Browsing by Author "Aslan, Emrah"

Now showing 1 - 10 of 10

Citation - WoS: 2
Citation - Scopus: 2
Air Quality Forecasting Using Machine Learning: Comparative Analysis and Ensemble Strategies for Enhanced Prediction
(Springer Int Publ Ag, 2025) Aslan, Emrah; Alpsalaz, Feyyaz; Aslan, Emrah; 08.01. Department of Computer Engineering / Bilgisayar Mühendisliği Bölümü; 08. Faculty of Engineering and Architecture / Mühendislik Mimarlık Fakültesi; 01. Mardin Artuklu University / Mardin Artuklu Üniversitesi
Air 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.
Citation - WoS: 16
Citation - Scopus: 21
Attention Enhanced Inceptionnext-Based Hybrid Deep Learning Model for Lung Cancer Detection
(IEEE-Inst Electrical Electronics Engineers inc, 2025) Ozdemir, Burhanettin; Aslan, Emrah; Aslan, Emrah; Pacal, Ishak; 08.01. Department of Computer Engineering / Bilgisayar Mühendisliği Bölümü; 08. Faculty of Engineering and Architecture / Mühendislik Mimarlık Fakültesi; 01. Mardin Artuklu University / Mardin Artuklu Üniversitesi
Lung cancer is the most common cause of cancer-related mortality globally. Early diagnosis of this highly fatal and prevalent disease can significantly improve survival rates and prevent its progression. Computed tomography (CT) is the gold standard imaging modality for lung cancer diagnosis, offering critical insights into the assessment of lung nodules. We present a hybrid deep learning model that integrates Convolutional Neural Networks (CNNs) with Vision Transformers (ViTs). By optimizing and integrating grid and block attention mechanisms with InceptionNeXt blocks, the proposed model effectively captures both fine-grained and large-scale features in CT images. This comprehensive approach enables the model not only to differentiate between malignant and benign nodules but also to identify specific cancer subtypes such as adenocarcinoma, large cell carcinoma, and squamous cell carcinoma. The use of InceptionNeXt blocks facilitates multi-scale feature processing, making the model particularly effective for complex and diverse lung nodule patterns. Similarly, including grid attention improves the model's capacity to identify spatial relationships across different sections of the picture, whereas block attention focuses on capturing hierarchical and contextual information, allowing for precise identification and categorization of lung nodules. To ensure robustness and generalizability, the model was trained and validated using two public datasets, Chest CT and IQ-OTH/NCCD, employing transfer learning and pre-processing techniques to improve detection accuracy. The proposed model achieved an impressive accuracy of 99.54% on the IQ-OTH/NCCD dataset and 98.41% on the Chest CT dataset, outperforming state-of-the-art CNN-based and ViT-based methods. With only 18.1 million parameters, the model provides a lightweight yet powerful solution for early lung cancer detection, potentially improving clinical outcomes and increasing patient survival rates.
Boiler Efficiency and Performance Optimization in District Heating and Cooling Systems With Machine Learning Models
(Taylor & Francis Ltd, 2025) Aslan, Emrah; Aslan, Emrah; Oezuepak, Yildirim; Alpsalaz, Feyyaz; 08.01. Department of Computer Engineering / Bilgisayar Mühendisliği Bölümü; 08. Faculty of Engineering and Architecture / Mühendislik Mimarlık Fakültesi; 01. Mardin Artuklu University / Mardin Artuklu Üniversitesi
This study focuses on the detection and analysis of boiler efficiency degradation in District Heating and Cooling (DHC) substations. The research presents an innovative approach to optimize boiler efficiency under different scenarios. Although DHC systems provide both heating and cooling services, this study focuses specifically on heating substations. In this context, various machine learning algorithms have been applied to effectively detect boiler efficiency degradation, and hyper-parameter adjustments have been performed using Bayesian optimization to improve the performance of the models. As a result of the analyses, the Gradient Boosting Regressor model showed significantly higher performance compared to other machine learning algorithms. The model successfully predicted the decline in boiler efficiency with an accuracy of 97.8%, and the Matthews Correlation Coefficient (MCC) value was recorded as 0.952. These results show that Gradient Boosting Regressor based approaches provide an effective solution for fault detection and diagnosis in district heating systems. In conclusion, this study provides both theoretical and practical contributions to the optimization of boiler efficiency, fault detection and diagnosis in DHC systems. The solutions offered by the study have the potential to increase the reliability and efficiency of the systems.
Citation - WoS: 2
Citation - Scopus: 2
Classification of Maize Leaf Diseases With Deep Learning: Performance Evaluation of the Proposed Model and Use of Explicable Artificial Intelligence
(Elsevier, 2025) Alpsalaz, Feyyaz; Aslan, Emrah; Ozupak, Yildirim; Aslan, Emrah; Uzel, Hasan; 08.01. Department of Computer Engineering / Bilgisayar Mühendisliği Bölümü; 08. Faculty of Engineering and Architecture / Mühendislik Mimarlık Fakültesi; 01. Mardin Artuklu University / Mardin Artuklu Üniversitesi
Maize 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.
