Search

Occupational accidents occur in many sectors in Türkiye every year. In this study, which aims to evaluate occupational accidents occurring in the oil sector, accident estimation was made using artificial neural networks. Data on 2210 work accidents that occurred between 2020 and 2023 in a company operating in the oil sector were used. In this study; Artificial neural network modeling was done with monthly accident data. In the study, Multilayer Perceptron Artificial Neural Networks (MLPANN) and Radial Basis Function Artificial Neural Networks (RBFANN), which are feed-forward networks, were used. 70% of the data is divided as training data and 30% as test data. As a result of the analysis; An 84.1% correct classification rate was obtained with the MLPANN method, and an 86.4% correct classification rate was obtained with the RBFANN method. It can be said that the RBFANN method performs more successfully than the MLPANN method. lt is suggested to use the methods in order to estimate the occupational accidents . [ABSTRACT FROM AUTHOR]

Copyright of International Journal of InformaticsTechnologies is the property of Institute of Informatics, Gazi University and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Duzce University Journal of Science & Technology is the property of Duzce University Journal of Science & Technology and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Objective: Sex determination has been found interesting in forensic handwriting examinations and has been researched by scientists. The inclusion of the sex parameter as a supporting element in the examination of forensic handwriting while deciding belonging will increase the reliability of the results. In addition, it will help reduce the number of people to be investigated for a large group of suspects, both men and women. In this study, it was aimed to investigate the contribution of the ascender and descender parts of the letters to sex prediction by measuring them. Methods: In line with this purpose, handwriting samples were collected from 50 female and 50 male participants by having them write 11 sentences containing the letters “b, d, f, g, h, k, t, y, p” at initial, medial, and end positions. The ascender and descender parts of these letters were measured in millimeters. Logistics, k-nearest neighbor (KNN), support vector machine (SVM) and artificial neural network (ANN) were selected and applied to these data. Results: The ascender and descender parts of these letters were measured in millimeters and statistically significant differences were found between male and female participants. The ascender parts of the “b, d, h, k, t” were determined to be statistically significantly longer in males. Accuracy rates are 0.65, 0.60, 0.71 and 0.82 for Logistics, KNN, SVM and ANN, respectively. Conclusion: In our opinion, this result is promising. If the studies on this subject are increased, higher success rates can be achieved, and more contributions can be made to forensic handwriting examination.

Copyright of SDU Journal of Engineering Sciences & Design / Mühendislik Bilimleri ve Tasarım Dergisi is the property of Journal of Engineering Sciences & Design and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

In today's competitive conditions, it has become important for investors to make accurate predictions from data. The diversity of data because of developments in information and technology has led to the need for modern statistical techniques. With these techniques, identifying and estimating unknown hidden relationships in the data is increasing day by day. Data mining is used in many fields, as well as in the field of finance. The data set used in this study consists of 1.423 trading days published between January 2, 2018 and June 27, 2023. The Fp Growth Algorithm was used to determine the co-change between the BIST30 Index, BIST100 Index, Dollar Rate, Euro Rate, Gold, and Brent Oil variables published in the daily bulletins, through association rule analysis, which is a descriptive model in data mining. After conducting the association analysis, a total of 20 association rules were generated, and the top 10 association rules were selected. OIL, GOLD, BIST30, BIST100 variables at 0.99 confidence criteria, and 0.98 confidence criteria; OIL, EURO, BIST30, BIST100 variables, in 0.97 confidence criterion, there is a significant association between USD, EUR, BIST30, BIST 100 and USD, GOLD, BIST30, BIST 100, as well as EUR, BIST30, BIST 100 and USD, BIST30, BIST 100 seen. [ABSTRACT FROM AUTHOR]

Emtialar, yatırımları çeşitlendirmek ve enflasyona karşı korunmak için alternatif bir yol olarak görülmüştür. Bu nedenle yatırımcıların bir piyasanın düşüşü veya yükselişi sonrasında diğer piyasaların veya finansal varlıkların hangi yöne doğru hareket edeceğini öngörmesi, hızlı ve etkili kararlar almasında kritik öneme sahiptir. Bu çalışmada, emtia piyasalarının birlikte hareketi veri madenciliğinde yer alan birliktelik kuralı ile analiz edilmiştir. Bu doğrultuda çalışmada 20 adet emtianın 01.01.2010-01.08.2023 tarihleri arasındaki 3216 işlem günündeki birlikte hareketleri analiz edilmiştir. Çalışmada birliktelik kuralı analizleri, Apriori ve FP-Growth algoritmaları kullanılarak gerçekleştirilmiştir. Hem Apriori hem de FP-Growth algoritmaları ile üretilen birliktelik kurallarının tümünde Brent petrolün diğer emtialara eşlik ettiği gözlemlenmiştir. Bu sonuç, Brent petrol fiyatlarının yukarı veya aşağı yönde hareketinin, Brent petrol fiyatlarını yakından takip eden yatırımcılara, karar vericilere ve politika yapıcılara, diğer emtiaların hareketi ile ilgili yol gösterici olabileceğini göstermektedir. Petrolün ekonomik sistemi etkileyen stratejik bir enerji kaynağı olduğu gerçeği göz önüne alındığında, bu sonucun şaşırtıcı olmadığı ifade edilebilir.

