Bilgisayar Mühendisliği Bölümü Koleksiyonu

Bu koleksiyon için kalıcı URI

https://hdl.handle.net/20.500.12899/16

Listeleniyor 1 - 18 / 18

COVID-CCD-Net: COVID-19 and colon cancer diagnosis system with optimized CNN hyperparameters using gradient-based optimizer
(Malatya Turgut Özal Üniversitesi, 2022) Sert,Eser; Kızıloluk,Soner
Coronavirus disease-2019 (COVID-19) is a new types of coronavirus which have turned into a pandemic within a short time. Reverse transcription-polymerase chain reaction (RT-PCR) test is used for the diagnosis of COVID-19 in national healthcare centers. Because the number of PCR test kits is often limited, it is sometimes difficult to diagnose the disease at an early stage. However, X-ray technology is accessible nearly all over the world, and it succeeds in detecting symptoms of COVID-19 more successfully. Another disease which affects people's lives to a great extent is colorectal cancer. Tissue microarray (TMA) is a technological method which is widely used for its high performance in the analysis of colorectal cancer. Computer-assisted approaches which can classify colorectal cancer in TMA images are also needed. In this respect, the present study proposes a convolutional neural network (CNN) classification approach with optimized parameters using gradient-based optimizer (GBO) algorithm. Thanks to the proposed approach, COVID-19, normal, and viral pneumonia in various chest X-ray images can be classified accurately. Additionally, other types such as epithelial and stromal regions in epidermal growth factor receptor (EFGR) colon in TMAs can also be classified. The proposed approach was called COVID-CCD-Net. AlexNet, DarkNet-19, Inception-v3, MobileNet, ResNet-18, and ShuffleNet architectures were used in COVID-CCD-Net, and the hyperparameters of this architecture was optimized for the proposed approach. Two different medical image classification datasets, namely, COVID-19 and Epistroma, were used in the present study. The experimental findings demonstrated that proposed approach increased the classification performance of the non-optimized CNN architectures significantly and displayed a very high classification performance even in very low value of epoch.
Automatic Diagnosis of Snoring Sounds with the Developed Artificial Intelligence-based Hybrid Model
(Turkish Journal of Science and Technology, 2022) Yıldırım,Muhammed
Sleep patterns and sleep continuity have a great impact on people's quality of life. The sound of snoring both reduces the sleep quality of the snorer and disturbs other people in the environment. Interpretation of sleep signals by experts and diagnosis of the disease is a difficult and costly process. Therefore, in the study, an artificial intelligence-based hybrid model was developed for the classification of snoring sounds. In the proposed method, first of all, sound signals were converted into images using the Mel-spectrogram method. The feature maps of the obtained images were obtained using Alexnet and Resnet101 architectures. After combining the feature maps that are different in each architecture, dimension reduction was made using the NCA dimension reduction method. The feature map optimized using the NCA method was classified in the Bilayered Neural Network. In addition, spectrogram images were classified with 8 different CNN models to compare the performance of the proposed model. Later, in order to test the performance of the proposed model, feature maps were obtained using the MFCC method and the obtained feature maps were classified in different classifiers. The accuracy value obtained in the proposed model is 99.5%.
