Search

Dijital dönüşüm ile tedarik zinciri yönetiminde büyük veri analitiğinin önemi gün geçtikçe artmaktadır. Özellikle müşteri taleplerinin hızlı ve doğru tahmin edilmesinde büyük verinin kullanımı firmalara rekabet avantajı sağlamaktadır. Bu doğrultuda, yapay zekâ tekniklerinden biri olan derin öğrenme modelleri büyük verideki karmaşık örüntülerin keşfedilmesinde öne çıkmaktadır. Son yıllarda literatürde çok sayıda derin öğrenme yöntemi önerilmiştir. Bu çalışmada, satış tahmini problemi için derin öğrenme yöntemlerinin performansları karşılaştırılmıştır. Bu kapsamda derin sinir ağı (DNN), derin otokodlayıcı (Deep AE), evrişimli sinir ağı (CNN), tekrarlayan sinir ağı (RNN), uzun kısa-süreli bellek (LSTM) ağı, çift yönlü LSTM (Bi-LSTM) ağı, kapılı tekrarlayan birim (GRU), CNN-LSTM ve evrişimli LSTM (ConvLSTM) yöntemleri uygulanmıştır. Çeşitli sektörlere ait satış verileri kullanılarak deneysel çalışmalar gerçekleştirilmiştir. Hiperparametre optimizasyonu ardından ele alınan yöntemlerin performansları tahmin doğruluğu ve eğitim süreleri açısından karşılaştırılarak sonuçların istatistiksel anlamlılığı değerlendirilmiştir. Sonuç olarak, LSTM ve GRU modellerinin tahmin doğruluğunda başarılı sonuçlar verdiği, CNN modelinin ise eğitim süresini kısalttığı görülmüştür.

Karayolu esnek üstyapılarındaki çatlaklar genellikle trafik yükleri ve hava koşullarından kaynaklanır. Bu çatlakların genişlemeden tespit edilip gerekli bakımlarının yapılması, yol konforunun sürekliliğini sağlamanın yanı sıra bakım maliyetlerini de azaltacaktır. Bu çalışma, yoldaki çatlakları gerçek zamanlı ve yüksek doğrulukla tespit etmeyi amaçlamaktadır. Bu bağlamda, Geri Yayımlı Birlikte Evrim yaklaşımıyla İyileştirilmiş Derin Sinir Ağları ve görüntü işleme yöntemleri birlikte kullanılmıştır. Ayrıca, çeşitli sayı ve çözünürlüklerde çatlaklı görsel veriler içeren EdmCrack600, AsphaltCrack, CFD ve CrackSegmentation veri setleri kullanılarak yeni bir veri seti oluşturulmuş ve bu veri seti üzerinde Derin Sinir Ağları tabanlı öğrenme gerçekleştirilmiştir. Modelin doğruluğu, CFD veri seti kullanılarak Kesinlik, Duyarlılık ve F1-Skoru ile değerlendirilmiştir. Değerlendirme sonucunda, önerilen yöntemin saniyede 48 görsel üzerinde çatlak tespit edebildiği ve %92,74 Kesinlik, %88,92 Duyarlılık ve %89,61 F1 Skoru başarı oranlarına ulaştığı gözlemlenmiştir.

As the amount of the available information continues to grow, finding the relevant information has become increasingly challenging. As a solution, text summarization has emerged as a vital method for extracting essential information from lengthy documents. There are various techniques available for filtering documents and extracting the pertinent information. In this study, a comparative analysis is conducted to evaluate traditional approaches and state-of-the-art methods on the BBC News and CNN/DailyMail datasets. This study offers valuable insights for researchers to advance their research and helps practitioners in selecting the most suitable techniques for their specific use cases.

Ensuring security in speaker recognition systems is crucial. In the past years, it has been demonstrated that spoofing attacks can fool these systems. In order to deal with this issue, spoof speech detection systems have been developed. While these systems have served with a good performance, their effectiveness tends to degrade under noise. Traditional speech enhancement methods are not efficient for improving performance, they even make it worse. In this research paper, performance of the noise mask obtained via a convolutional neural network structure for reducing the noise effects was investigated. The mask is used to suppress noisy regions of spectrograms in order to extract robust i-vectors. The proposed system is tested on the ASVspoof 2015 database with three different noise types and accomplished superior performance compared to the traditional systems. However, there is a loss of performance in noise types that are not encountered during training phase.

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 International Journal of Advances in Engineering & Pure Sciences is the property of Marmara 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.)

Diagnosis of anomalies in the gastrointestinal tract is a current research area. Wireless capsule endoscopy (WCE) for the evaluation of this region is a preferred alternative technology to avoid the risks of traditional endoscopy and to provide a painless process. But this technology, which has many advantages, offers low frame density. This situation affects the quality of the data and causes to a decrease in the diagnostic accuracy rate. In this study, WCE endoscopy images obtained from KID Atlas Dataset 2 were used and a three-stage artificial intelligence-supported diagnostic process was developed for the detection of the inflammatory anomaly, vascular anomaly, polypoid anomaly and normal image categories in the gastrointestinal tract. For the first stage, critical points on the images were clarified using 5 different approaches. These improved images were classified with a region proposal-based object recognition algorithm and performance comparison was made according to the approaches used. In the second stage, the data augmentation technique was applied to the improved images that showed maximum performance in the first stage. Thus, a dataset with a balanced and sufficient number of images was created. In the third stage, this current dataset was classified with five different object recognition algorithms. However, the individual success of each algorithm is different. For this reason, the ensemble learning approach was used to obtain stable outputs for each category and to create a balanced detection process among the categories. Finally, a balanced and stable estimation function was provided between categories with this hybrid structure. [ABSTRACT FROM AUTHOR]

