MAU GCRIS Standard Database (Mardin Artuklu University)
Not a member yet
7418 research outputs found
Sort by
Air Quality Forecasting Using Machine Learning: Comparative Analysis and Ensemble Strategies for Enhanced Prediction
No full textAir pollution poses a critical challenge to environmental sustainability, public health, and urban planning. Accurate air quality prediction is essential for devising effective management strategies and early warning systems. This study utilized a dataset comprising hourly measurements of pollutants such as PM2.5, NOx, CO, and benzene, sourced from five metal oxide sensors and a certified analyzer in a polluted urban area, totaling 9,357 records collected over one year (March 2004-February 2005) from the Kaggle Air Quality Data Set. A comprehensive comparison of ten machine learning regression models XGBoost, LightGBM, Random Forest, Gradient Boosting, CatBoost, Support Vector Regression (SVR) with Bayesian Optimization, Decision Tree, K-Nearest Neighbors (KNN), Elastic Net, and Bayesian Ridge was conducted. Model performance was enhanced through Bayesian optimization and randomized cross-validation, with stacking employed to leverage the strengths of base models. Experimental results showed that hyperparameter optimization and ensemble strategies significantly improved accuracy, with the SVR model optimized via Bayesian optimization achieving the highest performance: an R2 score of 99.94%, MAE of 0.0120, and MSE of 0.0005. These findings underscore the methodology's efficacy in precisely capturing the spatial and temporal dynamics of air pollution.Scientific and Technological Research Council of Turkiye (TUBITAK)Open access funding provided by the Scientific and Technological Research Council of Turkiye (TUBITAK)
Association Between the Triglyceride-Glucose Index and Contrast-Induced Nephropathy in Chronic Total Occlusion Patients Undergoing Percutaneous Coronary Intervention
No full textSoner, Serdar/0000-0002-2807-6424; KILIC, RAIF/0000-0002-8338-4948; GUZEL, TUNCAY/0000-0001-8470-1928Objective The triglyceride glucose (TyG) index is a biomarker of insulin resistance and is associated with an increased risk of cardiovascular events. Contrast-induced nephropathy (CIN) is an important complication that causes poor outcomes in patients undergoing percutaneous coronary intervention (PCI). In this study, we aimed to investigate the relationship between the TyG index and CIN and mortality in patients who underwent PCI due to chronic total coronary occlusion (CTO). Methods Two hundred eighteen individuals from three separate medical centers who underwent procedural PCI between February 2010 and April 2012 and had a CTO lesion in at least one coronary artery were recruited. According to the TyG index, patients were divided into two groups. Patients with a TyG index >= 8.65 were included in Group 1, and patients with a TyG index < 8.65 were included in Group 2. Patients were followed up for 96 months. The main outcome was the development of CIN and mortality. Results The mean age of the patients (65.8 +/- 10.94 vs. 61.68 +/- 11.4, P = 0.009), diabetes mellitus (60 [44.8%] vs. 11 [13.1%], P < 0.001), and dyslipidemia rates (52 [38.8%] vs. 21 [25%], P = 0.036) were higher in group 1. In multivariable logistic regression analysis, it was seen that age (OR = 1.04, 95% CI = 1.01-1.08, P = 0.020), chronic kidney disease (OR = 2.34, 95% CI = 1.02-5.33, P = 0.044), peripheral artery disease (OR = 5.66, 95% CI = 1.24-25.91, p = 0.026), LVEF (OR = 0.95, 95% CI = 0.92-0.99, P = 0.005), LDL cholesterol levels (OR = 1.00, 95%CI = 1.00-1.02, P = 0.024) and TyG index (OR = 2.17, 95% CI = 1.21-3.89, P = 0.009) were independent predictors of the development of CIN. Conclusion Our study demonstrates a correlation between the TyG index and the prevalence of CIN in patients with CTO undergoing PCI. Adding the TyG index to the routine clinical evaluation of patients with CTO undergoing PCI may help protect patients from the development of CIN
Classification of Maize Leaf Diseases With Deep Learning: Performance Evaluation of the Proposed Model and Use of Explicable Artificial Intelligence