Günümüzde üniversite öğrencilerinin eğitime ve eğitim materyallerine internetten erişim oranları oldukça artmıştır. Eğitimde internetin kullanılması ve ders materyallerine erişimin artmasına bağlı olarak analiz edilebilecek veri setinde artış meydana gelmiştir. Bu veri setlerinden bir tanesi de (planlı veya acilen) uzaktan eğitim sürecine geçen üniversitelerin, uzaktan eğitim sistemlerinde biriken ödev, sınav, proje, performans, devam notları ve benzeridir. Yeni Korona Virüs (Covid-19) pandemisinde Yüksek Öğretim Kurumu’nun (YÖK) tavsiyesi ile üniversiteler eğitimlerine uzaktan Asenkron, Senkron ve Hibrit yöntemlerini kullanarak devam etmiş, hatta sınavları uzaktan eğitim sisteminde yapmak zorunda kalmışlardır. Bu araştırmada, Kayseri Üniversitesinin Uzaktan Eğitim Uygulama ve Araştırma Merkezi (KAYUZEM) sisteminden alınmış veriler kullanılmıştır. Araştırma kapsamında 8319 işlenmiş veri bulunmaktadır. Bu veriler üzerinde Veri Madenciliği (VM) alanında kullanılan RapidMiner programının otomatik modelleme özelliği kullanılarak varsayılan algoritmalarla geleceğe yönelik tahminleme işlemi yapılmıştır. Varsayılan algoritmalar arasından en iyi sonucu veren Derin Öğrenme, Naive Bayes, Gradient Boosted Trees, Lojistik Regresyon kullanılmış ve bu otomatik modelleme de yer almayan k-En Yakın Komşu (k-NN) algoritması da çalışmaya dahil edilmiştir. Bu 5 algoritmanın parametreleri üzerinde değişiklikler yapılarak daha iyi sonuçlar elde edilmeye çalışılmıştır. Öğrenci başarısına göre en iyi tahminleme sonucunu, Lojistik Regresyon ile kurulan model vermiştir. Derse katılma yöntemlerinin tümünün (Senkron, Asenkron ve Hibrit) öğrenci başarısına etkisi Karışıklık Matrisi yöntemiyle karşılaştırılmıştır ve en güvenilir yöntemin Hibrit olduğu görülmüştür. Bu çalışma ile üniversitelerde derse katılma yöntemlerinden hangisinin, öğrenciler açısından daha güvenilir olacağına yönelik çıkarımlarda bulunulmuştur. Dolayısıyla yapılan çıkarımlar ile birlikte bir dahaki akademik dönem için öğrenci başarı düzeyinin artması yönünde, derse katılma yöntemlerinden hangisinin daha güvenilir olduğu konusunda tahminleme mümkün olmuştur.

Globally, the impact of the automotive industry on the economy and our daily existence is enormous, in both directions. Not only do they function as transportation, but far beyond that, vehicles have also become data generating machines. Manufacturers or dealers keep various records and collect statistics, including categories such as model types, production rates, etc.; odometer readings of the distance driven, purchase costs or repair/maintenance expenses, cost factors related to initial or long-term vehicle ownership, engine characteristics such as fuel type/horsepower/overall volume, transmission characteristics at downshift points and more. In this study, association analysis was performed with the Apriori algorithm, one of the data mining methods, using vehicle data from the automobile sector. A total of 634 cars were analyzed based on nine different categories: model, production category, mileage category, price category, engine size category, horsepower category, fuel type, cost category, and transmission type. The data was collected from a publicly accessible source. The Apriori algorithm was used to identify the strongest relationships between these attributes. The results show that vehicles in the high-cost category generally have gasoline fuel type, while vehicles in the new production category are generally in the low range category. In addition, the vehicles in the manual transmission type were found to be mostly gasoline. Vehicles in the low-cost category were generally found to have diesel fuel type. The 634 vehicles analyzed cover a wide range of models and categories. In particular, the strong relationship between fuel type and cost category suggests that gasoline vehicles are usually in the high-cost category. In addition, vehicles in the new production category are in the low-walk category, indicating that these vehicles are generally less used or newer. These findings offer new insights on the automotive industry and consumer behavior and can help vehicle manufacturers and dealers to better understand potential customer preferences. This study highlights the importance of extracting information from large data sets and supporting decision-making processes. [ABSTRACT FROM AUTHOR]