Citation - WoS: 1
Citation - Scopus: 1
Comparison and Optimization of Machine Learning Methods for Fault Detection in District Heating and Cooling Systems
(Polska Akad Nauk, Polish Acad Sci, Div IV Technical Sciences PAS, 2025) Aslan, Emrah; Cinar, Mehmet; Aslan, Emrah; Ozupak, Yildirim; 08.01. Department of Computer Engineering / Bilgisayar Mühendisliği Bölümü; 08. Faculty of Engineering and Architecture / Mühendislik Mimarlık Fakültesi; 01. Mardin Artuklu University / Mardin Artuklu Üniversitesi
In this study, the methods used for the detection of sub-station pollution failures in district heating and cooling (DHC) systems are analyzed. In the study, high, medium, and low-level pollution situations are considered and machine learning methods are applied for the detection of these failures. Random forest, decision tree, logistic regression, and CatBoost regression algorithms are compared within the scope of the analysis. The models are trained to perform fault detection at different pollution levels. To improve the model performance, hyper parameter optimization was performed with random search optimization, and the most appropriate values were selected. The results show that the CatBoost regression algorithm provides the highest accuracy and overall performance compared to other methods. The CatBoost model stood out with an accuracy of 0.9832 and a superior performance. These findings reveal that CatBoost-based approaches provide an effective solution in situations requiring high accuracy, such as contamination detection in DHC systems. The study makes an important contribution as a reliable fault detection solution in industrial applications.
Comparison of Machine Learning Algorithms for Automatic Prediction of Alzheimer Disease
(Lippincott Williams & Wilkins, 2025) Aslan, Emrah; Aslan, Emrah; Ozupak, Yildirim; 08.01. Department of Computer Engineering / Bilgisayar Mühendisliği Bölümü; 08. Faculty of Engineering and Architecture / Mühendislik Mimarlık Fakültesi; 01. Mardin Artuklu University / Mardin Artuklu Üniversitesi
Background:Alzheimer disease is a progressive neurological disorder marked by irreversible memory loss and cognitive decline. Traditional diagnostic tools, such as intracranial volume assessments, electroencephalography (EEG) signals, and brain magnetic resonance imaging (MRI), have shown utility in detecting the disease. However, artificial intelligence (AI) offers promise for automating this process, potentially enhancing diagnostic accuracy and accessibility.Methods:In this study, various machine learning models were used to detect Alzheimer disease, including K-nearest neighbor regression, support vector machines (SVM), AdaBoost regression, and logistic regression. A neural network was constructed and validated using data from 150 participants in the University of Washington's Alzheimer's Disease Research Center (Open Access Imaging Studies Series [OASIS] dataset). Cross-validation was also performed on the Alzheimer Disease Neuroimaging Initiative (ADNI) dataset to assess the robustness of the models.Results:Among the models tested, K-nearest neighbor regression achieved the highest accuracy, reaching 97.33%. The cross-validation on the ADNI dataset further confirmed the effectiveness of the models, demonstrating satisfactory results in screening and diagnosing Alzheimer disease in a community-based sample.Conclusion:The findings indicate that AI-based models, particularly K-nearest neighbor regression, provide promising accuracy for the early detection of Alzheimer disease. This approach has potential for further development into practical diagnostic tools that could be applied in clinical and community settings.
A Deep Learning Approach for Fault Detection in Photovoltaic Systems Using MobileNetV3
(2025) Özüpak, Yıldırım; Aslan, Emrah; Mansurov, Shuhratjon; Çetin, Ziya
This study investigates the use of the MobileNetV3 deep learning architecture for fault detection in Photovoltaic (PV) systems. The research developed a model capable of classifying solar panels under six different conditions: clean, physically damaged, electrically damaged, snow covered, bird droppings covered, and dusty panels. Using a dataset obtained from Kaggle, pre-processed and divided into training (70%) and test (30%) sets, the MobileNetV3 model achieved a validation accuracy of 95%. Confusion matrix analysis showed high classification accuracy, in particular 100% accuracy for snow-covered and bird droppings-covered panels, with F1 scores as high as 98.73% for certain classes. Training and validation curves confirmed stable learning with low loss values. Compared to models such as EfficientB0 + SVM and InceptionV3-Net + U-Net, MobileNetV3 demonstrated competitive accuracy and computational efficiency, making it suitable for resource-constrained devices. This approach improves energy efficiency, reduces manual inspection, and promotes sustainable energy production. Future work will expand the dataset to include different climatic conditions and fault scenarios, improving the robustness and real-world applicability of the model.