No full textMaize leaf diseases pose significant threats to global agricultural productivity, yet traditional diagnostic methods are slow, subjective, and resource-intensive. This study proposes a lightweight and interpretable convolutional neural network (CNN) model for accurate and efficient classification of maize leaf diseases. Using the 'Corn or Maize Leaf Disease Dataset', the model classifies four disease categories Healthy, Gray Leaf Spot, Common Rust, and Northern Leaf Blight with 94.97 % accuracy and a micro-average AUC of 0.99. With only 1.22 million parameters, the model supports real-time inference on mobile devices, making it ideal for field applications. Data augmentation and transfer learning techniques were applied to ensure robust generalization. To enhance transparency and user trust, Explainable Artificial Intelligence (XAI) methods, including LIME and SHAP, were employed to identify disease-relevant features such as lesions and pustules, with SHAP achieving an IoU of 0.82. The proposed model outperformed benchmark models like ResNet50, MobileNetV2, and EfficientNetB0 in both accuracy and computational efficiency. Robustness tests under simulated environmental challenges confirmed its adaptability, with only a 2.82 % performance drop under extreme conditions. Comparative analyses validated its statistical significance and practical superiority. This model represents a reliable, fast, and explainable solution for precision agriculture, especially in resource-constrained environments. Future enhancements will include multi-angle imaging, multimodal inputs, and extended datasets to improve adaptability and scalability in realworld conditions
Community Displacement Challenges in Educational Tourism
No full textThis study investigates issues relating to community displacement of the indigenous residents of Famagusta resulting in an increased rate of relocation to the suburbs due to the sudden growth of educational tourism; thus, the main objective of the current study is to obtain perspectives of learners on primary motives. An in-depth interview of 28 Cypriots in Famagusta, through purposive sampling was used to gather data for the current research. Findings reveal that the increase in educational tourism in Famagusta caused the indigenous Cypriots to move into suburban neighbourhoods. Factors including urbanization issues, social issues, economic issues, cultural issues, and environmental issues were revealed to be the most challenging issues resulting in community displacement
The Naples Prognostic Score in TAVI Patients: a Promising Tool Requiring Further Validation. Authors' Reply
No full textDeterminants of Adherence To the Mediterranean Diet and Depressive Symptoms in Turkish Young Adults
No full textPurpose: This research aimed to investigate the effects of adherence to the Mediterranean diet (MD) on depression risk in young adults and to understand potential associations. Material and Methods: An online survey form was sent to university students in Türkiye, and 479 participated in this cross-sectional study. Data was collected based on students' declarations. Adherence to the MD was decided using the Mediterranean Diet Adherence Screener (MEDAS). Beck Depression Inventory (BDI) was applied to measure the presence of manifestations of depression. Multivariate linear regression models were used for the determinants of MEDAS and BDI scores. Results: 73 males and 406 females with a mean age of 21.6±2.3 years and a mean Body Mass Index (BMI) of 22.0±3.5 kg/m2 participated in the study. While 61.8% had a moderate adherence to the MD, 54.9% had a mild or moderate BDI level. According to models, regular exercise, presence of NCD(s), and adherence to an adequate/balanced diet were MEDAS score's determinants, and adherence to an adequate/balanced diet and BMI were for BDI score (p0.05). Conclusion: The relationship between the MD and depression is complex and encompasses several dimensions. More comprehensive and long-term studies, considering the influence of individual differences and other factors such as genetics, environment, and lifestyle, may help to reveal this effect more clearly
Robot Chefs: the Impacts, Compatibility and Suitability
No full textPurpose - This research investigates the impacts, compatibility and suitability of robot chefs in a restaurant context from the perspective of human chefs. Design/methodology/approach - Based on a qualitative research approach, semi-structured interviews were conducted with 27 chefs working in restaurants in Turkiye. Findings - The study revealed the positive and negative impacts of robot chefs in restaurants, spanning aspects such as competitiveness, labour/human resources, financial, service quality, creativity and innovativeness and sustainability. The findings also shed light on the lack of necessary humanoid chef competencies of robot chefs and the suitability of restaurant concepts for their use. Originality/value - Although previous research has explored the integration of automation and robotics in hospitality experiences and the perceptions of guests towards robot chefs, a significant gap exists in understanding the viewpoints of human chefs. This study makes a novel contribution to the theoretical and practical understanding of the use of robot chefs in the kitchen and the dynamics of their interaction with human chefs