Copyright of Duzce University Journal of Science & Technology is the property of Duzce University Journal of Science & Technology and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Journal of Research in Economics, Politics & Finance / Ekonomi, Politika & Finans Arastirmalari Dergisi is the property of Journal of Research in Economics, Politics & Finance and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

In the field of after-sales services in the furniture sector, it is aimed to increase customer satisfaction by responding to customers' calls for spare parts (repair-maintenance process using spare parts) in a shorter time, that is, by supplying spare parts in a shorter time and sending them to the relevant region, by performing repair-maintenance operations on their products in a shorter time. After all spare parts under the same call number reach the area, the customer's problematic product can only be repaired. The determination of the items that were taken together as an order under the same call number was made with the help of the Weka package program, with the help of data mining association analysis application. In order to increase customer satisfaction in the after-sales services sector, which is gaining importance day by day and is now accepted by everyone as being as important as production, the practice of keeping spare parts stock by making association analysis is the first application in this field. The association analysis study also has quite different application and usage areas. At the end of this study, an improvement of 19.3% was achieved in the spare part collection time from the warehouse. [ABSTRACT FROM AUTHOR]

The present study aims to investigate the impact of organizational psychological capital, organizational citizenship behaviour, individual performance and various demographic variables on school principas’ burnout in public schools. The opinions of princals working in Diyarbakır province and districts between the years of 2016- 2017 were considered. This research employed a survey model, which falls under the quantitative research paradigm. Data were collected from 254 principals through the administration of the Organizational Psychological Capital Scale, Organizational Citizenship Behaviour Scale, Individual Performance Scale, and School Principal Burnour Scale. The collected data were analyzed using the Extreme Gradient Boosting (XGBoost) mining method. The findings revealed several key predictors of principals’ burnout, including altruism, resilience, professional seniority, individual performance, civic virtue, type of school, hope, sportsmanship, school principal’s length of service, marital status, optimism and the district of the school. Based on these results, it is recommended to alleviate principals’ burnout by reducing their responsibilities and creating conducive environments that foster their leadership roles.

Copyright of SDU Journal of Engineering Sciences & Design / Mühendislik Bilimleri ve Tasarım Dergisi is the property of Journal of Engineering Sciences & Design and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Journal of Traffic & Transportation Research / Trafik ve Ulaşım Araştırmaları Dergisi is the property of Journal of Traffic & Transportation Research and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Sosyal Güvence Dergisi is the property of Sosyal Guvenlik Uzmanlari Dernegi and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of International Journal of Engineering Research & Development (IJERAD) is the property of International Journal of Engineering Research & Development and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of International Journal of Engineering Research & Development (IJERAD) is the property of International Journal of Engineering Research & Development and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Online Journal of Art & Design is the property of Online Journal of Art & Design and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

The aim of this study was to evaluate the factors of affecting watermelon yield in Diyarbakır province. The data was obtained from surveying of 80 watermelon farmers in Diyarbakır province, Turkey by Simple Random Sampling Method using the Chi-square automatic interaction detector (EXHAUSTIVE CHAID) algorithm of the Data Mining Regression Tree methods. In the model created, the dependent variable was WY (watermelon yield), and the independent variables were determined as R (region), AF (age of farmer), EL (education level), CA (cultivation are), FD (fertilization date), FA (amount of fertilization), DS (date of spraying), AS (amount of spraying), NI (number of irrigation), IT (irrigation time), AN (anchor number), HT (harvest time). As a result of the study, the factors that significantly affect the yield of watermelon; AN, NI, HT, CA, R has been determined. An average of 4488.9 kg watermelon yield per decare was obtained and the number of hoes was the variable that most affected the watermelon yield. As a result in order to get a higher yield per unit area, watermelon producers should anchor number more than 4 times, irrigate 5 to 6 times at less than 2 hours, and apply fertilizer in May. In addition, Çermik, Eğil, Yenişehir and Bismil were determined as more suitable regions for watermelon production. [ABSTRACT FROM AUTHOR]

Nowadays, with the widespread use of e-commerce, online sales are becoming more and more important for businesses. This increase in the use of e-commerce brings with it the question of what factors may affect the use of e-commerce by consumers. In this study, the features that affect the e-commerce usage frequency of individuals in Turkey are analyzed with decision trees and Support Vector Machine (SVM) algorithms and interpreted. In addition, a classification model has been designed to predict e-commerce usage frequency of individuals by using variables that affect e-commerce usage. According to the results of the study, the most important variable which affects the e-commerce usage frequency in CHAID, C&R Tree and QUEST algorithms has been determined as the number of purchases of goods or services over the internet for private use in the last three months. While variable of age has been the second most important variable in CHAID and QUEST algorithms, the variable of sending/receiving e-mails for special purposes (including mobile applications) in the last three months has been the second most important variable in the C&R Tree. For e-commerce usage frequency estimation, the CHAID algorithm has given the best classification result with an accuracy rate of 86.19%. [ABSTRACT FROM AUTHOR]

