Urban traffic congestion remains a major challenge in intelligent transportation systems, requiring adaptive and data-driven traffic control strategies. This study proposes a simulation-based adaptive traffic signal control framework using deep learning and metaheuristic optimization. The framework integrates YOLOv8-based vehicle detection with a Kernel Extreme Learning Machine classifier optimized using Particle Swarm Optimization, Genetic Algorithm, Artificial Bee Colony, and Grey Wolf Optimizer. Vehicle counts and classes extracted from traffic images determine adaptive signal timings within a custom simulation environment. All optimization algorithms were evaluated over 30 independent runs using different random seeds. The Genetic Algorithm-optimized model achieved the highest classification accuracy (91.733%), and statistical analyses confirmed its superiority over competing methods. The YOLOv8 model achieved a mAP@50 of 92%. Simulation results demonstrated dynamic signal-time reallocation according to changing traffic demand compared with fixed-time control. The findings indicate that the proposed framework can support adaptive traffic management using existing roadside camera infrastructure.

Monkeypox is a viral disease belonging to the smallpox family. Although it has milder symptoms than smallpox in humans, it has become a global threat in recent years, especially in African countries. Initially, incidental immunity against monkeypox was provided by smallpox vaccines. However, the eradication of smallpox over time and thus the lack of vaccination has led to the widespread and clinical importance of monkeypox. Although mathematical epidemiology research on the disease is complementary to clinical studies, it has attracted attention in the last few years. The present study aims to discuss the indispensable effects of three control strategies such as vaccination, treatment, and quarantine to prevent the monkeypox epidemic modeled via the Atangana–Baleanu operator. The main purpose is to determine optimal control measures planned to reduce the rates of exposed and infected individuals at the minimum costs. For the controlled model, the existence-uniqueness of the solutions, stability, and sensitivity analysis, and numerical optimal solutions are exhibited. The optimal system is numerically solved using the Adams-type predictor–corrector method. In the numerical simulations, the efficacy of the vaccination, treatment, and quarantine controls is evaluated in separate analyzes as single-, double-, and triple-control strategies. The results demonstrate that the most effective strategy for achieving the aimed outcome is the simultaneous application of vaccination, treatment, and quarantine controls.

Facial expressions are universally understood and often linked to specific emotional states. These expressions result from the movement of facial muscles and are typically characterized by changes in the eyes, eyebrows, mouth, and cheeks. Basic facial expressions include surprise, sadness, neutrality, happiness, disgust, anger, and fear. Various approaches have been developed for facial expression classification. In this study, a new dataset was created by merging two commonly used datasets, CK + and KDEF, resulting in a total of 2,101 samples. Initially, appearance-based filters such as Gabor, SIFT, HOG, and LBP were applied for image preprocessing. Feature extraction was then conducted using the EfficientNetB7 convolutional neural network. The extracted features were individually classified for each filter using Support Vector Machines (SVM) and Multi-Layer Perceptron (MLP) models. Additionally, a hybrid model was proposed, evaluating features extracted from each appearance-based filter independently, which were then classified using deep learning methods. Among all methods evaluated, the highest accuracy of 91.92

Cervical cancer is the most common and fatal disease encountered by women worldwide. Early diagnosis of cervical cancer plays a critical role in reducing mortality rates and initiating the treatment process early. In this study, a hybrid model was developed to detect cervical cancer with high accuracy. In the developed model, 1280 and 768 features were extracted from each image, respectively, using pre-trained EfficientNet V2-M and Vision Transformer (ViT) architectures as the base; these features were combined to obtain a combined feature vector of 2048 dimensions. A feature attention mechanism was applied to highlight the important information in the data input, and then dimensionality reduction was performed using the mRMR and NCA methods. 838 standard features between the features selected with both methods were classified with six different machine learning algorithms. In the study, the five-class public SIPaKMeD dataset was used. The proposed model achieved a high accuracy value of 99.02