CatSumm: Spektral Çizge Bölmeleme ve Düğüm Merkeziliklerine Dayalı Çıkarıcı Metin Özetleme
(Malatya Turgut Özal Üniversitesi, 2021) Uçkan, Taner; Hark, Cengiz; Karcı, Ali
In this paper, we introduce CatSumm (Cengiz, Ali, Taner Summarization), a novel method for multi-document document summarisation. The suggested method forms a summarization according to three main steps: Representation of input texts, the main stages of the CatSumm model, and sentence scoring. A Text Processing software, is introduced and used to protect the semantic loyalty between word groups at stage of representation of input texts. Spectral Sentence Clustering (SSC), one of the main stages of the CatSumm model, is the summarization process obtained from the proportional values of the sub graphs obtained after spectral graph segmentation. Obtaining super edges is another of the main stages of the method, with the assumption that sentences with weak values below a threshold value calculated by the standard deviation (SD) cannot be included in the summary. Using the different node centrality methods of the CatSumm approach, it forms the sentence rating phase of the recommended summarising approach, determining the significant nodes and hence significant nodes. Finally, the result of the CatSumm method for the purpose of text summarisation within the in the research was measured ROUGE metrics on the Document Understanding Conference (DUC-2004, DUC-2002) datasets. The presented model produced 44.073%, 53.657%, and 56.513% summary success scores for abstracts of 100, 200 and 400 words, respectively
Hurricane-Faster R-CNN-JS: Hurricane detection with faster R-CNN using artificial Jellyfish Search (JS) optimizer
(SPRINGER, 2022) Kızıloluk, Soner; Sert, Eser
A hurricane is a type of storm called tropical cyclone (TC) and is likely to lead to severe storms and heavy rains. An early detection of hurricanes using satellite images can alarm people about upcoming disasters and thus minimize any casualties and material losses. Faster R-CNN is one of the most popular and recent object detection approaches. In the present study, AlexNet hyperparameters, which is a CNN model used as a feature extractor in Faster R-CNN, were optimized using artificial Jellyfish Search (JS), which is a recent algorithm, in order to propose a Faster R-CNN with a higher performance. The proposed approach is called Hurricane-Faster R-CNN-JS, since it is used as an early hurricane detection approach on satellite images before these hurricanes reach the land. The results of the present study demonstrated that hyperparameter optimization increased the detection performance of the proposed approach by 10% compared to AlexNet without optimized hyperparameters. As feature extractors of Faster R-CNN, the present study benefited from various architectures such as MobileNet-V2, GoogLeNet, AlexNet, ResNet 18, ResNet 50, VGG-16 and VGG-19 without any optimized hyperparameters to compare them with the proposed approach. It was observed that Average Precision (AP) of Hurricane-Faster R-CNN-JS was 97.39%, which was a remarkably higher AP level compared to other approaches.
Ensemble Residual Network Features and Cubic-SVM Based Tomato Leaves Disease Classification System
(International Information and Engineering Technology Association, 2022) Özyurt, Fatih; Sert, Eser; Avcı, Derya
The need for automatic disease detection applications that can help farmers in the detection of agricultural product diseases is increasing day by day. Convolutional Neural Network (CNN) is a very popular field in image processing, recognition, and classification. It is seen that CNN architectures are used in the determination of agricultural products. In this study, 3 different ResNet architectures of the features automatically are used in the detection of tomato diseases. The most efficient features obtained from these architectures have been obtained by the NCA algorithm again. The features obtained have been trained with the Cubic SVM machine learning algorithm. Tomato leaves belonging to a total of 10 classes have been trained at 80% and a test performance rate of 98.2% has been achieved.
Wireless Communication Protocols for Project Developers in IoT Applications
(2021) Topaloğlu, Fatih
The effective use of network technologies in IoT applications necessitates the determination and use of the most efficient wireless network protocols according to the application area and scope. A project developed with IoT systems uses network technology and protocol structure that includes many protocols according to its purpose and scope. The protocols used include the communication of hardware, data communication and standards of how this communication starts and ends in IoT applications. Choosing the most suitable connection for project and application developer engineers in the product line covering IoT applications is of great importance for the efficient operation of the system. In the study, the most effective wireless network protocols for IoT applications were researched, explained and comparisons were made.
Sis Hesaplamada Sis Düğümlerinin Rolü ve Mimari Yapısı
(2021) Topaloğlu, Fatih
Sis hesaplama, IoT uç cihazlar ve bulut arasındaki katmanda cihaz üstünde gerçekleşen bilişimi ifade eder. Sis bilişimin temelinde sis düğümleri yatar. Sis düğümleri coğrafi olarak dağınık durumda bulunan, zengin kaynaklı, ağın herhangi bir yerine konumlandırılabilecek cihazlardır. Sis düğümleri, yönetimi basitleştiren, güç ve alan gereksinimlerini azaltan birleştirilmiş bilgi işlem, ağ ve depolama alanına sahiptir. Bununla birlikte, sis hesaplama hala emekleme aşamasındadır ve hala açık problemler vardır. IoT uygulamalarında ağ geçidi ve uç düğümler, uçta gerçek zamanlı analiz gerektiren işlemlerde, verilerin sıkıştırılması işleminde ve bulut ile iletişimde meydana gelen gecikme için yetersiz kalmaktadır. Makalede, sis hesaplamada sis düğümlerinin rolü ve sis düğüm mimarisine odaklanarak bu problemlerin çözümü için detaylı analizler ve çözüm önerileri ortaya konmuştur.