Hydrothermal alteration is an important geological feature used in the exploration stages of precious minerals. This research focuses on two distinct deep-learning network structures created to identify hydrothermal alteration types in microscope images. A dataset of 2500 images, 70% of this data set was used to train, 20% to test, and 10% to measure the validity of the network. Convolutional Neural Network (CNN) and Xception models were trained using Adam, RMSprop and SGD optimization functions and the results are discussed. The Adam and SGD optimization functions for the CNN model performed the most successful classification with 96% accuracy. In the case of the Xception model, the highest accuracy value was 98% for the networks using the Adam and RMSprop optimization functions. Although the Xception model had higher accuracy values, it was observed that the CNN model completed the process significantly faster considering the training time of the network. [ABSTRACT FROM AUTHOR]

Copyright of Gazi Üniversitesi Fen Bilimleri Dergisi Part C: Tasarım ve Teknoloji is the property of 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 Gazi Üniversitesi Fen Bilimleri Dergisi Part C: Tasarım ve Teknoloji is the property of 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 Gazi Üniversitesi Fen Bilimleri Dergisi Part C: Tasarım ve Teknoloji is the property of 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 Gazi Üniversitesi Fen Bilimleri Dergisi Part C: Tasarım ve Teknoloji is the property of 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.)

Türkiye is a country on the Alpine-Himalayan earthquake zone and needs an effective disaster management plan, with its geography experiencing severe seismic activities. In this respect, natural disaster risks can be reduced by using developing artificial intelligence technology and deep learning applications in the mitigation, preparedness, response, and recovery phases that constitute the disaster management plan. This study examines deep learning models, application areas, deep learning layers and libraries used, and how deep learning can be used in the four stages of disaster management through study examples in the literature. The study aims to examine the use of deep learning in architecture and disaster management phases based on the earthquake factor as a result of the literature review. As a result, when studies on deep learning are examined, disaster management studies closely related to the discipline of architecture are mainly in the response phase. However, the discipline of architecture plays an important role at every stage of disaster management. In this respect, as holistic studies and applications related to deep learning, architectural science, and effective disaster management increase, the loss of life and property due to disasters, especially earthquakes, will decrease. The study carried out is thought to be an important guide for future research.

Traffic sign detection has attracted a lot of attention in recent years among object recognition applications. Accurate and fast detection of traffic signs will also eliminate an important technical problem in autonomous vehicles. With the developing artificial intelligency technology, deep learning applications can distinguish objects with high perception and accurate detection. New applications are being tested in this area for the detection of traffic signs using artificial intelligence technology. In this context, this article has an important place in correctly detecting traffic signs with deep learning algorithms. In this study, three model of (You Only Look Once) YOLOv5, an up-to-date algorithm for detecting traffic signs, were used. A system that uses deep learning models to detect traffic signs is proposed. In the proposed study, real-time plate detection was also performed. When the precision, recall and mAP50 values of the models were compared, the highest results were obtained as 99.3, 95% and 98.1%, respectively. Experimental results have supported that YOLOv5 architectures are an accurate method for object detection with both image and video. It has been seen that YOLOv5 algorithms are quite successful in detecting traffic signs and average precession.

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.)

Advanced camera systems integrated in to unmanned aerial vehicles (UAVs) enable the acquisition of highresolution images. These images are often more advantageous in terms of spatial, temporal, radiometric, and spectral resolution compared to satellite images. However, depending on the size of the scanned areas, the acquired data becomes large and occupies significant storage space. Therefore, processing the data to obtain meaningful information and insights becomes challenging. Various methods have been developed to extract meaningful data from images. While operators used to analyze images one by one in the past, today, objectbased and pixel-based data extractions have been developed. Thanks to these methods, data can be parsed by software rapidly and with high accuracy. Segmentation and classification methods facilitate processes such as categorization, sub-classification, parsing, and detection. Segmentation and classification processes on data are of crucial importance for the analysis of large and complex datasets. Numerous studies demonstrate that these techniques and applications are continuously evolving and gaining prominence in the literature. Within the scope of this study, segmentation and classification efforts conducted with UAVs have been discussed, and the outcomes of these studies have been examined. It is observed that studies utilizing hybrid and deep learning-based techniques tend to yield more efficient results compared to other approaches. [ABSTRACT FROM AUTHOR]

Nowadays, deep learning methods are widely used in many fields such as robotics, sound processing, medicine and imagery. In this study, studies on image classification and analysis in the literature were examined in detail. In addition, performance analyzes of deep learning methods were carried out using CNN on 4 different data sets named MNIST, Fashion MNIST, CIFAR-10 and CIFAR-100. The structures of the created deep learning models, the parameter values used for training, the layers used, the complexity matrices obtained for the validation data, accuracy and loss graphs are shown in detail. Our study was carried out with a different network structure consisting of 3 convolution layers, 3 batch normalization layers, 2 maxpooling layers, 1 flatten, 2 droupout, 2 dense layers. In addition, the performance of image classification on different data has been increased with our proposed model. At the end of the test, the accuracy results of our study were compared according to various evaluation metrics. For all the data sets used, the best and worst images were determined. With the proposed CNN model, high accuracy rates were observed for MNIST and Fashion MNIST datasets, with these values being 99.22% and 99.21%, respectively. [ABSTRACT FROM AUTHOR]

