Bilgisayar Mühendisliği Bölümü Koleksiyonu
Permanent URI for this collectionhttps://hdl.handle.net/20.500.11779/1940
Browse
4 results
Search Results
Conference Object Citation - Scopus: 1Enhancing Quality Control in Plastic Injection Production: Deep Learning-Based Detection and Classification of Defects(IEEE, 2023) Mutlu, İsmail; Çakar, Tuna; Çakar, Tuna; Yıldız, Ahmet; Sayar, Alperen; Şimsek, Kamil; Tunalı, Mustafa Mert; 02.02. Department of Computer Engineering; 02. Faculty of Engineering; 01. MEF UniversityThis study investigates the applicability of diverse deep learning techniques in detecting and classifying defects within plastic injection manufacturing processes. The findings derived from the models yield several feasible solutions that hold potential practical implications. Notably, the implementation of the Xception model as a classification framework presents a potential domain for enhancing quality control procedures. The developed models, trained on the prepared data sets, provide compelling evidence for the potential utilization of artificial intelligence technologies in the manufacturing industry. Consequently, this study represents a noteworthy contribution to the limited yet auspicious academic research in the field.Conference Object Noise Effect on Forecasting(IEEE, 2023) Tuncer, Suat; Çakar, Tuna; Çakar, Tuna; 02.02. Department of Computer Engineering; 02. Faculty of Engineering; 01. MEF UniversityThe lack of regulation and liquidity in crypto money markets causes higher volatility compared to other financial markets. This situation increases the noise in price change. The high noise and random walk create a problem that cannot be explained by traditional stochastic financial methods. For this reason, a multi-layered deep learning model with an additive attention layer, which uses a single observation in 10-day sequences, was used in this study. Different transformations are used to reduce the noise of the closing values. As a result of the comparisons made between different approaches, it has been revealed that exponential moving averages, to be used as the value to predict, give better results than other conversions and estimation of the original price, since they explain the price better than simple moving averages and reduce the noise of the original price.Conference Object Transaction Volume Estimation in Financial Markets With Lstm(IEEE, 2023) Bozkan, Tunahan; Çakar, Tuna; Ertuğrul, Seyit; Sayar, Alperen; Akçay, Ahmet; 02.02. Department of Computer Engineering; 02. Faculty of Engineering; 01. MEF UniversityIn this study, it was aimed to determine the transaction volume that will be encountered in the future (hourly) in the factoring sector, and then to take financial and operational action early. For the study, the LSTM model, which is a kind of recurrent neural network (RNN) that can capture long and short-term dependencies, was applied by using data-driven approaches to estimate the check amounts of hourly transactions. As a result of the results, it was aimed to increase the operational efficiency in a broad scope by allowing the factoring company to determine the loan amounts to be obtained from banks in the most optimal way, and then to take early action within the scope of both the workforce and business management of the financial resource allocation management process and operational activities. MAPE score was used as a measure of error in the time series analysis model. MAPE scores were found as %5.05 for 30 days, %4.18 for 10 days, %3.47 for 5 days, %3.09 for 3 days and %1.83 for 1 day. According to the MAPE scores calculated for different days, the enterprise will be able to decide on the loan to be drawn from banks both in terms of time and amount, and the necessary action will be taken.Article Citation - WoS: 1Citation - Scopus: 4Classification of Skin Lesion Images With Deep Learning Approaches(University of Latvia, 2022) Kulavuz, Bahadır; Çakar, Tuna; Bakırman, Tolga; Çakar, Tuna; Doğan, Metehan; Bayram, Bülent; Bayram, Buket; 02.02. Department of Computer Engineering; 02. Faculty of Engineering; 01. MEF UniversitySkin cancer is one of the most dangerous cancer types in the world. Like any other cancer type, early detection is the key factor for the patient's recovery. Integration of artificial intelligence with medical image processing can aid to decrease misdiagnosis. The purpose of the article is to show that deep learning-based image classification can aid doctors in the healthcare field for better diagnosis of skin lesions. VGG16 and ResNet50 architectures were chosen to examine the effect of CNN networks on the classification of skin cancer types. For the implementation of these networks, the ISIC 2019 Challenge has been chosen due to the richness of data. As a result of the experiments, confusion matrices were obtained and it was observed that ResNet50 architecture achieved 91.23% accuracy and VGG16 architecture 83.89% accuracy. The study shows that deep learning methods can be sufficiently exploited for skin lesion image classification. © 2022 Baltic Journal of Modern Computing. All rights reserved.