Yazar "Özhan, Erkan" seçeneğine göre listele
Listeleniyor 1 - 8 / 8
Sayfa Başına Sonuç
Sıralama seçenekleri
Öğe A COMPARISON OF THE THREE DIFFERENT TECHNIQUES IN PREDICTING BREAKING STRENGTH OF COTTON AND BLENDED WOVEN FABRICS(Chamber of Textile Engineers, 2024) Kastaci, Bilge Berkhan; Özek, Hikmet Ziya; Özhan, ErkanThe adaptation and utilization of artificial intelligence techniques for various demands of the textile and apparel industry has been gradually increasing. The use of such methods are particularly very useful when making predictions based on the past company data in the cases where statistical methods are likely to be insufficient. It is obvious that an accurate projection of both structural and performance properties of woven fabrics is extremely important in regard of fabric design. In this study, several models based on multiple linear regression, artificial neural networks and random forest algorithms were developed to predict the breaking strength of woven fabrics which is considered one of the most important performance characteristic. Industrial data comprising variables of 147 sets of pure cotton and 53 sets of polyester/viscose woven fabrics are used. Breaking strength of a fabric is very much effected by basic structural elements of the fabric. For the sake of revealing the best relationship between the breaking strength and variables of fabric, various explanatory variables influencing the fabric properties are taken into consideration and several models were developed by means of Minitab Statistics Program, Weka and R software and the overall results are compared. Among all the models created by the three different techniques, it was found that the regression and artificial neural networks models performed well in both cotton fabrics and blended fabrics, while random forest algorithms were not very accurate in estimating the breaking strength. © (2024), (Chamber of Textile Engineers). All Rights Reserved.Öğe Artificial intelligence-based scholarship and credit pre-assessment system(Institute of Electrical and Electronics Engineers Inc., 2017) Saatçı, Sercan; Cansız, Hande; Aslan, Gülşah; Özhan, ErkanScholarships are given to students who are studied in university by public institutions and organizations such as Yüksek Ögrenim Kredi ve Yurtlar Kurumu by taking different criterions into account. The students who deserve to have scholarship are detected by examining information in the forms that are given to student to detect the person who needs the scholarship. This process is causing time loose and also quite exhausting. On the other hand, it becomes too difficult to make objective decisions in some situations. Using artificial intelligence and machine learning in the process of detecting students who will be given scholarship is important to evaluate in both objective and subjective ways to students who apply. The data which are used in this study are collected from the internet and the purpose of this study is to detect the students who are studying in the university and given scholarship by answering the questions, which are prepared by Kredi ve Yurtlar Kurumu, with artificial intelligence and machine learning methods objective and subjectively in a correct way. © 2017 IEEE.Öğe Examining the Impact of Feature Selection on Classification of User Reviews in Web Pages(IEEE, 2018) Uzun, Erdinç; Özhan, ErkanThe user reviews in web pages can provide useful information about the content of the web page for text processing applications. Automatically extracting data from a web page is a crucial process for these applications. One of the used methods in this process is to construct a learning model with an appropriate classification method using features that are derived from data. However, some features can be either redundant or irrelevant for this model. In this study, an imbalanced dataset including 47 shallow text features obtained from web pages is utilized for extracting of the user reviews. Then, various well-known feature selection techniques are applied to reduce the number of these features. The effects of this reduction on the classification methods are also examined. The experimental results indicate that approximately half of the features are sufficient for the classification task. Additionally, the AdaBoost classifier gives the best results concerning precision of about 0.930 for the review layout prediction.Öğe Performance Evaluation of Classification Methods in Layout Prediction of Web Pages(IEEE, 2018) Özhan, Erkan; Uzun, ErdinçThe Web is an invaluable source of data stored on web pages. These data are contained in HTML layout elements of a web page. It is a crucial issue to extract data automatically from a web page. In this study, a dataset, which is annotated with seven different layouts including main content, headline, summary, other necessary layouts, menu, link, and other unnecessary layouts, is used. Then, 49 different features are computed from these layouts. Finally, we compare the different classification methods for evaluating the performance of these methods in layout prediction. The experiments show that the Random Forest classifier achieves a high accuracy of 98.46%. Thanks to this classifier, the prediction of link layout has a higher performance (approximately 0.988 f-Measure) according to the performance of the prediction of other layouts. On the other hand, the prediction of the summary layout has the worst performance with about 0.882 f-Measure.Öğe Renewable Energy Forecasting in Turkey: Analytical Approaches(Özer UYGUN, 2025) Colak, Mehmet Berke; Özhan, ErkanThe growing population and industrialization have resulted in an increased demand for energy, which has worsened environmental problems such as pollution and climate change. Renewable energy sources are considered a promising solution due to their environmental benefits and limited potential. This study examines the use of neural networks and time series analysis to predict electricity generation rates from renewable energy sources in Turkey. We use the LSTM, NNAR, and ELM models, all of which utilize the backpropagation algorithm for neural network forecasting. Additionally, we apply ARIMA, Holt’s trend, linear regression, mean, and exponential smoothing models for time series analysis. We evaluate the performance using the mean absolute error and root mean square error on the training and test data. The study showed that LSTM models outperformed the ARIMA (1,2,1), ARIMA (2,2,1), ARIMA (3,2,1), and NNAR methods in forecasting accuracy. Although the NNAR model initially had the lowest error, its linear predictions made it less suitable for practical applications. This study highlights the effectiveness of neural networks and time series analysis in predicting renewable energy sources. The ARIMA (1,2,1), LSTM and ARIMA (3,2,1) modeling methods are useful for optimizing the planning and management of Turkey's renewable energy future, contributing to a more sustainable energy landscape.