In this study, LSTM (Long-Short Term Memory) and GRU (Gated Recurrent Unit) techniques of deep learning, which are among the latest advanced technologies, were applied in the Google Colab software program for stock price forecasting. The dataset used in the study was obtained from Yahoo Finance and covers the dates between 02/01/2013 and 30/12/2022. Forecast models were created by considering 5 companies belonging to the XELKT (Electricity Market in Borsa Istanbul) index, which is part of BIST (Borsa Istanbul). Subsequently, the success of these forecast models was tested with the calculated model performance criteria, aiming to determine whether the techniques used were successful in stock price forecasting. Additionally, based on the results of MSE (Mean Squared Error) and MAPE (Mean Absolute Percentage Error) among the calculated model performance criteria, the techniques used were compared with each other, aiming to determine which of these techniques provided forecasts with less error. Then, through the analysis conducted on four different days, an attempt was made to identify the day that yielded the most successful forecasts. As a final step, the goal was to find a model with the least error based on techniques, epoch number, and the number of days forecasted, considering both MSE and MAPE for stocks. Since the model performance criteria outputs obtained from these analyses are below 1 for MSE and below 5% for MAPE, it can be concluded that both techniques demonstrate successful stock price forecasting. Consequently, in the comparison between these two techniques, it is observed that the LSTM technique is slightly more successful than the GRU technique.

The prominence of cyber security continues to increase on a daily basis. Following the cyber-attacks in recent years, governments have implemented a range of regulations. The advancement of technology and digitalization has led to the creation of new vulnerabilities that cyber attackers can exploit. The digitalization of facilities such as energy distribution networks and water infrastructures has enhanced their efficiency, thereby benefiting states and society. The modern sensors, controllers, and networks of these new generation facilities have made them susceptible to cyber attackers. While all forms of cyber-attacks are detrimental, targeting critical cyber-physical systems presents a heightened level of peril. These assaults have the potential to disrupt the social structure and pose a threat to human lives. Various techniques are employed to guarantee the security of these facilities, which is of utmost importance. This study examined the applications of machine learning and deep learning methods, which are sub-branches of artificial intelligence that have recently undergone a period of significant advancement. Intrusion detection systems are being created for the networks that facilitate communication among the hardware components of the cyber-physical system. Another potential application area involves the development of models capable of detecting anomalies and attacks in the data generated by sensors and controllers. Cyber physical systems exhibit a wide range of diversity. Due to the wide range of variations, it is necessary to utilize specific datasets for training the model. Generating a dataset through attacks on a functional cyber-physical system is unattainable. The study also analyzed the solutions to this problem. Based on the analyzed studies, it has been observed that the utilization of artificial intelligence enhances the security of cyber physical systems.

Yarı iletken devre elemanı üretim teknolojilerinde gerçekleşen gelişimler, bu elemanların üzerinde yer aldığı yonga plakası üretim süreçlerini daha karmaşık ve hassas hale getirmektedir. Üretim ile ilişkili çevresel koşullar, malzeme kalitesi gibi çeşitli faktörler, yonga plakası üzerinde kusursuz olarak nitelendirilebilecek alan miktarını yani verimi doğrudan etkilemektedir. Bir yarı iletken yonga plakası üzerindeki kusurlu alanların oluşturabileceği desenler standart olarak tanımlanmış durumdadır. İncelenen bir yonga plakası yüzeyindeki kusurların bu tanımlara göre sınıflandırılması, üretim süreçlerinde oluşan problemlerin kaynaklarının belirlenmesi için önemli bilgiler sağlayabilmektedir. Bu çalışmada, mevcut uygulamalarda her yarı iletken yonga levhası için insan operatörler tarafından yapılan kusur deseni sınıflandırma işlemini belirli bir güvenlik değerine kadar otomatik olarak gerçekleştiren ve böylece toplam işlem süresini azaltan bir karar destek yöntemi geliştirilmiştir. Bu yöntemde temel sınıflandırma işlemi için derin öğrenme metotlarıyla eğitilmiş bir ağ yapısı kullanılmaktadır. İstenilen güvenlik değerinin üzerinde bir doğrulukla sınıflandırılan yonga plakaları doğru sınıflandırılmış olarak kabul edilmekte, bu değerin altında kalan yonga plakaları ise insan operatörün incelemesine tabi tutulmaktadır. Yöntemin kullanılması ile; ortalama büyüklükte bir yonga plakası üretim tesisi için geçerli günlük toplam inceleme süresi, tüm incelemenin insan operatör tarafından yapıldığı durumda geçerli sürenin %10’una indirilebilmekte, ayrıca insan operatörün yapabileceği öznel değerlendirmelerin de önüne geçilebilmektedir.

