Gülcan Yıldız

Traffic accidents are largely caused by human errors and often result in severe injuries or loss of life. To mitigate these risks, intelligent transportation systems have gained increasing attention in recent years. Lane detection is a fundamental component of such systems, as it supports safe driving by ensuring that vehicles remain within their designated lanes and by reducing accidents caused by lane violations. In this study, an effective lane detection model that integrates traditional image processing techniques with Support Vector Regression (SVR) is proposed. In the developed model, perspective transformation is first performed on the road images obtained from in-car cameras, then visual separation is provided with color space transformation, and various morphological operations are applied to highlight the lane lines. After the lane lines are detected, the curved structure of the lanes is modeled with the SVR-based curve fitting algorithm, and thus a consistent lane structure suitable for the road geometry is created. In addition, the area between the detected lanes is colored to make the driving line more understandable. The proposed method is evaluated on two different datasets: an original dataset created by us under various road conditions in Türkiye and the publicly available Karlsruhe Institute of Technology and Toyota Technological Institute (KITTI) dataset, which is widely used in autonomous driving research. For the Türkiye dataset, lane regions are manually labeled, and the system performance is quantitatively assessed using accuracy, precision, recall, specificity, F1-score, and Intersection-over-Union (IoU) metrics. In addition, the SVR-based curve fitting approach is compared with the classical Hough Transform under identical preprocessing conditions. The comparative results demonstrate that the proposed method achieves higher accuracy and reliability across multiple evaluation metrics. Overall, the experimental findings indicate that the proposed approach provides a robust and practical solution for lane detection and tracking in intelligent driving systems.

Classification is a fundamental technique in data mining that predicts categorical labels by analyzing input features. However, training Artificial Neural Networks (ANNs) using traditional methods often encounters challenges, such as getting stuck in local minima and slow convergence. To address these issues, this study proposes a novel hybrid model, IPA-ANN, which integrates the Immune Plasma Algorithm (IPA) to optimize the ANN’s connection weights and biases. The IPA, inspired by the immune plasma treatment process, utilizes a unique donor-receiver mechanism to balance exploration and exploitation in the search space. The proposed model was evaluated on nine benchmark datasets from the UCI repository and compared with 18 state-of-the-art metaheuristic algorithms, including Grey Wolf Optimization (GWO), Differential Evolution (DE), and Particle Swarm Optimization (PSO). Experimental results were analyzed using accuracy, F1-score, confusion matrices, and convergence graphs. The findings indicate that IPA-ANN achieves competitive and stable classification performance across different datasets while demonstrating favorable convergence characteristics in several cases. Furthermore, the study investigates the influence of donor–receiver parameters on the optimization process, highlighting the adaptability of the proposed framework. The reliability of these findings was further examined through repeated stratified 5-fold cross-validation and paired Wilcoxon signed-rank tests with Holm–Bonferroni correction on representative datasets, confirming that a subset of the observed performance differences are statistically significant, and through a computational cost analysis showing that IPA-ANN incurs no additional overhead relative to the majority of the compared algorithms. This study contributes to the literature by presenting the first documented application of IPA in ANN training and by providing a modular infrastructure for future metaheuristic-based ANN optimization studies.

Sürücü davranışlarının trafik güvenliğine önemli derecede etkisi vardır. Bu nedenle, sürücülerin davranışsal örüntüleri ve bu örüntüleri etkileyen etmenler tanımlanmalıdır. Sürücüler, araçlarını daha verimli ve kurallara uygun kullanmaya yönlendirilmelidir. Bu bağlamda, sürücünün aracını nasıl kullandığı gözlemlenerek, sürücülerin sürüş risk derecelerine uygun olarak sigorta ya da kasko ücretleri belirlenebilir. Bu çalışmada, Araç İçi Teşhis (On Board Diagnostics-II, OBD-II) ve Küresel Konumlandırma Sistemi (Global Positioning System, GPS) cihazlarından alınan işlenmiş ve etiketlenmiş telemetri verileri ile Makine Öğrenmesi (Machine Learning, ML) algoritmaları kullanılarak sürücülerin risk gruplarının sınıflandırılması gerçekleştirilmiştir. OBD-II ile araçtan elde edilen verilerin işlenerek sürücülerin risk derecesinin belirlenip bu risk derecesine göre sigorta şirketlerinin kişiye özel sigorta ücreti belirlemesinde yardımcı rol oynanması planlanmaktadır. Çalışmada Destek Vektör Makinesi (Support Vector Machine, SVM, CatBoost, k-NN (k-nearest neighbors, K-En yakın komşuluk) ve Hafif Gradyan Artırma Makinesi (Light Gradient Boosting Machine, LGBM)) olmak üzere dört model kullanılmıştır. Test sonuçları incelendiğinde en iyi tanımaya SVM modeli ile erişilmiştir.