Improvement of a Subpixel Convolutional Neural Network for a Super-Resolution Image
No full textSuper-resolution technologies are one of the tools used in image restoration, which aims to obtain high-resolution content from low-resolution images. Super-resolution technology aims to increase the quality of a low-resolution image by reconstructing it. It is a useful technology, especially in content where low-resolution images need to be enhanced. Super-resolution applications are used in areas such as face recognition, medical imaging, and satellite imaging. Deep neural network models used for single-image super-resolution are quite successful in terms of computational performance. In these models, low-resolution images are converted to high resolution using methods such as bicubic interpolation. Since the super-resolution process is performed in the high-resolution area, it adds a memory cost and computational complexity. In our proposed model, a low-resolution image is given as input to a convolutional neural network to reduce computational complexity. In this model, a subpixel convolution layer is presented that learns a series of filters to enhance low-resolution feature maps to high-resolution images. In our proposed model, convolution layers are added to the efficient subpixel convolutional neural network (ESPCN) model, and in order to prevent the lost gradient value, we transfer the feature information of the current layer from the previous layer to the next upper layer. The efficient subpixel convolutional neural network (R-ESPCN) model proposed in this paper is remodeled to reduce the time required for the real-time subpixel convolutional neural network to perform super-resolution operations on images. The results show that our method is significantly improved in accuracy and demonstrates the applicability of deep learning methods in the field of image data processing
Examination of the Effects of Kefir on Healing Factors in a Mice Burn Model Infected With E. Coli, S. Aureus and P. Aeruginosa Using Qrt-Pcr (Vol 49, Pg 425, 2023)
No full textCetik Yildiz, Songul/0000-0002-7855-5343; Demir, Cemil/0000-0002-6365-0196Mardin Artuklu University-Coordination Unit of Scientific Research Project, Turkey [MAU-BAP-17-SHMYO-23]This study was supported by Mardin Artuklu University-Coordination Unit of Scientific Research Project, Turkey (MAU-BAP-17-SHMYO-23) . Furthermore, this study was approved by the Rectorate of Eskisehir Osmangazi University Local Ethics Committee of Animal Ex-periments with the number 618-2/30.11.2017
Enhancing Schizophrenia Diagnosis Through Multi-View Eeg Analysis: Integrating Raw Signals and Spectrograms in a Deep Learning Framework
No full textObjective: Schizophrenia is a chronic mental disorder marked by symptoms such as hallucinations, delusions, and cognitive impairments, which profoundly affect individuals' lives. Early detection is crucial for improving treatment outcomes, but the diagnostic process remains complex due to the disorder's multifaceted nature. In recent years, EEG data have been increasingly investigated to detect neural patterns linked to schizophrenia. Methods: This study presents a deep learning framework that integrates both raw multi-channel EEG signals and their spectrograms. Our two-branch model processes these complementary data views to capture both temporal dynamics and frequency-specific features while employing depth-wise convolution to efficiently combine spatial dependencies across EEG channels. Results: The model was evaluated on two datasets, consisting of 84 and 28 subjects, achieving classification accuracies of 0.985 and 0.994, respectively. These results highlight the effectiveness of combining raw EEG signals with their time-frequency representations for precise and automated schizophrenia detection. Additionally, an ablation study assessed the contributions of different architectural components. Conclusions: The approach outperformed existing methods in the literature, underscoring the value of utilizing multi-view EEG data in schizophrenia detection. These promising results suggest that our framework could contribute to more effective diagnostic tools in clinical practice.National Center for High Performance Computing of Turkey (UHeM) [1019002024]Computing resources used in this work were provided by the National Center for High Performance Computing of Turkey (UHeM) under grant number 1019002024