Environmental Sound Classification (ESC) has become a fundamental component of intelligent acoustic systems, enabling applications such as smart cities, environmental monitoring, and public safety. This study proposes a comprehensive feature-level fusion framework for machine learning-based ESC. We extract complementary features from the UrbanSound8K dataset—time-domain attributes (Zero Crossing Rate and Root Mean Square) and frequency-domain descriptors (Mel-Frequency Cepstral Coefficients and Chroma) —which are then concatenated into an enriched representation space. To ensure robustness, multiple preprocessing configurations were evaluated across various window sizes, hop lengths, and sampling rates. Seven classifiers, including a Multi-Layer Perceptron (MLP), XGBoost, and Support Vector Machine (SVM), were systematically compared using both individual and fused feature sets. The results empirically demonstrate that feature-level fusion consistently enhances classification performance, achieving a maximum accuracy of 94.4% with the MLP model and significantly outperforming the baseline configurations that rely on individual features. These findings affirm that the integration of heterogeneous acoustic features at the feature level substantially improves the generalization and robustness of environmental sound recognition, offering a scalable pathway for real-world acoustic scene analysis and intelligent monitoring infrastructures. Our main contributions are summarized as follows: 1. A comprehensive feature-level fusion strategy is proposed, integrating both time-domain (ZCR, RMS) and frequency-domain (MFCC, Chroma) acoustic features to construct a robust and discriminative representation for environmental sound classification. 2. A comprehensive experimental setup is designed, enabling a detailed performance analysis across diverse acoustic pre-processing configurations by systematically varying window size, hop length, and sampling rate parameters. 3. A systematic evaluation of multiple machine learning classifiers—including SVM, K-NN, Decision Tree, Random Forest, Naive Bayes, XGBoost, and Multi-Layer Perceptron (MLP)—is conducted to assess the impact of feature fusion on classification performance. 4. Performance comparisons demonstrate that the fused feature set significantly outperforms individual feature inputs, achieving a peak classification accuracy of 94.4% with the MLP model, thereby validating the efficacy of the proposed fusion approach. 5. The results validate the suitability of the proposed system for real-world acoustic monitoring tasks, including smart city surveillance and urban environmental sound recognition.

With the rise of large datasets in the healthcare sector, machine learning methods have gained significant importance in analyzing, predicting, and discovering patterns within diabetes datasets. This study focuses on the early diagnosis of diabetes by comparing the performance of seven machine learning models and exploring the impact of Explainable Artificial Intelligence (XAI) techniques. The models-K-Nearest Neighbors (KNN), Support Vector Machines (SVM), Naive Bayes, Artificial Neural Networks (ANN), Decision Trees, Random Forest, and XGBoost-were evaluated using a well-structured pipeline that included data cleaning, preprocessing, training, and testing stages. Performance metrics such as accuracy, F1 score, sensitivity, and specificity were applied for robust evaluation. Unlike many previous studies, this research integrates XAI methods like SHAP (Shapley Additive Explanations) and LIME (Local Interpretable Model-Agnostic Explanations) to enhance the interpretability of the best-performing model. These techniques identified critical features contributing to the model's decisions, enabling better insights into the decision-making process. Additionally, the findings were validated through expert opinions to ensure real-world applicability. The results demonstrated significant improvements, with XGBoost achieving an accuracy rate of 98.91%, outperforming the KNN (81.18%), SVM (75.38%), Naive Bayes (75.49%), ANN (74.83%), Decision Trees (76.91%), and Random Forest (91.68%) models. This study highlights the potential of integrating machine learning with XAI techniques for transparent and effective diabetes diagnosis.

The ongoing drought constitutes a pivotal environmental challenge for the Mediterranean Region of Türkiye, where elevated climatic variability and erratic precipitation patterns result in considerable agricultural and hydrological stress. This study applied two artificial intelligence models—artificial neural network (ANN) and Random Forest (RF)—to forecast meteorological drought using the Standardized Precipitation Index (SPI) derived from nearly a century of monthly precipitation data (1929–2024) across eight provinces: Adana, Antalya, Burdur, Hatay, Isparta, Kahramanmaraş, Mersin, and Osmaniye. The models were evaluated at four accumulation periods (SPI-3, SPI-6, SPI-12, and SPI-24) using multiple statistical indicators. The findings indicated that artificial neural networks (ANNs) attained the highest predictive accuracy at extended timescales (SPI-12 and SPI-24), with R2 values reaching up to 0.94. This outcome signifies the capacity of ANNs to discern nonlinear and persistent drought patterns. The RF model exhibited enhanced stability and responsiveness in short-term forecasts (SPI-3, R2 = 0.89), effectively reproducing rapid fluctuations in rainfall. The comparative findings underscore the complementary strengths of the two models: ANN is better suited for the analysis of long-term drought trends and the study of climate adaptation, while RF offers reliable, low-complexity forecasting for the operational monitoring of drought. Utilizing solely precipitation data, the approach furnishes a cost-effective and transferable framework for data-limited regions. The study proposes a reproducible AI-based methodology that enhances the precision of drought prediction, supports early-warning applications, and strengthens regional water resource management under increasing climatic uncertainty.