Copyright of Ankara Üniversitesi Dil ve Tarih-Cografya Fakültesi Dergisi DTCF Dergisi is the property of Ankara Universitesi Dil ve Tarih-Cografya Fakultesi (DTCF Dergisi) and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

With the rapid developments in information and communication technologies with globalization, the importance of the concept of Management Information Systems is increasing. The main reasons for MIS to gain importance can be listed as the fact that decisionmaking becomes increasingly difficult due to many factors that have an impact on the problems encountered, the increase in factors that need to be evaluated, and the desire to access information in a timely and accurate manner. In this study, the study areas of the first 300 academicians who have published in the field of Management Information Systems, which has shown a rapid development in recent years, were determined and the areas that were studied frequently were tried to be determined. At the same time, it was aimed to determine the relationships between keywords by examining a total of 121 articles published in 2022 in the Journal of Management Information Systems and MIS: Quarterly, scanned in SCIE, SSCI and Web of Science in the field of MIS. In this context, analysis was carried out with the association rules determined using the Apriori algorithm. As a result of the analysis, the academicians who published in the field of E-Government, in the field of E-Commerce (support=0.0132, confidence=0.4, lift=9.2615); it has been concluded that academics who have published in the field of Information Security, Data Analytics, ERP, Data Mining also work in the field of Management Information Systems. In addition, most of the academics working in these fields have the nationality of the United States of America, Turkey and Jordan, respectively. For keywords; it has been determined that academics using the keyword Dark Web are working in the field of Cyber-Security Analytics (support=0.0165, confidence=1, lift=60.5), and academics using the keyword Design Science are working in the field of Cyber-Security (support=0.0165, confidence=0.6666, lift=26.8888). [ABSTRACT FROM AUTHOR]

Data mining (DM) includes techniques for finding meaningful information hidden in these massive data stacks. The aim of this study is to divide the countries according to their prosperity levels with Cluster Analysis (CA), which is one of the DM techniques. In this context, the 2019 data of 167 countries within the updated 12 prosperity indicators in The Legatum Prosperity Index (LPI) were used. Countries were divided into clusters with the Ward's algorithm, and the Elbow method was used for verifying of the optimal cluster number. The similarities between the countries were determined with the K-Means, and Turkiye's place in the clusters was determined. The results show that countries are divided into three clusters. The most significant indicators in separating them into clusters are "market access and infrastructure, education, investment environment", and the least significant indicators are "social capital, natural environment, safety and security". It has been determined that Turkiye is located in the middle prosperity level cluster and its "health, living conditions, education" indicators are the highest, while its "natural environment, personal freedom, management" indicators are the lowest.

This paper analyzes the contributions of features widely used in the automatic classification of students’ academic performance. In this classification problem, the relationship between various features and classifiers is analyzed using an exhaustive feature selection strategy. In this way, the optimal subset of features providing the highest classification performance is obtained. For this purpose, an academic performance dataset consisting of 15 distinct features and 480 samples is used. The features mainly belong to four different categories, including demographic, academic background, parent participation, and behavioral. The samples are from three different classes corresponding to the low, middle, and high levels of students’ success. For evaluations, 10 different classification algorithms are employed. Extensive experimental analysis reveals that the accuracy of the classification of students’ academic performance can be improved up to 79.40% using only 8 features rather than all.

Bu çalışma perdesiz betonarme konut binalarına etkiyen yatay tasarım deprem yükünün veri madenciliği yöntemleri ile analiz edilmesi ve makine öğrenmesi yöntemleri ile tahminlenmesi konusundadır. Bu amaçla Türkiye Bina Deprem Yönetmeliği’ne (2018) göre eşdeğer deprem yükü yöntemi kullanılarak veri seti oluşturulmuştur. Oluşturulan veri seti üzerinde öznitelik seçimi, uç değerlerin tespit edilmesi ve silinmesi, boyut azaltma gibi veri madenciliği yöntemleri kullanılmış hangi yöntemlerle sonuçların nasıl değiştiği tartışılmıştır. Sonuçlar perdesiz betonarme binalara etkiyen deprem kuvvetinin makine öğrenmesi yöntemleri ile başarılı tahmini için kısa periyot harita spektral ivme katsayısının (SS) ve bina toplam yüksekliğinin (HN) gerekmediğini ortaya koymuştur.