Plant disease classification is the use of machine learning techniques for determining the type of disease from the input leaf images of the plants based on certain features. It is an important research area since early identification and treatment of plant disease is critical for saving crops, preventing agricultural disasters, and improving productivity in agriculture. This study proposes a new convolutional neural network model that accurately classifies the diseases on the plant leaves for the agriculture sectors. It especially works on the classification of plant diseases for grape leaves from images by designing a deeplearning architecture. A web application was also implemented to help the agricultural workers. The experiments carried out on real-world images showed that a significant improvement (8.7%) on average was achieved by the proposed model (98.53%) against the state-of-the-art models (89.84%) in terms of accuracy.

Mikroskobik sistemlerde var olan odaklama derinliğinden dolayı numunenin tüm alanının odaklandığı görüntü elde etmek imkânsız olabilmektedir. Bu durum, mikroskobik sistemlerde görüntü işleme ve yapay zekâ algoritmaları kullanılarak gerçekleştirilen sınıflandırma, bölütleme, hizalama (registration), panoramik birleştirme (stitching) gibi uygulamalarının başarılarını olumsuz yönde etkilemektedir. Literatürde numunenin tüm alanının odaklandığı görüntü elde etmek için odaklama derinliğinin artırılması yaklaşımları geliştirilmektedir. Literatür çalışmaları, bu yaklaşımların, görüntülerdeki eğrilerin ve kenarların düşük kesinlikte karakterizasyonu, daha yüksek koşma süresi ve incelenen numuneye ve kullanılan mikroskoba göre performans değişimi gibi çeşitli kısıtlamalara sahip olduklarını ortaya koymaktadır. Ek olarak, bu yaklaşımlar odaklama bilgilerini genelde görüntülerin gri seviye değerlerini kullanarak hesaplamaktadırlar. Bu çalışmada bu kısıtlamaları minimize etmek için yeni bir odaklama derinliğinin artırılması yaklaşımı geliştirilmekte ve odaklama derinliğinin artırılmasında derin özelliklerin odaklama değerlerinin çıkarılmasındaki etkileri incelenmektedir. Çalışmada elde edilen sonuçlar derin özelliklerin piksellerin odaklama değerlerini hesaplamada gri seviye değerlerine göre daha etkin olduğunu göstermektedir.

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 Sakarya Tıp Dergisi is the property of Sakarya Tip 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.)

Classification studies on image data sets with convolutional neural networks algorithm, which is one of the deep learning approaches, are widely performed successfully in many fields such as medicine and agriculture. However, in cases where the sample numbers of the classes in the image datasets are imbalanced, the classification performance of this algorithm is negatively affected. In general, unlike the majority class, the minority class(es) are not well learned by the convolutional neural network algorithm. In such cases, applying oversampling methods provides successful results. With oversampling methods, the number of minority class(s) samples is increased, making it close to or equal to the sample number of the majority class. In this study, translation, rotation, random erasing, noise injection, mixing of images, kernel filters, generative adversarial networks, flipping, feature space transformation, cropping and color space transformation oversampling methods frequently used in the literature were applied on the Ham10000 dataset. According to the results obtained as a result of the study, oversampling methods have been compared in terms of classification performance. From three different convolutional neural network models, according to the classification results obtained with ResNet50, DenseNet201, MobileNet, in terms of accuracy, the noise injection method in the ResNet50 model was 0.967, the color space transformation method in the DenseNet201 model was 0.965, and in the MobileNet model, the mixing of images method had a classification performance value of 0.974 which was better than the other oversampling methods. [ABSTRACT FROM AUTHOR]

During apple (Malus communis L.) harvesting, physical damage that reduces the quality of the product is inevitable. Early detection and separation of damaged fruits is important in terms of increasing their commercial value. Undetected defective products reduce the production volume as well as food loss, since they affect the quality of intact products. The aim of this study is to detect defects in apples using deep learning techniques on images taken from the "Granny Smith" apple cultivar. A technique that does not require special conditions and that will make classification and defect detection cost-effectively has been researched. In the study, the test accuracy of the InceptionV3 model was 100% after 100 epochs, and the test accuracy of the AlexNet model was 98.33%. A method has been developed that can prevent economic losses that may occur after harvesting by detecting and separating the damages that occur on the fruit during harvesting with deep learning techniques. [ABSTRACT FROM AUTHOR]