Sis Bilişim: Güvenlik Boyutları ve Güvenlik Analizi
(2021) Topaloğlu, Fatih
Sis bilişim, bulut bilişimi ağların kenarına kadar genişleten bir paradigmadır. Sis bilişimin öne çıkan özelliği dağınık ve son kullanıcılara yakın hizmetler sunmasıdır. Bu özellik, gizliliğin ve verilerin güvenliğinin korunması açısından çok önemlidir. Çünkü, sis bilişimin dağıtılmış mimarisi saldırı vektörlerinin sayısını arttırarak uç cihazların sahip olduğu verileri daha savunmasız hale getirir ve kötü amaçlı yazılım sızmalarına ve güvenlik açıklarına neden olur. Makale sis bilişim ortamındaki çeşitli güvenlik unsurlarının boyutlarını ve kapsamlı teknik analizini içermektedir. Bu çalışma iki nedenden dolayı ele alınmıştır. Birincisi, güvenlik, IoT sistemleri arasında belki de en büyük teknik kaygıdır, dolayısıyla özel bir çalışma olarak ele alınması gerekmektedir. İkincisi, çalışma son derece teknik ayrıntılar içerdiğinden güvenlik uzmanlarının en çok ilgi duyduğu bilgilerin bir kaynakta toplanması amaçlanmıştır.
Industrial Automation and Edge Computing SCADA PLC PAC IO-LINK-2
(Fırat Üniversitesi, 2021) Topaloğlu, Fatih
Increasing interest in Industry 4.0 applications has brought with it many new technologies and strategies for processing all kinds of production-related data, which are at the center of this trend. Although many of these technologies are not very new, they have not yet reached sufficient recognition in the industry. The term edge computing is among the concepts that need to be clarified in this context. Edge computing draws local intelligence and data processing capability to the parts of the communication network close to the end devices such as pumps, motors, sensors, relays that produce data, and performs the analysis of the data without the need to transfer it somewhere. However, this process also has difficulties. Edge computing architectures in industrial applications need to address bandwidth, management complexity, latency, and network security risks. With this study, four important architectural solutions that help to optimize resource usage on the edge computing platform for industrial applications are proposed and analyzed.
Kalite Test Fonksiyonları Kullanılarak Güncel Metasezgisel Optimizasyon Algoritmalarının Karşılaştırılması
(Munzur Üniversitesi, 2021) Kızıloluk, Soner; Can, Ümit
Doğadaki canlıların sürü davranışlarından, bitkilerden, insana özgü olgulardan, fizik, matematik, biyoloji ve kimya gibi bilimsel alanlardaki olaylardan esinlenen onlarca metasezgisel optimizasyon yöntemi mevcuttur. Bu yöntemler belirli problemlerde başarılı olmakla birlikte bütün problemlerde başarılı olamamaktadır. Bundan dolayı araştırmacılar tarafından her geçen gün yeni metasezgisel yöntemler önerilmektedir. Bu çalışmada ilk defa güncel Yapay Deniz Anası Optimizasyonu, Etçil Bitki Optimizasyonu, Giza Piramitleri İnşaatı Optimizasyonu, Gradyan Tabanlı Optimizasyon, Öğrenci Psikolojisine Dayalı Optimizasyon ve Tunik Sürüsü Optimizasyonu olmak üzere altı güncel metasezgisel optimizasyon algoritması 10 adet matematiksel kalite testi foksiyonunda 10, 30 ve 50 boyut değerleri baz alınarak ayrıntılı bir şekilde karşılaştırılmıştır. Elde edilen sonuçlara göre 10 kalite testinden 7’sinde en iyi sonuçları Öğrenci Psikolojisine Dayalı Optimizasyon vermiştir. Gradyan Tabanlı Optimizasyon’un ise 4 kalite testinde en iyi sonuçları verdiği görülmüştür. En kötü performansı ise Etçil Bitki Optimizasyonu ve Tunik Sürüsü Optimizasyonu göstermiştir. Süre bakımından karşılaştırmak üzere algoritmalar 50 boyutlu test fonksiyonlarında 1000 iterasyonda çalıştırılmış ve elde edilen ortalama çalışma süreleri incelendiğinde, Yapay Deniz Anası Optimizasyonu ve Tunik Sürüsü Optimizasyonu’nun en hızlı çalışan algoritmalar olduğu görülmektedir. Etçil Bitki Optimizasyonu ve Öğrenci Psikolojisine Dayalı Optimizasyon ise en yavaş çalışan algoritmalar olmuştur.