Pes planus is a foot problem that occurs when the arch of the foot is lower than normal. Techniques such as radiography are actively used for its diagnosis. Artificial intelligence plays an important role in medical diagnoses when combined with traditional methods. It provides a faster and more accurate process in diagnosing diseases with its performance in image analysis. In the study, the use of artificial intelligence in diagnosing a foot deformity called pes planus from x-ray images is discussed. The stages of the study are feature extraction, feature selection and classification. After the feature extraction step, the most important 300 features were selected for each method from the features obtained using the Relief-F, Lasso and RFE methods. The classifier parameters were determined with the Optuna method and the K-Nearest Neighbor (KNN), Support Vector Machine (SVM), Decision Tree (DT), XGBoost and CatBoost algorithms classified the data as normal and pes planus using these features. The results show that the XGBoost algorithm provides the highest performance with 97% accuracy for the features selected with the Relief-F method. This finding indicates a high success rate compared to similar studies. The limited number of studies in the literature on pes planus and artificial intelligence, and the fact that there is only one study that includes artificial intelligence-assisted diagnosis via X-ray images, reveal its innovative aspect. It is expected that artificial intelligence will be an important tool in the early diagnosis of the disease by optimizing the diagnostic processes of the study.

Background/Objectives: Pes planus (flat feet) is a condition characterized by flatter than normal soles of the foot. In this study, a Vision Transformer (ViT)-based deep learning architecture is proposed to automate the diagnosis of pes planus. The model analyzes foot images and classifies them into two classes, as “pes planus” and “not pes planus”. In the literature, models based on Convolutional neural networks (CNNs) can automatically perform such classification, regression, and prediction processes, but these models cannot capture long-term addictions and general conditions. Methods: In this study, the pes planus dataset, which is openly available on the Kaggle database, was used. This paper suggests a ViT-OELM hybrid model for automatic diagnosis from the obtained pes planus images. The suggested ViT-OELM hybrid model includes an attention mechanism for feature extraction from the pes planus images. A total of 1000 features obtained for each sample image from this attention mechanism are used as inputs for an Optimum Extreme Learning Machine (OELM) classifier using various activation functions, and are classified. Results: In this study, the performance of this suggested ViT-OELM hybrid model is compared with some other studies, which used the same pes planus database. These comparison results are given. The suggested ViT-OELM hybrid model was trained for binary classification. The performance metrics were computed in testing phase. The model showed 98.04% accuracy, 98.04% recall, 98.05% precision, and an F-1 score of 98.03%. Conclusions: Our suggested ViT-OELM hybrid model demonstrates superior performance compared to those of other studies, which used the same dataset, in the literature.