Amaç: Bu çalışmada Dünya Bankası sitesinde yer alan açık veri kaynağında sağlık göstergeleri olarak bulunan 30 adet değişken kullanılmış ve G-20 ülkelerinin sağlık sistemlerinin performansları değerlendirilmiştir. Yöntem: Sağlık göstergeleri için 2000-2018 yılları arasında toplam 19 yıllık veri kullanılmıştır. Oluşan veri sayısının fazla olmasından dolayı kümeleme analizi ile sınıflandırma yapılabilmesi adına veri madenciliği yöntemleri kullanılmıştır. Kümelerin performanslarının değerlendirilmesinde öncelikle ağırlıkların belirlenmesi için sağlık göstergeleri önem derecesine göre uzman kişiler tarafından gruplandırılmış ve sıralanmıştır. Elde edilen değerler ile çok kriterli karar verme tekniklerinden MAUT yöntemi kullanılarak kümelerin performansları değerlendirilmiştir. Bulgular: Kümeleme analizi sonucunda ülkelerin 4 farklı kümede sınıflandıkları görülmüştür. Sağlık göstergeleri açısından “Çok Yüksek” performansa sahip olan ülkeler Çin ve Güney Kore’dir. “Yüksek” düzeyde performansa sahip olan kümede yer alan ülkeler; Almanya, Amerika, Avustralya, Fransa, İngiltere, İtalya, Japonya, Kanada ve Rusya şeklindedir. “Ortalama Üstü” düzeyde performansa sahip olan kümede yer alan ülkeler; Arjantin, Brezilya, Meksika, Suudi Arabistan ve Türkiye’dir. “Düşük” performansa sahip olan kümede yer alan ülkeler; Endonezya, Güney Afrika ve Hindistan’dır. Özgünlük: Uygulama sonucunda ülkelerin bulunduğu kümeler arasında sağlık alanındaki yetersizlikleri açık şekilde görülebilmiştir. Böylece yapılması gereken iyileştirmeler açısından karar vericiler için ortak bir planlama alanı oluşturulmuştur.

MR spectroscopy (MRS) is a critical imaging modality in brain tumor detection, in which brain metabolites other than water and fat can be measured. Along with the advances in artificial intelligence and data mining, it is seen that computer aided diagnosis (CAD) systems are widely used in medicine. The high achievements achieved have a positive effect on medical diagnosis and treatment processes by providing time saving for CAD applications. Deep learning, based on classical classification methods, the results are more successful on the data, and with high classification ability is the artificial intelligence algorithm. In this study, it was aimed to develop a CAD system to assist physicians in tumor detection by using the ratios of Choline (Cho), creatine (Cr) and N-Acetyl Aspartate (Naa) metabolites (Cho/Cr, Cho/Naa and Naa/Cr) obtained by MRS. For classification data, four classical data classification methods were used, which are deep learning application, Long Short-Term Memory (LSTM) and comparison. While the class performance results obtained with K-Nearest Neighborhood (KEYK), Support Vector Machine (SVM) and Decision Trees (DT) were found to be around 83±6,36 % from classical methods, this value was obtained as 93% with the LSTM-based deep learning method proposed in the study. This shows that deep learning can be used in a CAD system that can assist the experts in the relevant field in the decision-making process in classifying MRS data by demonstrating high classification performance. [ABSTRACT FROM AUTHOR]

Effective warehouse management has become one of the most important goals of businesses with the development of technology. The realization of these goals will be possible by using the data in the hands of the businesses to extract meaningful information and to use this information in warehouse management. One of the most important functions of warehouse management is product placement. Improper product placements cause time and financial losses for businesses. Scope of work; it is aimed to develop a dynamic product analysis model based on output orders. In the first stage of the study, ideal periods were determined by using the standard deviation technique. In the second stage of the study, the waiting times of the products were calculated with the technique of holding time in stock. In the third stage of the study, the products were ranked according to their stock keeping times. Afterward, the locations divided into Pareto-based Diamond, Gold and Silver regions were matched with the products in the warehouse. In the fourth stage of the study, the Apriori algorithm technique, which is one of the data mining models, is the most accepted in the literature, was used. The association analysis of the data was carried out and the collection bin locations of the products were determined by placing the products that go frequently in the same region side by side. As a result of the study, it is aimed to contribute to the businesses engaged in storage activities and researchers working in this field in determining a model that they will benefit from in the product placement processes. In this study, product tonnage information or product output information, which is frequently encountered in the literature, is not taken as a basis for product analysis, and the stock keeping time and go-with feature of that product are taken as the basis. Thus, a new and effective perspective has been gained to the literature. [ABSTRACT FROM AUTHOR]

