Yazılım Mühendisliği Bölümü Makale Koleksiyonu

Bu koleksiyon için kalıcı URI

https://hdl.handle.net/20.500.12418/328

Listeleniyor 1 - 9 / 9

MI-STEG: A Medical Image Steganalysis Framework Based on Ensemble Deep Learning
(Tech Science Press, 2023) Karakış, Rukiye
Medical image steganography aims to increase data security by concealing patient-personal information as well as diagnostic and therapeutic data in the spatial or frequency domain of radiological images. On the other hand, the discipline of image steganalysis generally provides a classification based on whether an image has hidden data or not. Inspired by previous studies on image steganalysis, this study proposes a deep ensemble learning model for medical image steganalysis to detect malicious hidden data in medical images and develop medical image steganography methods aimed at securing personal information. With this purpose in mind, a dataset containing brain Magnetic Resonance (MR) images of healthy individuals and epileptic patients was built. Spatial Version of the Universal Wavelet Relative Distortion (S-UNIWARD), Highly Undetectable Stego (HUGO), and Minimizing the Power of Optimal Detector (MIPOD) techniques used in spatial image steganalysis were adapted to the problem, and various payloads of confidential data were hidden in medical images. The architectures of medical image steganalysis networks were transferred separately from eleven Dense Convolutional Network (DenseNet), Residual Neural Network (ResNet), and Inception-based models. The steganalysis outputs of these networks were determined by assembling models separately for each spatial embedding method with different payload ratios. The study demonstrated the success of pre-trained ResNet, DenseNet, and Inception models in the cover-stego mismatch scenario for each hiding technique with different payloads. Due to the high detection accuracy achieved, the proposed model has the potential to lead to the development of novel medical image steganography algorithms that existing deep learning-based steganalysis methods cannot detect. The experiments and the evaluations clearly proved this attempt.
Improving Brain Tumor Classification with Deep Learning Using Synthetic Data
(Tech Science Press, 2023) Yapıcı, Muhammed Mutlu; Karakış, Rukiye; Gürkahraman, Kali
Deep learning (DL) techniques, which do not need complex pre-processing and feature analysis, are used in many areas of medicine and achieve promising results. On the other hand, in medical studies, a limited dataset decreases the abstraction ability of the DL model. In this context, we aimed to produce synthetic brain images including three tumor types (glioma, meningioma, and pituitary), unlike traditional data augmentation methods, and classify them with DL. This study proposes a tumor classification model consisting of a Dense Convolutional Network (DenseNet121)-based DL model to prevent forgetting problems in deep networks and delay information flow between layers. By comparing models trained on two different datasets, we demonstrated the effect of synthetic images generated by Cycle Generative Adversarial Network (CycleGAN) on the generalization of DL. One model is trained only on the original dataset, while the other is trained on the combined dataset of synthetic and original images. Synthetic data generated by CycleGAN improved the best accuracy values for glioma, meningioma, and pituitary tumor classes from 0.9633, 0.9569, and 0.9904 to 0.9968, 0.9920, and 0.9952, respectively. The developed model using synthetic data obtained a higher accuracy value than the related studies in the literature. Additionally, except for pixel-level and affine transform data augmentation, synthetic data has been generated in the figshare brain dataset for the first time.
A comprehensive review of automatic programming methods
(09.07.2023) Arslan, Sibel; Ozturk,Celal
Automatic programming (AP) is one of the most attractive branches of artificial intelligence because it provides effective solutions to problems with limited knowledge in many different application areas. AP methods can be used to determine the effects of a system’s inputs on its outputs. Although there is increasing interest in solving many problems using these methods for a variety of applications, there is a lack of reviews that address the methods. Therefore, the goal of this paper is to provide a comprehensive literature review of AP methods. At the same time, we mention the main characteristics of the methods by grouping them according to how they represent solutions. We also try to give an outlook on the future of the field by highlighting possible bottlenecks and perspectives for the benefit of the researchers involved.