Random Number Generator Based on Discrete Cosine Transform Based Lossy Picture Compression
(Malatya Turgut Ozal University, 2021) Yakut, Selman; Yakut, Selman
The The widespread use of digital data makes the security of this data important. Various cryptographic systems are used to ensure the security of this data. The most important part of these systems is random numbers. In this article, a random number generator based on the discrete cosine transform, which is the basis of image compression algorithms, is proposed. In this generator, the difference between the original image and the compressed image produced using the discrete cosine transform is used. The original picture is transferred to the frequency plane using the discrete cosine transform. It is then converted back to the space plane using the inverse discrete cosine transform. These transformations cause some losses as certain coefficients are taken into account. Raw random numbers were generated using the differences between the original image and the compressed image. Then, the possible weaknesses in the random numbers generated by passing these raw data through the hash function were fixed. The SHA-512 algorithm was used as the hash function. An important advantage of the developed system is that it can be easily produced using any digital data source. It has been shown by the analysis that the generated random numbers are safe.
Comparison of Standard and Pretrained CNN Models for Potato, Cotton, Bean and Banana Disease Detection
(Malatya Turgut Ozal University, 2021) Kızıloluk, Soner
Plant diseases lead to a significant decrease in product efficiency and economic losses for producers. However, early detection of plant diseases plays an important role in preventing these losses. Today, Convolutional Neural Network (CNN) models are widely used for image processing in many fields such as face recognition, climate, health, and agriculture. But in these models, the weights of the layers are randomly initialized during training, which increases training time and decreases performance. With the method known as Transfer Learning in the literature, CNN models are trained on large databases such as ImageNet. Then, pretrained CNN models are created using the weights obtained in this training. Thus, training time decreases while performance improves. In this study, standard and pretrained versions of popular CNN models DarkNet-19, GoogleNet, Inception-v3, Resnet-18, and ShuffleNet have been used for automatic classification of diseases from leaf images of potato, cotton, bean, and banana. In the experimental study, the classification performances of all these standard and pretrained CNN models are presented comparatively. Experimental results have shown that the performance of CNN models is significantly improved by transfer learning, even in a small number of epochs
In Dynamic Systems with Fuzzy α - Cutting Determination of Membership Function Rang
(Malatya Turgut Ozal University, 2020) Topaloğlu, Fatih; Pehlivan, Hüseyin
Uncertainties and inaccuracies in the membership function value ranges defined by the expert in dynamic systems cause serious errors in system output. In this study, fuzzy ?-cutting technique was used to determine the ranges of membership functions on the universal cluster and neighborhood values of normal values were calculated for different ? cutting coefficients and then neighborhood values were adjusted according to determined step values. Thus, while determining the value range of membership function in dynamic systems, it will be possible to talk about its neighborhood in the values that serve the same purpose. Operation in the dynamic process as wind power installation for Turkey wind energy interval value set in the potential atlas used and ? cutting techniques of the gap on the universal set of the determined value with re-calculation and determination are provided.
A new 3D segmentation approach using extreme learning machine algorithm and morphological operations
(Elsevier, 2020) Kaya, Ertuğrul; Sert, Eser
Segmentation is one of the most crucial steps of image processing. Because 3D images contain depth information, they have gradually gained importance for numerical systems in image analysis. In the present study, a new 3D segmentation method based on extreme learning machine and morphological operations (3DS-ELM) is proposed. The present study benefits from extreme learning machine (ELM) algorithm, which is a novel and fast learning algorithm for single-hidden layer feedforward networks (SLFNs), for training objects. Because a 3D model contains many points, direct segmentation on a 3D model is time-consuming and causes problems in the segmentation process, the proposed approach minimizes these problems and offers a quick and high-performance 3D segmentation method that can be used in various industrial fields. The proposed 3DS-ELM was compared with different approaches in order to analyze its 3D segmentation performance. Experimental studies proved that the proposed 3DS-ELM performed better than other approaches.