İnsanoğlu makinelerin insanlar gibi düşünebildiği ve hareket edebildiği bir çağın başlangıcında bulunuyor. Bu durum her ne kadar ürkütücü görünse de, akademide ilgi gören ve üzerinde artan miktarda çalışmalar gerçekleşmeye başlanan bir konudur. Makine öğrenmesi ve derin öğrenmeyle oluşturulan yapay zeka pek çok alanda olduğu gibi, finans alanında da çokça kullanılmaktadır. Bu çalışmalar içerisinde yurt içinde ve yurt dışında yayınlanan makale, kitap, kitap bölümleri, sempozyum bildirileri olduğu gibi, gerçekleştirilen yüksek lisans ve doktora tezleri de yer almaktadır. Bu tür çalışmalarda gelinen son durumu tespit etmek ve literatürdeki boşlukları ortaya çıkarmak amacıyla sistematik literatür taramaları yapılmaktadır. Bu çalışmada, Türkiye’de gerçekleştirilen ve uygulama bölümlerinde finans alanında makine öğrenmesi ve derin öğrenme tekniklerinin kullanıldığı lisansüstü tezler sistematik literatür taraması ile incelenmektedir. Araştırma, 2018-2023 yılları arasındaki dönemde yapılan çalışmaları kapsamaktadır. Araştırmanın sonucunda, konuyla ilgili yapılan tezlerde makine ve derin öğrenme yöntemlerinin en çok finansal enstrümanların gelecekteki fiyatlarının tahminlemesinde, ardından sırasıyla finansal risklerin tespit edilmesinde, kurumsal finansal başarısızlık ve iflas tahmininde ve ayrıca portföy optimizasyon modellerinde kullanıldığı belirlenmiştir. İlgili dönem boyunca, yapılan tez çalışmalarının sayılarında artan bir grafik bulunmaktadır. Bu çalışmalarda genellikle birden fazla algoritmanın uygulamadaki başarıları karşılaştırılarak en başarılı sonuçlar belirlenmeye çalışılmıştır. En çok çalışılan tez konusunun makine öğrenmesiyle kredi riskinin analizi olduğu, ardından makine öğrenmesiyle hisse senedi fiyat tahmininin geldiği ortaya çıkmıştır. En çok kullanılan algoritmaların karar ormanı, karar ağacı ve uzun-kısa dönem hafıza algoritmaları olduğu tespit edilmiştir. Lisansüstü tez konusu olarak sosyal bilimlerden daha çok, fen bilimleri temel alanında tercih edildiği ve yazılan tezlerin en çok bilgisayar mühendisliği ana bilim dalında hazırlandığı, ardından işletme ana bilim dalında hazırlanan tezlerin geldiği ortaya çıkmıştır.

Financial time-series data are nonlinear, complex, influenced by many economic factors, and are difficult to predict. Several traditional statistical methods have been developed for financial time series modeling. However, because it is now easier to record, analyze, and transform big data into meaningful information, the use of machine learning algorithms in financial forecast development has increased in recent years. In this study, the data of EREGL stocks, which are among the stocks traded in the main metal market in the Borsa İstanbul index, are analyzed using time series methods and then modeled using ARIMA and deep models. In the developed deep learning method, the prediction performance improved with data preprocessing stages, feature extraction studies, and different time windows. For deep learning algorithms to be used in time-series studies, a framework of time delays must be used. In this study, scenarios for different time delays and performance comparisons are performed between ARIMA models and deep learning models using long-short term emory (LSTM), gated repeating unit (GRU), and recursive neural network (RNN) algorithms. Experimental studies demonstrate that the RNN algorithm has a better predi

We present a recognition system for online Turkish handwriting using transfer learning. Training deep networks requires large amounts of data. Since such a sufficiently large collection of Turkish handwriting samples is not available, So we adopt the transfer learning approach and train and optimize a CNN-BLSTM recognition system first using the standard IAM-On dataset of English handwriting. Then, we fine tune it with Turkish handwriting samples from a smaller dataset. Fine tuning increases the character recognition rate of the final system which is evaluated on 2,041 samples of isolated Turkish words from the initial value of 49% to 85%. The results show that transfer learning can be a solution to the data scarcity problem of online Turkish handwriting.

2019 yılında dünya çapında pandemi ilan edilmesine sebep olan COVİD-19 virüsü, bulaştığı bazı kişilerde hastalığın çok hızlı ilerlemesi sebebi ile çok ciddi sağlık problemlerine, hatta ölümlere neden olmuştur. Hastalığın hızlı teşhisi bu olumsuz durumların ortaya çıkmasını engellemek için büyük önem arz etmiştir. X-Ray göğüs görüntüleri, Bilgisayarlı Tomografi (BT) vb. gibi tıbbi görüntüleme yöntemleri covid-19 un tespit edilmesinde önemli rol oynamıştır. Derin öğrenme yöntemleri, insan faktörünü ve insandan kaynaklı hata payını minimuma indirerek üstün görüntü analizi yeteneğini kanıtlamıştır. Bu çalışmada, son dönemlerde bilgisayarlı görü uygulamalarında öne çıkan görüntü dönüştürücülerin (Vision Transformers, VIT) X-ray göğüs görüntüleri üzerinde Covid-19 tespiti için kullanılması önerilmiştir. Önerilen sistemin eğitim ve test performansı literatürde yaygın kullanılan bir Konvolüsyonel Sinir Ağı, Resnet50, ile ayrıntılı olarak karşılaştırılarak analiz edilmiştir. Ayrıca VİT mimarisinin etkinliği doğruluk, kesinlik, hassasiyet ve F1 skoru kriterleri aracılığı ile Resnet50’nin yanı sıra COVİD-19’un çok sınıflı veri kümelerinde başarı gösterdiği kaydedilen VGG16 ve InceptionV3 mimarileri ile de karşılaştırılmıştır. Deneyler sonucunda VİT mimarisinin öğrenme aktarımı yöntemi ile eğitilen Resnet50 ve VGG16 mimarilerinden daha iyi performans gösterdiği ve InceptionV3 ile başa baş sonuçlar elde ettiği gözlemlenmiş ve COVİD-19 tespitinde alternatif bir karar destek sistemi olarak kullanılabileceği tespit edilmiştir.