Öğe The Analysis of Corporate Social Responsibility, Identification and Customer Orientation by Structural Equation Modelling and Artificial Intelligence(Sage Publications India Pvt. Ltd, 2021) Özhan, Şeniz; Özhan, Erkan; Yakar Pritchard, GamzeWhen the successful businesses of today are examined, it is seen that the main factor in their success is the value they give to the customers rather than the production power. One of the most important factors in ensuring customer satisfaction and loyalty is customer orientation (CO). In this study, it is aimed to investigate the perceived management and customer support for corporate social responsibility, the identification of the employees with the business and the customers and its effect on CO. Another aim of the study is to obtain a model that classifies employee–customer identification (ECI)-CO levels for employees by using artificial intelligence methods not used in previous studies. The research data were obtained from salesperson working in shopping malls in Istanbul. Hypothesis testing with structural equation modelling (SEM) has shown that perceived management and customer support for corporate social responsibility have an impact on employee identification with the business and customers. It has been observed that ECI affects CO, while organizational identification has no significant effect on CO. The structural equation modelling and artificial intelligence findings have empirically demonstrated that high accuracy practical classification models can be obtained and used to detect and solve different marketing problems. © 2021 Management Development Institute.Öğe The Analysis of Firewall Policy Through Machine Learning and Data Mining(Springer, 2017) Uçar, Erdem; Özhan, ErkanFirewalls are primary components for ensuring the network and information security. For this purpose, they are deployed in all commercial, governmental and military networks as well as other large-scale networks. The security policies in an institution are implemented as firewall rules. An anomaly in these rules may lead to serious security gaps. When the network is large and policies are complicated, manual cross-check may be insufficient to detect anomalies. In this paper, an automated model based on machine learning and high performance computing methods is proposed for the detection of anomalies in firewall rule repository. To achieve this, firewall logs are analysed and the extracted features are fed to a set of machine learning classification algorithms including Naive Bayes, kNN, Decision Table and HyperPipes. F-measure, which combines precision and recall, is used for performance evaluation. In the experiments, kNN has shown the best performance. Then, a model based on the F-measure distribution was envisaged. 93 firewall rules were analysed via this model. The model anticipated that 6 firewall rules cause anomaly. These problematic rules were checked against the security reports prepared by experts and each of them are verified to be an anomaly. This paper shows that anomalies in firewall rules can be detected by analysing large scale log files automatically with machine learning methods, which enables avoiding security breaches, saving dramatic amount of expert effort and timely intervention.Öğe Yapay Sinir Ağları ve Üstel Düzleştirme Yöntemi ile Türkiye'deki $CO_2$ Emisyonunun Zaman Serisi ile Tahmini(2020) Özhan, ErkanSera gazlarının atmosferdeki miktarı gün geçtikçe artmaktadır. Bu artışın başta küresel ısınma olmak üzere neden olduğu çok sayıdaolumsuz etki ortaya çıkmaktadır. Geleceğe dönük sera gazı emisyonunun tahminlenmesi özellikle karar alıcılar ve $CO_2$ salınımındapayı olan sektörler açısından bakıldığında bu salınımın azaltılması ve alternatif kaynakların aranması için cesaret verici olabilir.Zaman serileri zaman düzleminde düzenli olarak belirli aralıklarla elde edilmiş verilerin literatürdeki adıdır ve bu serilerin analizininnasılını inceleyen süreçlere ise zaman serisi analizi denir. Araştırmada Türkiye’ye ait sera gazı emisyonu ($CO_2$ eşdeğeri) değerleriniiçeren Dünya Bankası veri tabanındaki 55 yıllık verileri içeren veri seti kullanımıştır. Bu veri seti içerisinden yapay sinir ağları veüstel düzleştirme yöntemleri ile faydalı örüntüler elde edilmesi amaçlanmıştır. Analizler için zaman serisi formatına dönüştürülen veriseti daha sonra eğitim ve test verisi olarak iki bölüme ayrılmıştır. Zaman serisi tipindeki eğitim verileri üstel düzleştirme yönteminitemel alan Holt’un lineer trend modeli ve yapay zekanın alt dallarından biri olan yapay sinir ağları (YSA) ile analizi edilmiştir. Buanalizler sonucunda ortaya çıkan modellere göre eğitim ve test verileri üzerinden tahmin modelleri elde edilmiştir. YSA’nın veHolt’un lineer trend yönteminin test verileri için ortaya koyduğu tahminler ile modelleri değerlendirmek için RMSE, MAPE gibideğerlendirme metrikleri elde edilmiştir. Bu değerlere göre iki model karşılaştırılmış ve en az hata oranına sahip modelin YSA olduğutespit edilmiştir. Çalışmada elde edilen bulgulara göre YSA 0.1607’lik RMSE değeri ile, Holt’un liner trend yöntemine göre çok dahaaz hata oranına sahiptir. YSA’nın daha doğru tahminler yapacağı bulgusu elde edildikten sonra bu yöntemin önerdiği modelkullanılarak 2021 yılına kadar tahminler gerçekleştirilmiştir. Model Türkiye için 2021 yılı sera gazı eşdeğeri $CO_2$ emisyonunu366,3972 milyon ton olarak tahminlemiştir. Araştırmada görülen bir diğer sonuç ise $CO_2$ emisyonunun dalgalı bir seyir izlediği ancakgenel olarak yükselme eğiliminde olduğudur.