Investigating the best automatic programming method in predicting the aerodynamic characteristics of wind turbine blade
(Elsevier, 03.05.2023) Arslan, Sibel; Koca, Kemal
Automatic programming (AP) is a subfield of artificial intelligence (AI) that can automatically generate computer programs and solve complex engineering problems. This paper presents the accuracy of four different AP methods in predicting the aerodynamic coefficients and power efficiency of the AH 93-W-145 wind turbine blade at different Reynolds numbers and angles of attack. For the first time in the literature, Genetic Programming (GP) and Artificial Bee Colony Programming (ABCP) methods are used for such predictions. In addition, Airfoil Tools and JavaFoil are utilized for airfoil selection and dataset generation. The Reynolds number and angle of attack of the wind turbine airfoil are input parameters, while the coefficients 𝐶𝐿, 𝐶𝐷 and power efficiency are output parameters. The results show that while all four methods tested in the study accurately predict the aerodynamic coefficients, Multi Gene GP (MGGP) method achieves the highest accuracy for 𝑅2 Train and 𝑅2 Test (𝑅2 values in 𝐶𝐷 Train: 0.997-Test: 0.994, in 𝐶𝐿 Train: 0.991-Test: 0.990, in 𝑃𝐸 Train: 0.990-Test: 0.970). By providing the most precise model for properly predicting the aerodynamic performance of higher cambered wind turbine airfoils, this innovative and comprehensive study will close a research gap. This will make a significant contribution to the field of AI and aerodynamics research without experimental cost, labor, and additional time.
Support Vector Machine (SVM) Application for Uniaxial Compression Strength (UCS) Prediction: A Case Study for Maragheh Limestone
(09.02.2023) Cemiloglu, Ahmed; Zhu Licai; Arslan, Sibel; Xu,Jinxia; Yuan,Xiaofeng; Azarafza, Mohammad; Derakhshani, Reza
The geomechanical properties of rock materials, such as uniaxial compression strength (UCS), are the main requirements for geo-engineering design and construction. A proper understanding of UCS has a significant impression on the safe design of different foundations on rocks. So, applying fast and reliable approaches to predict UCS based on limited data can be an efficient alternative to regular traditional fitting curves. In order to improve the prediction accuracy of UCS, the presented study attempted to utilize the support vector machine (SVM) algorithm. Multiple training and testing datasets were prepared for the UCS predictions based on a total of 120 samples recorded on limestone from the Maragheh region, northwest Iran, which were used to achieve a high precision rate for UCS prediction. The models were validated using a confusion matrix, loss functions, and error tables (MAE, MSE, and RMSE). In addition, 24 samples were tested (20% of the primary dataset) and used for the model justifications. Referring to the results of the study, the SVM (accuracy = 0.91/precision = 0.86) showed good agreement with the actual data, and the estimated coefficient of determination (R2) reached 0.967, showing that the model’s performance was impressively better than that of traditional fitting curves.
A new lattice based artificial bee colony algorithm for EEG noise minimization
(2023) Arslan, Sibel; Aslan, Selçuk
Geçtiğimiz yıllar büyük veri olarak adlandırılan yeni bir kavramla başlayan değişimlere tanıklık etmiştir. Bu yeni kavram ve özellikleri gerçek hayat en iyileme problemlerinin tanımlarını değiştirmiş ve daha önce önerilen çözüm yöntemlerinin performanslarının incelenmesi ve büyük veri kavramının özelliklerini dikkate alarak yeni yöntemlerin geliştirilmesi kritik hale gelmiştir. Arıların yiyecek arama davranışlarından ilham alan Yapay Arı Koloni (ABC) algoritması sürü zekâsı temelli yöntemlerinin en başarıları arasındadır. Bu çalışmada, ABC algoritmasının işçi ve gözcü arı fazları elektroensefalografi sinyallerinde gürültü minimizasyonunu gerektiren büyük veri en iyileme probleminin çözümü için düzenlenmiş ve kafes temelli ABC algoritması (LBABC) tanıtılmıştır. Önerilen yöntemin çözüm kapasitesinin analizi için farklı problem örneklerini içeren bir dizi uygulama gerçekleştirilmiştir. Elde edilen sonuçlar yaygın kullanılan yöntemler tarafından elde edilen sonuçlar ile de kıyaslanmıştır. Karşılaştırma sonuçlarından, yeni yönteminin test problemlerinin tamamına yakınında diğer yöntemlerden daha iyi ya da oldukça yakın çözümlere ulaşabildiği anlaşılmıştır.