An effective Turkey marble classification system: Convolutional neural network with genetic algorithm -wavelet kernel - Extreme learning machine
(IIETA International Information and Engineering Technology Association, 2021) Avcı, Derya; Sert, Eser
Marble is one of the most popular decorative elements. Marble quality varies depending on its vein patterns and color, which are the two most important factors affecting marble quality and class. The manual classification of marbles is likely to lead to various mistakes due to different optical illusions. However, computer vision minimizes these mistakes thanks to artificial intelligence and machine learning. The present study proposes the Convolutional Neural Network- (CNN-) with genetic algorithm- (GA) Wavelet Kernel- (WK-) Extreme Learning Machine (ELM) (CNN–GA-WK-ELM) approach. Using CNN architectures such as AlexNet, VGG-19, SqueezeNet, and ResNet-50, the proposed approach obtained 4 different feature vectors from 10 different marble images. Later, Genetic Algorithm (GA) was used to optimize adjustable parameters, i.e. k, 1, and m, and hidden layer neuron number in Wavelet Kernel (WK) – Extreme Learning Machine (ELM) and to increase the performance of ELM. Finally, 4 different feature vector parameters were optimized and classified using the WK-ELM classifier. The proposed CNN–GA-WK-ELM yielded an accuracy rate of 98.20%, 96.40%, 96.20%, and 95.60% using AlexNet, SequeezeNet, VGG-19, and ResNet-50, respectively.
Fine-Tuning of Feedback Gain Control for Hover Quad Copter Rotors by Stochastic Optimization Methods
(Springer, 2020) Ateş, Abdullah; Baykant Alagöz, Barış; Kavuran, Gürkan; Yeroğlu, Celaleddin
Three degree of freedom (3 DOF) Hover Quad Copter (HQC) platforms are implemented for various missions in diverse scales from the micro to macro platforms. As HQC platforms scale down, micro platform requires rather robust and effective control techniques. This study investigates applicability of some stochastic optimization methods for tuning feedback gain control of HQC rotors and compares optimization results with results of linear quadratic regulator (LQR) method that has been widely used analytical method for optimal feedback gain control of HQCs. This study considers the utilization of two stochastic methods for tuning of HQCs. These methods are stochastic multi-parameter divergence optimization method (SMDO) and discrete stochastic optimization method (DSO). These methods are employed to optimize feedback gain coefficients of an experimental HQC test platform. Simulation and experimental results of SMDO and DSO methods are reported and compared with results of LQR method.
A New Secure and Efficient Approach for TRNG and Its Post-Processing Algorithms
(World Scientific, 2020) Yakut, Selman; Tuncer, Taner; Özer, Ahmet Bedri
Chaotic systems; post-processing; post-processing algorithm; secure random numbers
UC-merced image classification with CNN feature reduction using wavelet entropy optimized with genetic algorithm
(International Information and Engineering Technology Association, 2020) Özyurt, Fatih; Ava, Engin; Sert, Eser
The classification of high-resolution and remote sensed terrain images with high accuracy is one of the greatest challenges in machine learning. In the present study, a novel CNN feature reduction using Wavelet Entropy Optimized with Genetic Algorithm (GA-WEE-CNN) method was used for remote sensing images classification. The optimal wavelet family and optimal value of the parameters of the Wavelet Sure Entropy (WSE), Wavelet Nom Entropy (WNE), and Wavelet Threshold Entropy (WTE) were calculated, and given to classifiers such as K-Nearest Neighbors (KNN) and Support Vector Machine (SVM). The efficiency of the proposed hybrid method was tested using the UC-Merced dataset. 80% of the data were used as training data, and a performance rate of 98.8% was achieved with SVM classifier, which has been the highest ratio compared to all studies using same dataset so far with only 18 features. These results proved the advantage of the proposed method.

Güncel Gönderiler