This study predicts the stock price of Petkim Petrokimya Holding Corp. (PETKM), which is listed in Borsa Istanbul (BIST), using PETKM stock price, US dollar (USD/TRY) price and BIST Chemical, Petroleum Plastic (XKMYA) index price. A time series data set with three inputs and one output is created using these data. Random Forest Regression (RFR), Long-Short Term Memory (LSTM), and Convolutional Neural Network (CNN) algorithms are used in the prediction model. The success of these methods is compared using performance metrics such as MSE, RMSE, MAE, and R2. According to the calculated error metrics, LSTM and RFR algorithms gave better results than CNN with an MSE value less than 0.02. However, the fact that the R2 values of the most successful models created with all three algorithms were greater than 95% revealed that all the algorithms mentioned could be used to estimate this data set.

There are many factors that can change and affect appearance, including age and environment. Knowing the skin type helps to choose the products best suited to the needs of the skin and therefore the right skin care. Recently, the increasing demand for cosmetics and the scarcity of well-equipped cosmetologists have encouraged cosmetology centers to meet the need by using artificial intelligence applications. Deep learning applications can give high accuracy results in determining the skin type. Recent research shows that learning performs better on nonlinear data than machine learning methods. The aim of this study is to find the best classification model for skin type prediction in skin analysis data with deep learning. For this purpose, 4 different optimization algorithms as Sgd, Adagrad, Adam and Adamax; Tanh and ReLU activation functions and combinations of different neuron numbers using, 16 different models were created.In experimental studies, the performance of the models varies according to the parameters, and it has been observed that the most successful deep neural network model is the model consisting of 64 neurons, Sgd optimization function and ReLU activation function combination with a success rate of 93.75. The accuracy result obtained has a higher classification success compared to other methods, and shows that deep neural networks can make an accurate skin type classification.

Haberleşme teknolojilerinde her geçen gün artan sinyal çeşitliliği, bu sinyallerin tanımlanması ve sınıflandırılması gerekliliğini ortaya çıkarmıştır. Beşinci nesil (fifth generation, 5G) ve ötesi kablosuz haberleşme teknolojileri, birçok uygulama için vazgeçilmez iletişim araçları haline gelmiştir. Otomatik modülasyon tanıma (automatic modulation recognition, AMR) tekniği, özellikle yeni nesil nesnelerin interneti, akıllı şehirler, otonom araçlar ve bilişsel radyo gibi birçok uygulama için temel bileşen haline gelmiştir. Bu çalışmada sekiz farklı modülasyon türü kullanılarak bir veri seti oluşturulmuş ve derin öğrenme (deep learning, DL) algoritmalarından olan evrişimli sinir ağları (convolutional neural network, CNN) kullanılarak farklı sinyal-gürültü oranlarında (signal-to-noise ratio, SNR) modülasyon türü sınıflandırılması yapılmıştır. Sonuç olarak SNR değerleri 10 dB, 20 dB ve 30 dB iken CNN ile sınıflandırma işleminde sırasıyla %80,76, %99,89 ve %100 doğruluk sağlanmıştır.

Brain tumors can have very dangerous and fatal effects if not diagnosed early. These are diagnosed by specialized doctors using biopsy samples taken from the brain. This process is exhausting and wastes doctors' time too much. Researchers have been working to develop a quick and accurate way for identifying and classifying brain tumors in order to overcome these drawbacks. Computer-assisted technologies are utilized to support doctors and specialists in making more efficient and accurate decisions. Deep learning-based methods are one of these technologies and have been used extensively in recent years. However, there is still a need to explore architectures with higher accuracy performance. For this purpose, in this paper proposed a novel convolutional neural network (CNN) which has twenty-four layers to multi-classify brain tumors from brain MRI images for early diagnosis. In order to demonstrate the effectiveness of the proposed model, various comparisons and tests were carried out. Three different state-of-the-art CNN models were used in the comparison: AlexNet, ShuffleNet and SqueezeNet. At the end of the training, proposed model is achieved highest accuracy of 92.82% and lowest loss of 0.2481. In addition, ShuflleNet determines the second highest accuracy at 90.17%. AlexNet has the lowest accuracy at 80.5% with 0.4679 of loss. These results demonstrate that the proposed CNN model provides greater precision and accuracy than the state-of-art CNN models.

Fossil studies are of great importance in order to observe the change of living species over the years, to make inferences by using the information provided by the observed species, and to understand the developing and changing structure of the world we live in over the years. However, the examination and interpretation of fossil specimens is a complex and long process. Artificial intelligence studies have begun to be applied to this field in order to facilitate the working methods of paleontologists. The detection and classification of fossil specimens with the aid of computers simplifies this process as much as possible compared to manual classification processes and reduces foreign dependency for fossil assemblages for which paleontologists are not experts. To achieve this, 9 benthic foraminiferal species and non-foraminiferal sample photographs from a selected dataset were used. In this study, a new method developed for the classification of benthic foraminifera using deep convolutional neural networks, reaching higher accuracy than the results in the literature, is presented. With this method, at least 70% accuracy rates were achieved in the test results of the trained system. This study, which reached high accuracy rates with a new method, has created a successful development for the branch of paleontology in the use of artificial intelligence in microfossil identification.