With the Covid-19 that emerged in 2019, the education system was greatly affected. The face-to-face education system all over the world was suspended for a while. In many countries, especially in our country, a hybrid education system has been introduced in universities. Istanbul Aydın University English Preparatory Program student notes were examined and data mining methods were used in data analysis. The aim of this study is to analyze the success of the preparatory program students. For this purpose, modeling was carried out with the help of machine learning algorithms, taking into account the student success criteria. The methods used in this study, decision trees, support vector machines and nearest neighbor algorithms were used, different results were obtained by changing the parameters. The data used to teach the model during the studies are the notes taken by the preparatory class students in face-to-face education. It was estimated whether the students would be successful in the online education process, and then they were compared with the online education grades and the success of the model was determined. [ABSTRACT FROM AUTHOR]

The effect of foreign exchange markets, commodity markets and stock market indices of developing countries on Bist100 is very important. The economies of the countries are strongly dependent on the economies of both their own and other countries, and therefore the markets are affected. Forecasting methods are used to follow the market economically and to make correct decisions. The dataset consists of closing data between January 2017 and October 2021. In order to ensure objectivity in experimental studies, a k=5 and 10-fold cross-validation model was applied. In comparison of models; Mean Absolute Error (MAE), Relative Absolute Error (RAE), Root Mean Square Error (RMSE) and long short-term memory (LSTM) were used. As a result of experimental studies, it has been seen that the LSTM model gives better results than machine learning models. When the test results for the LSTM model are examined, the MAE value is 10.27, the RMSE value is 14.15, and the RAE value is 6.06. [ABSTRACT FROM AUTHOR]

There is an enormous amount of data on the Internet. If desired, these data can be obtained by a method called web mining/scraping and can be used in information extraction. This research was carried out to obtain data about Turkish cinema by using web mining and to obtain various findings about Turkish cinema as a result of analyzing this data with text mining. In the text mining conducted on a total of 8596 TV and cinema films, it is seen that highest audience score belongs to the films Hababam Sınıfı (1975, p. = 9,3), Tosun Paşa (1976, p. = 9,0), 25 Liters (2019, p. = 8,9), respectively. It is seen that 13 of the 20 highest-rated films were made in the period called Yeşilçam in Turkish Cinema. 13 of these films were made in the Comedy genre. The list includes 8 films by Ertem Eğilmez, 2 films by Kartal Tibet and 2 films by Atıf Yılmaz as directors. After 1950, the year in which the most films were made in Turkish cinema was 1975 (275 films), while the year in which the fewest films were made was 2002 (20 films). Web mining method offers an alternative data acquisition method that can be used in many areas to obtain data on the internet with robot software or programming languages. This method has been used as an example to obtain various information about Turkish Cinema. The Internet has rich content that can be used in scientific research with big data sources. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Statistical Research / İstatistik Araştırma Dergisi is the property of Turkish Statistical Institute and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of SDU Journal of Engineering Sciences & Design / Mühendislik Bilimleri ve Tasarım Dergisi is the property of Journal of Engineering Sciences & Design and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Turkish Studies - Economics, Finance, Politics is the property of Electronic Turkish Studies and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Purpose: In this study, a content analysis of a platform that publishes content on the internet about blockchain technologies was made. The study aims to determine the factors (word and word string) affecting the reading rate of the digital content -on a titles basis- posted by the platform on Facebook. Method: 500 out of 2206 examples of content published between the specified dates were chosen randomly. The titles of the content were processed using standard text mining techniques and a new approach specific to the problem in this study on python programming language and then two different datasets were collected. The datasets were analysed using multiple linear regression. Findings: As a result of the analysis, it was discovered that some words and phrases used in the content titles affected the reading rate of the content. In addition, it has been determined that the new approach provides higher performance than standard text mining techniques. Implications: In this study, valuable information was obtained by processing raw data. As a result of the study, the theory was compared with the practice, and it was observed consistent results. It is determined that the new approach can be used effectively in similar text mining problems. Originality: The research relying on text mining was handled with a new approach on the basis of the content title. In this respect, the study has a unique quality. [ABSTRACT FROM AUTHOR]

One of the most important strategic decisions taken by company managers at corporate level is in which areas to invest and how to manage and organize investments. Strategic management proposes portfolio analysis techniques in this regard. It is stated that portfolio analysis techniques, which have been criticized at many points, should be considered as initial techniques and should be supported by other techniques in practice. At this point, the question of whether or not data mining techniques will be used to identify new investment areas and allocate resources has constituted the main problematic of this study. In this study, it has been investigated whether there are association rules between investment areas thus, it is tried to reach the evaluations that may affect the strategic decisions in the process of determining investment areas, by using data belonging to various investor organizations. For this purpose, Association Rules Mining was conducted using data from 102 holding companies. As a result of the study, 35 rules were produced above the 50% confidence level. It is presented as a suggestion to the enterprises in which they can benefit from these rules in their investment planning.

