In pantographs, current collector strips transmit the electrical energy they receive from the catenary to the locomotive and provide the necessary power for the locomotive’s movement. In order for the current collector strips to transmit electricity to the locomotive in a healthy way, their surface must be smooth. Wear on the surface of the current collector strips reduces conductivity and can create arcs, endangering the health and safety of the pantograph and catenary system. In this paper, a Convolutional Neural Network (CNN) architecture is developed to detect wear on the current collector strips. Images obtained from pantographs used on railways were created with a clean and improved data set using Hough Transform and Power Law Transform. The created dataset contains 909 pantograph images. This dataset was trained and tested with both the developed CNN architecture and classic deep learning architectures (ResNet50, VGG16). The experimental results show that the developed CNN architecture’s training results and test results are more successful than classical architectures.

Faults in railway and pantograph and catenary systems significantly endanger transport safety. Since periodic maintenance or maintenance at the time of fault will be costly, predictive maintenance methods are recommended to prevent faults in these systems. Performing predictive maintenance requires obtaining data from the railway and recording and using this data appropriately. The platform used in this study, allows data to be recorded from every device that can be connected to the internet. This recorded data are easily accessible. For this reason, this study proposes a new predictive maintenance method using the fuzzy classifier in railway systems. A simulation is performed using an internet of things platform. The data are recorded instantly on the proposed platform. Two modules, a camera and a temperature sensor, to be placed on either side of a rail line are simulated. Correlation is applied to the pantograph images obtained with the camera, and vector features are obtained from the images. In this way, a correlation coefficient for each image is calculated and gives information about the health of the pantograph. Data consisting of correlation coefficients and temperature values from modules is transmitted as input to a fuzzy classifier. The fuzzy classifier provides results about the health status of the pantograph. The results are evaluated by the ROC analysis method. When the results of the simulation are examined, it is shown that the proposed method produces effective and accurate results.

Background/Objectives: Early detection and diagnosis are important when treating gallbladder (GB) diseases. Poorer clinical outcomes and increased patient symptoms may result from any error or delay in diagnosis. Many signs and symptoms, especially those related to GB diseases with similar symptoms, may be unclear. Therefore, highly qualified medical professionals should interpret and understand ultrasound images. Considering that diagnosis via ultrasound imaging can be time- and labor-consuming, it may be challenging to finance and benefit from this service in remote locations. Methods: Today, artificial intelligence (AI) techniques ranging from machine learning (ML) to deep learning (DL), especially in large datasets, can help analysts using Content-Based Image Retrieval (CBIR) systems with the early diagnosis, treatment, and recognition of diseases, and then provide effective methods for a medical diagnosis. Results: The developed model is compared with two different textural and six different Convolutional Neural Network (CNN) models accepted in the literature—the developed model combines features obtained from three different pre-trained architectures for feature extraction. The cosine method was preferred as the similarity measurement metric. Conclusions: Our proposed CBIR model achieved successful results from six other different models. The AP value obtained in the proposed model is 0.94. This value shows that our CBIR-based model can be used to detect GB diseases.

The use of railways has continually increased with high-speed trains. The increased speed and usage wear on the rails poses a serious problem. In recent years, to detect wear and cracks in the rails, image-based detection methods have been developed. In this paper, wears on the surface of railheads are detected by contactless image processing and image analysis techniques. The shadow removal algorithm with a minimal entropy method is implemented onto the noise-free images to eliminate the light variations that can occur on the rail. The Hough transform is applied on the noise and shadow free image in order to determine the rail edge and the KNN nearest neighbour algorithm is applied the image to detect the surface of the railhead at the same time. Both of these methods result in new images that are combined. Therefore, minimum errors are seen in detection of rail wear using this method.

İzolatörler elektrikli demiryolu hatlarında katener sistemlerin en önemli bileşenleridir. İzolatörlerde meydana gelen kırıklar veya yanmalar ulaşımda kesintilere neden olmaktadır. Bu kesintiler de özellikle yüksek hızlı ray hatlarında güvenli çalışmayı engeller. İzolatörlerdeki arızaların erken bir aşamada tespit edilmesi katener sistemlerine en uygun zamanda müdahale etmeyi ve izolatör kaynaklı kazaları engellemeyi sağlayacaktır. Bu makalede katener sistemlerindeki izolatörleri arızalı ya da sağlam olarak sınıflandırmak için derin öğrenme tabanlı bir yöntem önerilmektedir. Çalışmada 1100 adet izolatör görüntüsü içeren bir veri seti kullanılmıştır. Bu veri setindeki görüntüler ResNet34 derin öğrenme mimarisi ile eğitilmiş ve test edilmiştir. Önerilen mimari ile izolatörlerdeki arızalar %95,7 doğruluk, %99 kesinlik ve %96,6 duyarlılık değerleriyle sınıflandırılmıştır. Bu değerler gerçekleştirilen çalışmanın katener sistemlerindeki izolatörlerdeki arıza tespiti için güvenilir bir yöntem olduğunu göstermektedir.

Objective: This study aims to construct a high-precision decision support model by integrating explainable artificial intelligence (XAI) techniques utilizing urinary and plasma biomarkers. Methods: We used an open-access dataset published by Debernardi et al. (2020) containing the biomarkers Lymphatic Vessel Endothelial Hyaluronan Receptor 1 (LYVE1), Regenerating Family Member 1 Beta (REG1B), Trefoil Factor 1 (TFF1), and plasma CA19-9. The preprocessing phase involved missing value imputation, Z-score normalization, and feature engineering. An autoencoder (AE)-based unsupervised learning framework was employed for dimensionality reduction. Classification was performed using an XGBoost algorithm optimized via the Optuna framework. Class imbalance was addressed through the Synthetic Minority Over-sampling Technique (SMOTE). Model interpretability was ensured using SHapley Additive Explanations (SHAP). Results: The proposed Autoencoder–XGBoost model optimized with Optuna outperformed conventional methods, achieving an accuracy of 95.8%, 95% precision, 93% recall, 93% F1-score, and an AUC of 0.984. SHAP analysis identified plasma CA19-9, LYVE1, creatinine, and age as the most influential predictors contributing to model decisions. Conclusion: The developed XAI framework offers high diagnostic accuracy and transparent decision logic for the early detection of PDAC. By leveraging the clinical potential of urinary biomarkers, the model demonstrates strong applicability for integration into screening and risk stratification modules of clinical decision support systems.