The developments in semiconductor circuit manufacturing technologies make the wafer production processes on which these structures are located more complex and sensitive. Various factors such as environmental conditions associated with manufacturing and material quality directly affect the wafer yield, that is, the amount of space on the wafer that can be considered perfect. Possible patterns showing defective areas on a semiconductor wafer are defined as standard. Classifying the defects on the wafer according to these definitions can provide important information to diagnose the causes of problems that occur in the manufacturing processes. In this study, a decision support method has been developed that automatically performs the wafer defect model classification process up to a certain security value. In this method, the basic classification process is performed by a network structure trained with deep learning methods. Wafers classified with an accuracy above the desired safety value are considered to be correctly classified, only the wafers below this value are subject to the inspection of the human operator. By using the method, the total daily inspection time for an average sized wafer manufacturing facility can be reduced to 10% of the time that would apply if the entire inspection was done by the human operator. In addition, subjective evaluations by the human operator can be avoided to a large extent. [ABSTRACT FROM AUTHOR]

Copyright of PLANARCH - Design & Planning Research is the property of Ataturk University Coordinatorship of Scientific Journals 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.)

The unregulated and unconscious use of energy sources causes environmental damage. On the other hand the increasing population density, development of industry and technology increase the demand for electrical energy day by day. For this purpose, investments in the energy sector are directed towards renewable energy sources such as wind energy in order to ensure both environment-friendly and supply-demand balance. The amount of energy obtained from wind energy varies depending on regional differences such as wind direction and speed. In this study, a method is proposed to achieve better results in predicting electricity generation from wind energy by capturing the non-linear and non-stationary nature of wind energy using a hybrid approach of deep learning methods, specifically CNN and BLSTM architectures. In the forecasting model, 26280 real-time data measured at hourly frequency are used. In addition, the hyperparameter values used in the model were optimized using the Grid Search algorithm in order to increase the prediction success. The success of the proposed hybrid model is compared with the BLSTM model. As a result, the R² value, which indicates the success rate of the proposed CNN-BLSTM model, was calculated as 0.984. [ABSTRACT FROM AUTHOR]

Blood pressure is the pressure exerted by the blood in the vessels against the vessel walls. If this pressure value is above normal levels, it is known as high blood pressure (HBP) or hypertension (HPT). The diagnosis of this health problem, which negatively affects the quality of life, often causes various damage to organs and can lead to death, is very important. In this study, a method for automatic diagnosis of HPT using ballistocardiography (BCG) signals is proposed. For this, BCG signals are transferred to the time-frequency domain using the continuous wavelet transform filter bank (CWTFB) method. The quality of the conversion has been increased by making some parameter settings in the conversion method used while performing these operations. Then, the obtained images were classified with ResNet18, ResNet50, VGG16 and AlexNet convolutional neural networks and the obtained results were compared. With the proposed method, classification accuracy of 98.92%, 99.34%, 99.22% and 98.07% was obtained for ResNet18, ResNet50, VGG16 and AlexNet architectures, respectively. These high classification results obtained prove that the proposed method can be used for the diagnosis of hypertension. [ABSTRACT FROM AUTHOR]

Copyright of Sakarya University Graduate School of Business Journal (SAUGSB-J)Sakarya Üniversitesi İşletme Enstitüsü Dergisi is the property of Sakarya University Journal of Business Administration Institute (SAUIED) 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 Gazi Üniversitesi Fen Bilimleri Dergisi Part C: Tasarım ve Teknoloji is the property of 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.)

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.)

With the enormous growth rate in the number of movies coming into our lives, it can be very challenging to decide whether a movie is suitable for a family or not. Almost every country has a Movie Rating System that determines movies’ suitability age. But these current movie rating systems require watching the full movie with a professional. In this paper, we developed a model which can determine the rating level of the movie by only using its subtitle without any professional interfere. To convert the text data to numbers, we use TF-IDF vectorizer, WIDF vectorizer and Glasgow Weighting Scheme. We utilized random forest, support vector machine, k-nearest neighbor and multinomial naive bayes to find the best combination that achieves the highest results. We achieved an accuracy of 85%. The result of our classification approach is promising and can be used by the movie rating committee for pre-evaluation. Cautionary Note: In some chapters of this paper may contain some words that many will find offensive or inappropriateness; however, this cannot be avoided owing to the nature of the work

Semantik segmentasyon, çevredeki nesnelere anlam vermek için etiketlenmiş her pikseli anlamlı bir sınıfa atayan bir veri işleme yöntemidir. Derin öğrenme (DÖ) tabanlı yöntemlerin geliştirilmesi, Nokta Bulutu (NB) ile segmentasyon yöntemlerine olan ilgiyi artırmıştır. 3 Boyutlu (3B) nokta bulutu semantik segmentasyonu, farklı tarama araçları ile elde edilen 3B veri setlerinde aynı bölgede aynı özelliklere sahip noktaları homojen bölgelere ayırmaktadır. 3B nokta bulutları ile 3B nesneleri anlamak için semantik segmentasyonun kullanılması önemli bir başlangıç olmuştur. Özellikle derin öğrenme yöntemlerinin kullanılması bu alanı odak noktası haline getirmiştir. 3B yapılandırılmamış büyük nokta bulutlarını işlerken, derin öğrenmeyi temel alarak geliştirilen yeni yöntemler, yaklaşımlar ve modeller üzerinde benzersiz sorunlarla karşılaşılması bu alanın gelişime açık olduğunu göstermektedir. Bu yeni yöntemlerin başarılarını anlamak için, kıyaslama veri kümeleri: ShapeNet, S3dis, ScanNet, SemanticKITTI üzerindeki performansları değerlendirilmiş. 3B nokta bulutu ile segmentasyon alanına katkıda bulunan dikkate değer araştırmalar incelenmiş, avantajları, dezavantajları ve önerilen yöntemlerin katkıları sunulmuştur. Sunulan tüm yöntemlerin mimari yapısı, yaygın olarak kullanılan veri kümeleri üzerindeki başarıları tartışılmış ve gelecekteki araştırmalara öncülük edecek bilgiler önerilmiştir.