Termal kameralar, cisimlerin sıcaklık farklılıklarını kızılötesi ışın değerlerine bağlı olarak renklendirdiği görüntüleme sistemleridir. Günümüzde başta savunma sanayi olmak üzere sağlık, ziraat, inşaat gibi birçok farklı alanda termal kameralar kullanılmaktadır. Özellikle savunma sanayi alanında kullanılan bu kameralardan elde edilen görüntüler, çeşitli nesnelerin ve canlıların tespiti için büyük önem arz etmektedir. Bu çalışmada termal kamera görüntülerinin sınıflandırması için derin öğrenme tabanlı tekniklerin kapsamlı bir karşılaştırması sunulmaktadır. Çalışmada 7 farklı Evrişimli Sinir Ağları mimarisi ile görüntülerin özellikleri çıkarılmış, 5 farklı sınıflandırma yöntemi ile sınıflandırılması sağlanmıştır. Performans değerlendirmesi için dengesiz çok sınıflı veri kümelerinin sınıflandırılmasına uygun metrikler olan dengeli doğruluk, makro ve mikro ortalama duyarlılık, makro ve mikro ortalama kesinlik, makro ve mikro ortalama F ölçütü metrik değerleri kullanılmıştır. Ayrıca tüm yapıların ayrı ayrı eğitim ve test süreleri karşılaştırılmıştır. Çalışmada en yüksek doğruluk değeri %95.24 ile Resnet101+Softmax ve Resnet50+DVM mimarilerinde elde edilmiştir. Sınıfların eşit ağırlıklı alındığı dengeli doğruluk değerinde ise en yüksek %95,17 ile Resnet101+Softmax mimarisinden elde edilmiştir. Resnet101+Softmax mimarisinde makro ortalamalı kesinlik 0.9579, makro ortalamalı F ölçütü 0.9543 ve mikro ortalamalı F ölçütü 0.9524 değerleri elde edilmiştir. Bu çalışma, küçük ve dengesiz termal görüntüler üzerinde, önceden eğitilmiş ESA ağlarının özellik çıkarımı ile makine öğrenimi sınıflandırıcılarının kullanımının, tamamen eğitilmiş ağlarla elde edilen performansa benzer sonuçlar sağlanabileceğini göstermiştir

Brain MRI is a medical image obtained by MRI, which stands for "Magnetic Resonance Imaging". Brain MRI uses magnetic fields and radio waves to create detailed images of the brain and surrounding tissues. Today, deep learning algorithms are used to detect brain tumors or classify different brain regions. In this study, feature extraction has been performed with current deep learning models using a dataset consisting of 7023 open access images obtained from patients from various parts of the world, and the results were evaluated by training Support Vector Machine (SVM) and XGBoost models with the extracted features. In this study, 4 deep learning models, VGG16, VGG19, ResNet50 and MobileNetV2, have been used for feature extraction. In order to achieve higher performance, transfer learning method is used in this study, which allows the weights of models that are pre-trained with large data sets to be used in other models. The weights of the models trained with ImageNet were included in the study to improve performance and save time. Although the original layer structures of the models are fixed, the GlobalAveragePooling2D layer has been added to the CNN models to improve performance and generalize the features extracted from deep learning models. Brain MRI images divided into 4 classes as glioma tumor, meningioma tumor, pituitary tumor and no tumor. Auxiliary functions have been used to obtain optimum values for the parameters used for training the models. Accuracy, F1-score, precision and sensitivity metrics used to evaluate the training results. When the results are evaluated, the best performance with an F1-score of 97.87% is obtained by classifying the features extracted from the ResNet50 CNN model with Support Vector Machine (SVM).

ObjectivesBreast cancer is a type of cancer caused by the uncontrolled growth of cells in the breast tissue. In a few cases, erroneous diagnosis of breast cancer by specialists and unnecessary biopsies can lead to various negative consequences. In some cases, radiologic examinations or clinical findings may raise the suspicion of breast cancer, but subsequent detailed evaluations may not confirm cancer. In addition to causing unnecessary anxiety and stress to patients, such diagnosis can also lead to unnecessary biopsy procedures, which are painful, expensive, and prone to misdiagnosis. Therefore, there is a need for the development of more accurate and reliable methods for breast cancer diagnosis.MethodsIn this study, we proposed an artificial intelligence (AI)‐based method for automatically classifying breast solid mass lesions as benign vs malignant. In this study, a new breast cancer dataset (Breast‐XD) was created with 791 solid mass lesions belonging to 752 different patients aged 18 to 85 years, which were examined by experienced radiologists between 2017 and 2022.ResultsSix classifiers, support vector machine (SVM), K‐nearest neighbor (K‐NN), random forest (RF), decision tree (DT), logistic regression (LR), and XGBoost, were trained on the training samples of the Breast‐XD dataset. Then, each classifier made predictions on 159 test data that it had not seen before. The highest classification result was obtained using the explainable XGBoost model (X2GAI) with an accuracy of 94.34%. An explainable structure is also implemented to build the reliability of the developed model.ConclusionsThe results obtained by radiologists and the X2GAI model were compared according to the diagnosis obtained from the biopsy. It was observed that our developed model performed well in cases where experienced radiologists gave false positive results.