Son yıllarda internete erişim imkanlarının artması ve kullanıcılardaki akıllı telefon kullanımının yaygınlaşması sebebiyle sosyal medya olarak adlandırılan ve insanların çeşitli konulardaki fikirlerini paylaştığı servisler çok yaygın olarak kullanılmaktadır. Sosyal medya verilerinin analiz edilmesiyle insanların farklı konulardaki duygularına dair anlamlı çıkarımlarda bulunulması anlamına gelen ve temelde bir sınıflandırma işlemi olan Duygu Analizi çalışmaları son yıllarda öne çıkan çalışma alanlarından biridir. Bu çalışmada, Python programlama dili içindeki kütüphaneler kullanılarak Naive Bayes (NB), Logistic Regression (LR), Support Vector Machine (SVM), Decision Tree (DT), Random Forest (RF) ve Artificial Neural Network (ANN) gibi 6 adet sınıflandırma algoritmasının Duygu Analizi kapsamında, performans karşılaştırması yapılmıştır. Veri seti olarak, açık kaynaklı, IMDB sitesinde yer alan etiketli kullanıcı yorumları kullanılmıştır. Doğal Dil İşleme yöntemleri kullanılarak temizlenen veri setinin sayısal olarak temsil edilebilmesi için Bag of Words (BoW), TF-IDF, FastText ve Word2Vec metin temsil yöntemleri kullanılmıştır. Veri setinin eğitimi ve test edilmesi aşamasında k=5 olacak şekilde k-fold cross validation yöntemi kullanılmıştır. 6 farklı sınıflandırma yöntemi için elde edilen sonuçlar accuracy, precision, recall ve f1 score hesaplanarak ayrıntılı bir karşılaştırma yapılmış ve sonuçlar kaydedilmiştir. En yüksek accuracy değerleri olarak LR ve SVM sırasıyla BOW’da %86, TF-IDF’te %87, word2Vec’de %87 ve FastText’te %83 seviyelerinde benzer sonuçlar vermiştir.

This study examines the level of development of countries with the Human Development Index and the Gender Development Index, which are indicators that measure socioeconomic development at national level and compare the differences between economies. Which variables are influential in the grouping of countries is being investigated through a two-stage clustering analysis, one of the data mining techniques All data used in the study are obtained from the United Nations Development Program (UNDP) Analyzes were conducted with 2268 observation for 189 countries published by UNDP for 2019 According to the results of the Human Development Index, countries are grouped into three groups: countries with high, medium and low development indexes According to the results of the Gender Development Index, countries are grouped into five groups: countries with high, high-medium, medium, medium-low and low development indexes. It has been determined that the number of groups determined for the Human Development Index is different from the number of groups announced in the UNDP report, and the number of groups for the Gender Development Index is the same as the report. In general, the results show that women live longer than men, the education level of men and women is almost the same, and men have a higher national income than women. Thus, the effect of the gender factor on the development index was revealed. [ABSTRACT FROM AUTHOR]

Copyright of Dicle University Journal of Engineering / Dicle Üniversitesi Mühendislik Dergisi is the property of Dicle Universitesi and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Dokuz Eylul University Muhendislik Faculty of Engineering Journal of Science & Engineering / Dokuz Eylül Üniversitesi Mühendislik Fakültesi Fen ve Mühendislik Dergisi is the property of Dokuz Eylul Universitesi Muhendislik Fakultesi Fen ve Muhendislik Dergisi and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

It is thought that data mining can solve many problems in visible light communication. In the VLC systems, different receiver and transmitter units are usually designed for each modulation technique. Here, the proposed systems are designed for shortened pulse position modulation. In the paper, K-Nearest Neighbor algorithm and Decision Trees based demodulators that can be applied to synchronous modulation techniques are proposed. Afterwards, a generalized entropy expression is obtained for M-SPPM signals. Additionally, demodulators that can decode signals according to the Manhattan and Minkowski distance and other demodulators are compared in terms of accuracy and bit error rate. From the numerical results, it can be seen that the proposed KNN and Decision Trees based demodulators can be used as traditional systems for synchronous modulation techniques. Furthermore, it is seen that bit error rate performances and accuracy rates of the proposed KNN based demodulator and decision trees based demodulator that is optimally designed are completely the same. In 4-SPPM signals, it is seen that the accuracy of KNN (Demodulator-1) and Decision Trees (Demodulator-3) is 98.78% for SNR=10 dB. Here, the accuracy of the KNN (Demodulator-2) and Decision Trees (Demodulator-5) is 99.07% for 8-SPPM signals. [ABSTRACT FROM AUTHOR]

