher education populations. Support vector regression, random forest, decision tree, and beta regression model were applied to estimate success rates. Two models with the highest R2 value were found to be beta regression and random forest models. When the prediction errors of beta regression and random forest model were examined, it seemed to be that the random forest model is relatively superior to the beta regression model in predicting the success rates. While the beta regression model was the best predictor of the success rates of Çanakkale province, the random forest model predicted the success rates of Ankara well. Also, it was seen that the variables found to be significant in the beta regression model for success rates were also crucial in the random forest model. It is recommended to use both the beta and random forest models to estimate the students' success rates. PubDate: Wed, 02 Mar 2022 00:00:00 +030
Authors:Mesut TOĞAÇAR; Kamil Abdullah EŞİDİR, Burhan ERGEN Abstract: Fake news is fabricated news that spread consciously or unconsciously through various communication channels and has no real share. Today, the masses receive most news on digital and social media. In such communication environments, where news can be transferred to the masses quickly, the accuracy of this news can often be abused. News of unknown origin can cause serious problems in societies by making disinformation or misinformation. Especially, fake news exposed to information pollution in the internet environment can show its effect on society very quickly. To prevent such problems in digital environments, an artificial intelligence-based approach that can grasp the accuracy of the news and confirm it quickly is proposed in this study. In addition, a classification analysis was performed using the Natural Language Processing (NLP) method, a sub-branch of artificial intelligence, to determine whether the news was real or false using the dataset that was accessible. The dataset consisted of 6335 news headlines and content. While 3171 of this news is real news; 3164 is fake news. In the analysis of the study, the Long Short Term Memory (LSTM) model was used together with the NLP method and the training of the dataset was carried out with this model. As a result, the overall accuracy success from the training data was 99.83%, and the overall accuracy success from the test data was 91.48%. These results show us that similar studies that we plan to think about in the future have been promising. PubDate: Wed, 02 Mar 2022 00:00:00 +030
Open Access journal
[187 journals]