Stress Analysis of 2D-FG Rectangular Plates with Multi-Gene Genetic Programming
(MDPIST ALBAN-ANLAGE 66, CH-4052 BASEL, SWITZERLAND, 16.08.2022) Arslan, Sibel; Demirbas, Munise Didem; Çakır, Didem; Ozturk,Celal
Functionally Graded Materials (FGMs) are designed for use in high-temperature applications. Since the mass production of FGM has not yet been made, the determination of its thermomechanical limits depends on the compositional gradient exponent value. In this study, an efficient working model is created for the thermal stress problem of the 2D-FG plate using Multi-gene Genetic Programming (MGGP). In our MGGP model in this study, data sets obtained from the numerical analysis results of the thermal stress problem are used, and formulas that give equivalent stress levels as output data, with the input data being the compositional gradient exponent, are obtained. For the current problem, efficient models that reduce CPU processing time are obtained by using the MGGP method.
Biosorption of methyl orange from aqueous solution with hemp waste, investigation of isotherm, kinetic and thermodynamic studies and modeling using multigene genetic programming
(SPRINGER INT PUBL AGGEWERBESTRASSE 11, CHAM CH-6330, SWITZERLAND, 16.08.2022) Kütük, Nurşah; Arslan, Sibel
Water resources around the world are getting polluted day by day due to the rapidly developing industry. Industrial wastes have caused serious damage to the environment in recent years. Especially, dyes are waste products that mix with waters such as lakes, rivers and seas and have toxic and carcinogenic effects. In this study, the removal of methyl orange (MO) dye, which was chosen as a model dye compound, from aqueous solution by biosorption using hemp waste was investigated. The biosorption process was optimized by the parameters of pH, initial dye concentration and amount of biosorbent. Biosorption of MO to hemp waste was investigated by isotherms, kinetics and thermodynamic studies. It was determined that the biosorption equilibrium fitted to the Langmuir isotherm (R2 =0.9739). As a result of the experimental studies, 83% biosorption value and 1428 mg/g maximum biosorption capacity were reached with 250 mg/L dye concentration and 0.5 g/L biosorbent amount at pH = 2. It was determined that the reaction kinetics were in accordance with the pseudo-second-order kinetics (R2 =0.9911). In addition to, the study aims to evaluate to what extent the modeling of the biosorption process is successful. For this purpose, we used multigene genetic programming (MGGP), which has been renewed with the latest developments in the field of model extraction. The results show that MGGP is efficient for modeling the biosorption process in real environments. The analysis of MGGP models also showed that pH is the most important parameter affecting the biosorption process.
A modified artificial bee colony algorithm for classification optimisation
(INDERSCIENCE ENTERPRISES LTDWORLD TRADE CENTER BLDG, 29 ROUTE DE PRE-BOIS, CASE POSTALE 856, CH-1215 GENEVA, SWITZERLAND, 18.10.2022) Aslan, Selçuk; Arslan, Sibel
The promising capabilities, easily implementable and customisable structures of the meta-heuristic algorithms have increased the researchers’ attentions to the well-known problems and their new approximations that are suitable to be solved with the meta-heuristics directly. In this study, an attempt was made to solve with an artificial bee colony (ABC)-based technique called classifierABC algorithm, a new approximation that defines the classification problem by using a set of linear equations. The performance of the classifierABC was investigated in detail by using various datasets and assigning different values to the algorithm specific control parameters. The results obtained by the classifierABC algorithm were also compared with the results of the other meta-heuristics including particle swarm optimisation (PSO), differential evaluation (DE), fireworks algorithm (FWA) and different variants of the FWA. Comparative studies showed that the classifierABC solves the new problem approximation more robustly and its solutions determine the classes of instances in sets with high accuracies.

Güncel Gönderiler