A new fusion method based on Multi-Focus Image Fusion Based on Discrete Wavelet Transform with Deep Convolutional Neural Network (MFIF-DWT-CNN) is presented to reduce spatial artifacts and blurring effects in edge details and increase the robustness of multifocal image fusion. The main purpose of the MFIF-DWT-CNN approach is to create a new merged image by collecting the required features from the main image. With the MFIF-DWT-CNN approach, information focused on individual images is combined into a single image, resulting in a clearer image. Within the scope of MFIF-DWT-CNN approach, DWT is applied to the image pairs and the obtained images are then given to the CNN architecture. The MFIF-DWT-CNN approach was developed in this study to reduce spatial artifacts and blurring effects in edge details and to increase the robustness of multifocal image fusion. In order to evaluate our proposed MFIF-DWT-CNN method, QMI, QG, QYi QCB evaluations were made on the public data set. From the experimental results, it is seen that the proposed method gives better results in the relevant metrics than the other methods. This demonstrated the effectiveness of the proposed method.

Early diagnosis of diabetes can increase patients' quality of life and improve treatment processes. In this context, this article focuses on the early diagnosis and prediction of diabetes, addressing the performance of various machine learning models and the role of explainable artificial intelligence (XAI) techniques. With the rise of large datasets in the healthcare industry, data mining and machine learning techniques have become an important tool for the discovery and analysis of diabetes datasets spanning healthcare systems. This study investigates a diabetes dataset that includes healthcare systems. Various machine learning models such as K-NN, SVM, Naive Bayes, CNN, Decision Tree, Random Forest and XGBoost were evaluated on this data set and their performances were compared. Visualizing the overall structure of the data set is important for analyzing relationships between diabetes-related features. The article starts with cleaning the dataset and preprocessing steps, followed by the training and testing phases of each model on the dataset. Each model was evaluated based on success criteria such as accuracy, F1 score, sensitivity, and specificity. In addition, the understandability of the model's decisions was increased by applying explainable artificial intelligence (XAI) methods, SHAP (Shapley Additive exPlanations) and LIME (Local Interpretable Model-agnostic Explanations) to the outputs of the most successful model. These techniques explain the internal working mechanism of the model by determining which features have the most impact on model outputs. The analyzes were supported by expert doctor's comments and the potential of the models in real world applications was highlighted. When the models and results are examined, respectively; it can be seen that the results of K-NN: 81.18%, SVM: 75.38%, Naïve Bayes: 75.49%, CNN: 74.83%, Decision Tree: 76.91%, Random Forest: 91.68%, XGBoost: 98.91% are obtained. As a result, machine learning models effectively demonstrate early detection and diagnosis of diabetes. The explainability of these applied models is emphasized and their effects on real life are shown.

The diagnosis of urinary tract infections and kidney diseases using urine microscopy images has gained significant attention of medical community in recent years. These images are usually created by physicians’ own rule of thumb manually. However, this manual urine sediment analysis is usually labor-intensive and time-consuming. In addition, even when physicians carefully examine an image, an erroneous cell recognition may occur due to some optical illusions. In order to achieve cell recognition in low-resolution urine microscopy images with a higher level of accuracy, a new super resolution Faster Region-based Convolutional Neural Network (Faster R-CNN) method is proposed. It aims to increase resolution in low-resolution urine microscopy images using self-similarity based single image super resolution which was used during the pre-processing. De-noising based Wiener filter and Discrete Wavelet Transform (DWT) are used to de-noise high resolution images, respectively, to increase the level of accuracy for image recognition. Finally, for the feature extraction and classification stages, AlexNet, VGFG16 and VGG19 based Faster R-CNN models are used for the recognition and detection of multi-class cells. The model yielded accuracy rates are 98.6%, 96.4% and 96.2% respectively.

This chapter presents the impact of adult vaccination as a control strategy on a model describing the spreading of COVID-19 between the kids and adults. The main goal is reducing the infected people with minimal vaccination costs. To succeed in this purpose, an optimal control problem is constructed. The Hamiltonian formalism is considered to get the optimality conditions. The fourth-order Runge–Kutta method structured with forward–backward sweep algorithm is implemented to arrive the numerical solutions. The graphical results show that adult vaccination is effective not only in reducing the infected adults but also in reducing the infected children. As a natural consequence of this, while adults return to their social and working lives very quickly thanks to vaccination, children also do not stay away from educational activities by this optimal vaccination strategy.