Despite the increasing use of machine learning (ML) in the early diagnosis and determination of risk factors of various infections, studies evaluating the use of ML in central nervous system infections (CNSI) are limited. The Scopus, Web of Science, and PubMed databases were searched via Ovid using the keywords “Artificial intelligence” OR “Machine learning” OR “Deep learning” AND “Central nervous system infection” OR “Encephalitis” OR “Meningitis”. The last search was performed on July 20, 2022. Studies were selected based on the population, intervention, comparator, outcome(s) of interest, and study design (PICOS). The Joanna Briggs Institute Cohort Studies and Case Control Research Checklist were used to determine the study quality. Studies that included adolescent and adult patients diagnosed with CNSI via cerebrospinal fluid testing or other laboratory examination and imaging methods were reviewed. Five of the 731 identified articles were included. The studies have focused on the role of ML in the following issues: risk factors for developing healthcare-associated ventriculitis/meningitis, assessing treatment failure in patients with spinal epidural abscess (SEA) who were treated non-operatively, prediction of mortality in patients with SEA, differential diagnosis of meningitis, and comparison of differential diagnoses determined using ML methods and that determined by clinicians. Although more studies are needed in this area, ML may soon be used effectively in the diagnosis of CNSI. It is essential to determine the best ML model for each issue. Artificial intelligence applications could potentially contribute to the rapid diagnosis and effective early treatment of diseases.

The restrictions and closures experienced during the COVID-19 pandemic period have affected the global supply chains greatly. The logistics sector is among the most affected sectors from this process. For this reason, accurate and fast estimation of logistics demand is important for effective resource planning. In this study, the aim is to predict the demand accurately in a third-party logistics company during the COVID-19 pandemic period. The shipment data of a logistics company between June 2020 and December 2020 were examined, and the prediction problem was considered as univariate time series. In the scope of the study, a deep learning-based demand forecasting model is proposed. In the proposed prediction model, convolutional neural network (CNN) and long short-term memory (LSTM) network are integrated. CNN provides feature extraction, LSTM captures long-term dependencies, and the proposed model is called hybrid CNN-LSTM. The prediction performance of the hybrid CNN-LSTM was evaluated by comparing it with the classical prediction approaches as well as machine learning and deep learning approaches. The parameter values of all forecasting methods were determined by experimental studies. According to the experimental results, the proposed hybrid CNN-LSTM method showed higher performance than the other methods. The proposed approach generates input to workforce and resource planning activities by providing accurate estimation of logistics demand. [ABSTRACT FROM AUTHOR]

The COVID-19 virus, which caused the declaration of a worldwide pandemic in 2019, caused serious health problems and even death due to the rapid progression of the disease. Hence, early diagnosis of the disease has been of great importance to prevent the emergence of these adverse conditions. Medical imaging methods, such as X-Ray chest images, Computed Tomography (CT), etc. have played an important role in the detection. Deep learning methods have proven their superior image analysis ability. In this study, it is proposed to use the Vision Transformer (VIT), which has recently been popular in computer vision applications, for Covid-19 detection using X-ray chest images. The effectiveness of the VIT architecture is compared with a popular Convolutional Neural Network architecture, Resnet50 through various criteria, as well as VGG16 and InceptionV3 architectures, which were recorded to be successful in multi-class datasets of COVID-19. As a result of the experiments, it has been observed that the VIT architecture outperforms the Resnet50 and VGG16 architectures trained with the transfer learning method, and it has been observed that it achieves head-to-head results with InceptionV3, and it has been concluded that it can be used as an alternative decision support system for COVID-19 detection. [ABSTRACT FROM AUTHOR]

The demand for artificial intelligence in the world is increasing day by day in the gastronomy sector. In this study, the importance of artificial intelligence in the gastronomy sector is emphasized and the studies on this subject are mentioned. Since the studies in the literature are limited, studies on all sub-branches related to artificial intelligence-based gastronomy and tourism are mentioned. The number of studies related to gastronomy and artificial intelligence in the literature is limited. Therefore, in this study, artificial intelligence applications used in the gastronomy sector are detailed under the subheadings of cuisine, promotion, health, and forecasting. Accordingly, approximately 40 articles were analyzed considering these sub-headings. In light of the information obtained from these studies, artificial intelligence systems to be developed in the gastronomy sector will provide great gains. Moreover, it is estimated that meeting consumer expectations and using innovative technologies in the gastronomy sector will increase the popularity of gastronomy science.