Yazar "Arslankaya, Seher" seçeneğine göre listele
Listeleniyor 1 - 5 / 5
Sayfa Başına Sonuç
Sıralama seçenekleri
Öğe Analysis of quality control criteria in an business with the fuzzy DEMATEL method: Glass business example(Academic Publication Council, 2023) Celik, Mirac Tuba; Arslankaya, SeherQuality is at the forefront of the issues to which the production and service sectors attach importance. Increasing customer satisfaction, gaining competitive advantage in the industry, increase in sales vb. for many reasons, companies have increased the importance given to quality control. Before sending the products to the customer, taking into account the necessary quality control criteria, the control of the products will contribute to the solution of any problems that may arise in advance. Especially in sectors where energy and capital are intense, and the capacity is very high, it is one of the fundamental processes that should be done in the company, inspection of products taking into account all quality control criteria. Therefore, it is essential to consider the glass industry in this sense. This study determines the critical value of the quality control criteria on the glass, which a company that produces tempered glass pays attention to before putting the product used as a contract into production. Control criteria were determined by interviewing a team of experts in the company, and then the criteria were evaluated by experts. Then, fuzzy DEMATEL method, which is one of the multi-criteria deci-sion-making techniques, was used and the relations of the criteria with each other were determined. As a result of the calculations made with fuzzy DEMATEL, the criteria are listed as K1 > K2 > K4 > K7 > K6 > K5 > K3 and the aspect measurement with a criterion weight of 0,150 was found to have the most significant effect on the glass.Öğe Autism Spectrum Disorder Diagnosis with Neural Networks(Ayandegan Institute of Higher Education, 2024) Demir, Asude; Arslankaya, SeherAutism Spectrum Disorder (ASD) affects the whole life of children and leads their families to seek effective treatment and education. According to the Centres for Disease Control and Prevention, the disorder affects one in every 36 children today. Diagnosing this disease at an early age facilitates the treatment process and enables children to be reintegrated into society. The use of Artificial Neural Networks (ANN), one of the artificial intelligence methods used for prediction, has increased in the field of health in recent years and has become an important tool for early disease diagnosis. In this study, single layer perceptron neural networks were designed for the diagnosis of ASD. Data of 14 different parameters taken from children between 12-36 months of age were used, and as a result of the classification, the accuracy value of the neural network was 99.18%, the sensitivity value was 98.91%, the sensitivity value was 1 and the f1 score value was 99.45%. As a result, it is seen that the perceptron classification algorithm has a very high performance in terms of accuracy, precision, sensitivity and f1 score and successfully discriminates the data. © 2024, Ayandegan Institute of Higher Education. All rights reserved.Öğe Bulanık Mantık Yaklaşımı ile Trafik Kazası Riskinin Değerlendirilmesi(2024) Kulaç, Seçil; Arslankaya, SeherTrafik kazalarından kaynaklanan ölümler ve yaralanmalar tüm dünyada ciddi bir sorun olmaya devam etmektedir. Trafik kazalarına sebep olan faktörler oldukça çeşitlidir ve genellikle çoklu etkenlerin birleşimi sonucunda meydana gelirler. Sürücü davranışları, yol koşulları, araç durumu, iklim faktörleri, trafik kurallarının ihlali, yaya veya yolcuların hatalı davranışları ile eksik altyapı ve trafik düzenlemeleri gibi çeşitli faktörler kazaların oluşumunda etkilidir. Bu çalışmada, trafik kazalarını etkileyen dış etkenler ve sürücü etkeni dikkate alınarak bulanık mantık yaklaşımı ile trafik kazası olasılığı analiz edilmiştir. Bulanık mantık yaklaşımı ile model geliştirilmesinde önemli bir konu olan üyelik işlevlerinin belirlenmesinde 2022 yılına ait Karayolu Trafik Kaza İstatistikleri ve 2019 yılına ait Trafik Kaza ve Denetim İstatistikleri Raporları’ndan yararlanılarak yeni bir kaza tahmin modeli önerilmiştir. Önerilen modelde, faktörlerin bağımlı değişken üzerindeki etkilerini değerlendirmek amacıyla regresyon analizi uygulanmıştır. Analiz sonucunda yaş, alkol, saat, hız, hava durumu faktörlerinin kaza olasılığını anlamlı bir şekilde etkilediği tespit edilmiştir. Çalışma sonuçları, önerilen modelin, trafik kazalarının oluşumunu tahmin etmede sürücü etkeni ve dış faktörlerin karmaşıklığını dikkate alan etkili bir araç olduğunu göstermektedir.Öğe Real-time detection of plastic part surface defects using deep learning-based object detection model(Elsevier Sci Ltd, 2024) Celik, Mirac Tuba; Arslankaya, Seher; Yildiz, AytacIn this study, it was aimed to detect defects in plastic parts produced in a company operating in the automotive sub -industry using the YOLOv8 object detection model. The defect types seen in plastic parts were evaluated with the help of Pareto analysis, and scratches, stains and shine were selected as the most common defect types, and data on the three defect types were collected. YOLOv8 models were trained using faulty part images. As a result of the training, the highest mean average precision value of 0.990 was obtained in the YOLOv8s model, and the shortest training time was obtained in the YOLOv8n model. In the YOLOv8s model, which gave the highest mAP value, hyperparameter adjustment was made according to the batch size and learning rate values. The testing phase was carried out with the hyperparameter values that gave the best results and the mAP value was obtained as 0.902.Öğe Solution of the assembly line balancing problem using the rank positional weight method and Kilbridge and Wester heuristics method: An application in the cable industry(Academic Publication Council, 2023) Celik, Mirac Tuba; Arslankaya, SeherToday, assembly lines are frequently used in factories' production areas because they increase production processes' efficiency. Due to increased customer demands, increasing production amounts and intense competition cause severe fluctuations in production environments. This is also evident in assembly lines. Balancing problems caused by many reasons in assembly lines has become a big problem for companies. In this study, the balancing problem in the assembly line in an automotive supplier industry company that produces cables has been tried to be solved. In the solution of the problem, the Rank positional weight method, which is among the heuristics frequently used in the literature, and the Kilbridge and Wester heuristics were used. Considering the current situation, the cycle time from 170 s has been reduced to 142.25 s, and the line efficiency has been increased from 82.36% to 98.42%. There was no increase or decrease in the number of stations on the line and the number of operators working there. As a result of all these efforts, the workload was distributed equally among the stations, severely reducing waiting time. In this way, the downtimes in production were reduced, the overtime hours required to reach the required daily production amount were eliminated, and labor costs were reduced.