In this study, a heat transfer problem defined by the Caputo–Fabrizio derivative, which is known to behave by the exponential decaying law, is addressed in an axially symmetric cylindrical region. Thus, the fundamental solutions of the heat diffusion process and the associated thermal stresses are aimed to find. For this purpose, Laplace and finite Hankel integral transforms are applied according to the geometry of the region. To obtain the thermal stresses, constitutive relations of the classical thermoelasticity theory are used. The effects of fractional orders on the diffusion process are illustrated graphically using MATLAB.

Pes planus, colloquially known as flatfoot, is a deformity defined as the collapse, flattening or loss of the medial longitudinal arch of the foot. The first standard radiographic examination for diagnosing pes planus involves lateral and dorsoplantar weight-bearing radiographs. Recently, many artificial intelligence-based computer-aided diagnosis (CAD) systems and models have been developed for the detection of various diseases from radiological images. However, to the best of our knowledge, no model and system has been proposed in the literature for automated pes planus diagnosis using X-ray images. This study presents a novel deep learning-based model for automated pes planus diagnosis using X-ray images, a first in the literature. To perform this study, a new pes planus dataset consisting of weight-bearing X-ray images was collected and labeled by specialist radiologists. In the preprocessing stage, the number of X-ray images was augmented and then divided into 4 and 16 patches, respectively in a pyramidal fashion. Thus, a total of 21 images are obtained for each image, including 20 patches and one original image. These 21 images were then fed to the pre-trained MobileNetV2 and 21,000 features were extracted from the Logits layer. Among the extracted deep features, the most important 1312 features were selected using the proposed iterative ReliefF algorithm, and then classified with support vector machine (SVM). The proposed deep learning-based framework achieved 95.14% accuracy using 10-fold cross validation. The results demonstrate that our transfer learning-based model can be used as an auxiliary tool for diagnosing pes planus in clinical practice.

This study proposes different optimal control strategies to eliminate the damage of virus propagation in a computer network with a minimum cost of installing anti-virus software. The model discussed to be developed is a fractional-order SEIR epidemiological model. Unlike the existing studies on the model, it has been considered that the recovered computers may malfunction due to any mechanical reason, and the model has been developed accordingly. In addition, unit consistency for the model is provided. Although there are a limited number of studies in the literature, the control variable affects the equilibrium points and thus the stability of the controlled system. Therefore, the reproduction number is recalculated for the controlled system. Before the optimal control problem is formulated, the existence of optimal control is proved. Then, the optimal system is obtained using Hamiltonian formalism. The numerical solutions of the optimal system are achieved by the fractional Euler method combined with the forward–backward sweep algorithm. The graphs drawn with MATLAB software show the efficiency of the fractional parameter for different control scenarios. Comparing the three proposed control strategies, it is clear that Strategy 1 is the most effective anti-virus installation strategy. In other words, if an anti-virus software is installed on both infected computers and susceptible computers connected to exposed and infected computers, virus propagation in the network can be prevented quickly as intended. Moreover, this is achieved by minimizing the cost of installing an antivirus program, thanks to the optimal control strategy.

The high resolution of the image is very important for applications. Publicly available satellite images generally have low resolutions. Since low resolution causes loss of information, the desired performance cannot be achieved depending on the type of problem studied in the field of remote sensing. In such a case, super resolution algorithms are used to render low resolution images high resolution. Super resolution algorithms are used to obtain high resolution images from low resolution images. In studies with satellite images, the use of images enhanced with super resolution is important. Since the resolution of satellite images is low, the success rate in the classification process is low. In this study, super resolution method is proposed to increase the classification performance of satellite images. The attributes of satellite images were extracted using AlexNet, ResNet50, Vgg19 from deep learning architecture. Then the extracted features were then classified into 6 classes by giving input to AlexNet-Softmax, ResNet50-Softmax, Vgg19-Softmax, Support Vector Machine, K-Nearest Neighbor, decision trees and Naive Bayes classification algorithms. Without super resolution and with super resolution feature extraction and classification processes were performed separately. Classification results without super resolution and with super resolution were compared. Improvement in classification performance was observed using super resolution.