Development of Malaria Diagnosis With Convolutional Neural Network Architectures: a Cnn-Based Software for Accurate Cell Image Analysis
(Galileo Institute of Technology and Education of the Amazon (ITEGAM), 2025) Aslan, E.; Aslan, Emrah; 08.01. Department of Computer Engineering / Bilgisayar Mühendisliği Bölümü; 08. Faculty of Engineering and Architecture / Mühendislik Mimarlık Fakültesi; 01. Mardin Artuklu University / Mardin Artuklu Üniversitesi
This study emphasizes that early diagnosis and treatment of malaria is critical in reducing health problems and mortality from the disease, especially in developing countries where the disease is prevalent. Malaria is a potentially fatal disease transmitted to humans by mosquitoes infected by a blood parasite called Plasmodium. The traditional method of diagnosis relies on experts examining red blood cells under a microscope and is inefficient as it is dependent on expert knowledge and experience. Nowadays, machine learning methods that provide high accuracy are increasingly used in disease detection. In this paper, a Convolutional Neural Network (CNN) architecture is proposed to distinguish between parasitized and non-parasitized cells. In addition, the performance of the proposed CNN architecture is compared to pre-trained CNN models such as VGG-19 and EfficientNetB3. The studies were carried out using the Malaria Dataset supplied by the National Institute of Health (NIH), and our proposed architecture was shown to function with 99.12% accuracy. The results of the study reveal that it is effective in improving the accuracy of cell images containing Plasmodium. In addition, a software that predicts whether cell images are noisy or not has been developed. © 2025 by authors and Galileo Institute of Technology and Education of the Amazon (ITEGAM).
Hybrid Deep Learning Model for Maize Leaf Disease Classification With Explainable AI
(Taylor & Francis Ltd, 2025) Aslan, Emrah; Alpsalaz, Feyyaz; Aslan, Emrah; Uzel, Hasan; 08.01. Department of Computer Engineering / Bilgisayar Mühendisliği Bölümü; 08. Faculty of Engineering and Architecture / Mühendislik Mimarlık Fakültesi; 01. Mardin Artuklu University / Mardin Artuklu Üniversitesi
This study presents a hybrid learning model that integrates MobileNetV2 and Vision Transformer (ViT) with a stacking model to classify maize leaf diseases, addressing the critical need for early detection to improve agricultural productivity and sustainability. Utilising the 'Corn or Maize Leaf Disease Dataset' from Kaggle, comprising 4,062 high-resolution images across five classes (Common Rust, Grey Leaf Spot, Healthy, Northern Leaf Blight, Not Maize Leaf), the model achieves an impressive accuracy of 96.73%. Transfer learning from ImageNet, coupled with data augmentation (rotation, flipping, scaling, brightness adjustment), enhances generalisation, while a 20% dropout rate mitigates overfitting. The key advantage of the hybrid model lies in its ability to combine the strengths of MobileNetV2's localised feature extraction and ViT's global context understanding, enhanced by the stacking model's ability to reduce the weaknesses of either model. Explainable AI techniques, including SHapley Additive exPlanations (SHAP), Local Interpretable Model-agnostic Explanations (LIME), and Grad-CAM, provide transparent insights into model decisions, fostering trust among agricultural stakeholders. Comparative analysis demonstrates the model's superiority over prior works, with F1-scores ranging from 0.9276 to 1.0000. Despite minor misclassifications due to visual similarities, the model offers a robust, interpretable solution for precision agriculture.
A Hybrid Machine Learning Approach for Predicting Power Transformer Failures Using Internet of Things-Based Monitoring and Explainable Artificial Intelligence
(Institute of Electrical and Electronics Engineers Inc., 2025) Aslan, E.; Aslan, Emrah; Özüpak, Y.; Alpsalaz, F.; Elbarbary, Z.M.S.; 08.01. Department of Computer Engineering / Bilgisayar Mühendisliği Bölümü; 08. Faculty of Engineering and Architecture / Mühendislik Mimarlık Fakültesi; 01. Mardin Artuklu University / Mardin Artuklu Üniversitesi
Power transformers are critical components in ensuring the continuous and stable operation of power systems. Failures in these units can lead to significant power outages and costly downtime. Existing maintenance strategies often fail to accurately predict such failures, highlighting the need for novel predictive approaches. This study aims to improve the reliability of power systems by predicting transformer failures through the integration of IoT technologies and advanced machine learning techniques. The proposed hybrid model combines the LightGBM algorithm with GridSearch optimization to achieve both high predictive accuracy and computational efficiency. In addition, the model enhances interpretability by incorporating SHapley Additive exPlanations (SHAP) and Local Interpretable Model-Agnostic Explanations (LIME) for transparent decision making. The study presents a detailed comparison of different classification algorithms and evaluates their performance using metrics such as accuracy, recall, and F1 score. The results show that the hybrid model outperforms other methods, achieving an accuracy of 99.91%. The SHAP and LIME analyses provide engineers and researchers with valuable insights by highlighting the most influential features in failure prediction. In addition, the model's ability to efficiently handle large data sets enhances its practicality in real-world power systems. By proposing an innovative approach to failure prediction, this research contributes to both the theoretical foundation and practical advancement of sustainable and reliable energy infrastructures. © 2013 IEEE.