Machine learning did not become widespread until the 1990s when data mining began to be used. In this study, the numerical data collected from the Central Bank of the Republic of Turkey has been divided into sections according to data groups by data mining. The algorithms used for machine learning are decision support trees, linear regression, support vector machines, gaussian regression. Exchange rate models were created by using the data for the period of January 2020 -May 2021. Four different machine learning methods were used for 1352 exchange rate data, and they were classified as 99.84% accurate in the first method, 99% in the second method, 93.72% in the third method, and 86.83% in the fourth method. It develops strategies and plans according to the highest accuracy rate Evaluations in the construction of prediction programs of data mining and machine learning methods will be useful for future applications. The results were analyzed by comparing the accuracy rates of the methods used in the literature. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Abant Social Sciences / Abant Sosyal Bilimler Dergisi is the property of Journal of Abant Social Sciences and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Verimlilik Dergisi is the property of Verimlilik Dergisi and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Çağımızda bilginin dijital dünyadaki varlığı her geçen gün daha çok hissedilmektedir. Dijital ortamda dolaşan bu bilgiler işlenip nitelikli bilgiye dönüştürüldüğünde gelişen teknoloji çağına katkı sunacaktır. Bu noktada büyük miktardaki bilgiyi yapılandıran veri madenciliği yöntemleri ve algoritmik araştırmalar devreye girmektedir. Veri madenciliği, fen bilimlerinden sosyal bilimlere birçok sahada kullanılan ve kullanılması muhtemel yöntemlerden biridir. Pek çok ilmî disiplinde karşımıza çıkan bu yöntemlerin özellikle son yirmi yıldır hadis alanında da yapıldığı görülmektedir. Bu çalışmada dünya üzerinde veri madenciliği yöntemlerini ve algoritmik araştırmaları hadis ilmine uygulayan ve en çok atıf alan bilimsel makaleler incelenmiştir. Şu ana kadar yapılan çalışmalar hadisin metnine, ricâline, sıhhatine yahut web ortamındaki kullanımına odaklanmaktadır. Bu araştırmaların bir kısmı genel olarak hadisleri konularına göre tasnif etmeyi, özel olarak hadis sözlükleri oluşturmayı hedeflemektedir. Öte yandan seneddeki râvi zincirini ve sahih hadisi formüle ederek hadisin sıhhat tespitini sistemleştirmeye yönelik çalışmalar da bulunmaktadır. Ayrıca sosyal ağ grafikleri oluşturmak suretiyle râviler üzerine incelemelerde bulunan araştırmalara rastlanmaktadır. Bu araştırmalar fen bilimlerinde olduğu gibi hadis ilmindeki verilerin yapılandırılarak hesaplanabilir ve nesnel bir şekilde ortaya konulmasına fırsat sunmaktadır. Esasında asırlar önce sünnetin unutulmasının ve tahrip edilmesinin önüne geçmeyi amaçlayan muhaddisler de hadis ilmine dair edindikleri bilgileri ölçmeye ve değerlendirmeye çalışmışlardır. Bu muhaddislerden bizlere hem hadisin ricâli hem de metni konusunda kimi zaman üzerinde ittifak edilen kimi zaman münferit öznel değerlendirmeler ulaşmıştır. İşte bu noktada veri madenciliği teknikleri ve algoritmik araştırmalar kimi zaman yoruma dayalı ve kendini tekrar eden malumatları somut verilere dönüştürecektir. Bu araştırmaların sunduğu bir diğer fırsat ise hadis metnine dijital ortamdan ulaşan halkın hadis verilerinin içeriği hakkında bilgi edinme bilincini kazanmasıdır. Nitekim bazı araştırmalarda görüldüğü üzere hadis karşıtı web siteleri hadis hakkında bilgi sahibi olmak isteyen öğrenciler tarafından sıkça ziyaret edilmektedir. Bu sebeple halkın ulaştığı bilgi kaynaklarını yönetmek yanlış din algısından kaynaklanan sosyal ve politik birçok problemin çözüme kavuşturulmasına yardımcı olacaktır. Bu çalışmanın amacı özellikle Türkiye’deki hadis alanında çalışan araştırmacılara veri madenciliğini ve algoritmik araştırmaları tanıtmak ve bahsi geçen bu yöntemleri hadis ilmiyle birlikte kullanarak araştırmacıların hadis ilminin gelişimine katkıda bulunmasını sağlamaktır.

Copyright of Journal of Defense Sciences / Savunma Bilmleri Dergisi is the property of Turkish Military Academy Defense Sciences Institute and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Journal of Engineering & Architectural Faculty of Eskisehir Osmangazi University / Eskişehir Osmangazi Üniversitesi Mühendislik ve Mimarlık Fakültesi Dergisi is the property of Eskisehir Osmangazi University and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)