Traffic sign recognition techniques aim to reduce the probability of traffic accidents by increasing road and vehicle safety. These systems play an essential role in the development of autonomous vehicles. Autonomous driving is a popular field that is seeing more and more growth. In this study, a new high-performance and robust deep convolutional neural network model is proposed for traffic sign recognition. The stacking ensemble model is presented by combining the trained models by applying improvement methods on the input images. For this, first of all, by performing preprocessing on the data set, more accurate recognition was achieved by preventing adverse weather conditions and shooting errors. In addition, data augmentation was applied to increase the images in the data set due to the uneven distribution of the number of images belonging to the classes. During the model training, the learning rate was adjusted to prevent overfitting. Then, a new stacking ensemble model was created by combining the models trained with the input images that were subjected to different preprocessing. This ensemble model obtained 99.75% test accuracy on the German Traffic Sign Recognition Benchmark (GTSRB) dataset. When compared with other studies in this field in the literature, it is seen that recognition is performed with higher accuracy than these studies. Additively different approaches have been applied for model evaluation. Grad-CAM (gradient weighted class activation mapping) was used to make the model explainable. Evidential deep learning approach was applied to measure the uncertainty in classification. Results for safe monitoring are also shared with SafeML-II, which is based on measuring statistical distances. In addition to these, the migration test is applied with BTSC (Belgium Traffic Sign Classification) dataset to test the robustness of the model. With the transfer learning method of the models trained with GTSRB, the parameter weights in the feature extraction stage are preserved, and the training is carried out for the classification stage. Accordingly, with the stacking ensemble model obtained by combining the models trained with transfer learning, a high accuracy of 99.33% is achieved on the BTSC dataset. While the number of parameters the single model is 7.15 M, the number of parameters of the stacking ensemble model with additional layers is 14.34 M. However, the parameters of the models trained on a single preprocessed dataset were not trained, and transfer learning was performed. Thus, the number of trainable parameters in the ensemble model is only 39,643.

Machine learning techniques, especially deep learning, have made great achievements in computer vision including image denoising recently. However, in most convolutional neural network (CNN) based methods presented for image denoising, convolutional kernels are considered for only one scale and more scales are neglected mostly. Studies on multilevel feature extraction treat these features as if they have the same importance and do not use a mechanism such as feature attention for their weighting. Also, for effective noise removal, edge information is used as prior knowledge, but texture information is generally disregarded. This study has focused on these shortcomings and introduced a new attention-based CNN for image denoising. The main contributions of this study are as follows: First, we propose a CNN-based network to extract Local Binary Pattern (LBP) from the noisy image for texture information. So, we use texture information as prior knowledge for the preservation of details in the evolved image during the denoising process. Besides we propose a new multilevel feature extraction block to get different level features. After extracting multilevel features using feature attention, we weight these different levels of features. In addition to this, we introduce a multilevel feature attention network (MLFAN) for noise removal by combining them. The comprehensive experimental results show that our MLFAN noise reduction network can effectively remove Gaussian noise from images and compared with some state-of-the-art denoising methods, it outperforms in terms of both quantitative and qualitative evaluations. For Set12 grey image set, and McMaster color image set, MLFAN gives PSNR={33.08, 30.75, 27.56}, SSIM={0.9087, 0.8702, 0.7939} and PSNR={35.08, 32.68, 29.47}, SSIM={0.9288, 0.8956, 0.8263} respectively for noise level σ = {15, 25, 50}.

Artan nüfus yoğunluğunun ve küresel ısınmadan kaynaklanan iklim değişikliklerinin tarımsal üretimin miktarı ve kalitesi üzerinde önemli etkileri bulunmaktadır. Bu nedenle dünya, gıda kıtlığı gibi ciddi problemlerle karşı karşıyadır. Dolayısıyla tarım, ülkelerin ekonomik ve sosyal kalkınma programlarında bulunan hayati bir faaliyettir. Sert kabuklu meyveler kategorisinde dünyada bademden sonra üretimi en fazla yapılan ürün fındıktır. Üretimi Türkiye, İtalya, İspanya, ABD gibi ülkelerde yoğunlaşmış olan fındığın dünyadaki talebinin yaklaşık %70'ini Türkiye karşılamaktadır. Bu nedenle, fındık üretiminde verime etki eden parametrelerin tespit edilmesi ve bu parametrelere bağlı olarak verimin tahmin edilmesi çok büyük önem arz etmektedir. Bu çalışmada, Sakarya, Düzce, Samsun, Giresun, Trabzon illerindeki ve bu illerin fındık üretimi yapılan ilçelerindeki, fındık üretimine etki eden parametreler incelenerek bir sonraki adımda elde edilecek verim tahmini yapılmıştır. Tahmin işlemi için gereken özniteliklerin eldesi için ham veri setine bazı ön işleme adımları uygulanmış, temel bileşenler analizi (Principal Component Analysis, PCA) ile öznitelik sayısı azaltılmıştır. Ön işlemeden geçen bu veriler girdi olarak, XGBoost algoritması, Yalın Uzun-Kısa Süreli Bellek (Long Short-Term Memory, LSTM) modeli, Yığılmış LSTM modeli, Konvolüsyonel Sinir Ağı (Convolutional Neural Network, CNN) modeli ve CNN-LSTM hibrit modeline verilerek tahmin işlemi gerçekleştirilmiştir. Son olarak bu yöntemlerin her biri için Ortalama Hataların Karekökü (Root Mean Square Error, RMSE) ile tahmin hatası elde edilmiş ve yöntem kıyaslamaları için kullanılmıştır. Bu sonuçlara göre, en düşük RMSE=1,32 değeriyle en iyi performans CNN-LSTM hibrit modeli ile elde edilmiştir.

Traffic sign recognition has been one of the indispensable issues of Advanced Driver Assistance Systems. In this study, a new CNN model for traffic sign recognition based on deep learning is proposed. The proposed model has low number of parameter and high accuracy compared to most studies in the literature. Initially, in preprocessing stage, different color spaces are tried for the input image, and their combinations are given to the network together. Color spaces used in the study are RGB, CIELab, RIQ and LGI. In addition, the accuracy results were compared by experimenting on the input image dimensions. Additionally, data augmentation was applied during the training phase. As a result, 98.84% accuracy was obtained by giving the input image with RIQ and LGI color space to the network. The number of parameters is 0.95 M.