Scopus İndeksli Yayınlar Koleksiyonu
Permanent URI for this collectionhttps://hdl.handle.net/20.500.12416/8651
Browse
27 results
Search Results
Article Enhanced Mapping of Rainfall Induced Landslide Susceptibility Using a Deep Feedforward Neural Network with Soft Computing(Techno-Press, 2026) Zhu, Licai; Akagic, Amila; Nanehkaran, Yaser A.; Pusatli, Tolga; Mahmud, Elkhan; Jian, DongThe presented study attempted to propose enhanced rainfall-induced landslide susceptibility mapping method by using the Deep Feedforward Neural Network (DFNN) which is developed for analysis the non-liner feature detection in landslide susceptibility analysis. To evaluate our approach, a comprehensive dataset of triggering factors was compiled, encompassing historical landslide occurrences with total of 107 records, rainfall data, geological information, seismicity, human-activities, and topographic attributes. Through rigorous training and testing procedures, the DFNN demonstratedsuperior ability for generalization and superior performance. The effectiveness of the selected method is demonstrated on the data from the Zanjan County, known for its diverse geographical, geological, and hydrological characteristics, which are pivotal factors in mapping of landslide susceptibility. Results showcased a substantial enhancement in the accuracy of mapping of rainfall-induced landslide susceptibility for the Zanjan County, which is compared with benchmark learning classifiers. According to the results of the study, it appeared that the northeastern and southwestern area of the Zanjan County can be deemed to have a high to very-high risk of landslide occurrence, which is validated via benchmark classifiers. The western part of the Zanjan County was observed to have a very low to low risk.Article Citation - Scopus: 3A New Parallel Multi-Objective Harris Hawk Algorithm for Predicting the Mortality of COVID-19 Patients(PeerJ Inc., 2023) Dokeroglu, TanselHarris' Hawk Optimization (HHO) is a novel metaheuristic inspired by the collective hunting behaviors of hawks. This technique employs the flight patterns of hawks to produce (near)-optimal solutions, enhanced with feature selection, for challenging classification problems. In this study, we propose a new parallel multi-objective HHO algorithm for predicting the mortality risk of COVID-19 patients based on their symptoms. There are two objectives in this optimization problem: to reduce the number of features while increasing the accuracy of the predictions. We conduct comprehensive experiments on a recent real-world COVID-19 dataset from Kaggle. An augmented version of the COVID-19 dataset is also generated and experimentally shown to improve the quality of the solutions. Significant improvements are observed compared to existing state-of-the-art metaheuristic wrapper algorithms. We report better classification results with feature selection than when using the entire set of features. During experiments, a 98.15% prediction accuracy with a 45% reduction is achieved in the number of features. We successfully obtained new best solutions for this COVID-19 dataset.Article Comprehensive Analysis of Data Augmentation Methods in Classification for an Imbalanced Epilepsy Dataset(Institute of Electrical and Electronics Engineers Inc., 2026) Calis, A.G.; Ergezer, H.Imbalanced class distribution reduces the generalizability of classifiers in EEG-based epilepsy detection. This study examines the impact of the synthetic minority oversampling technique (SMOTE) and its variants on imbalanced electroencephalography (EEG) data, utilizing an end-to-end data processing pipeline. Band-limited filtering is applied as pre-processing, and then the training data is gradually oversampled by 20% increments in four scenes. Experiments are conducted on coarse-k-nearest neighbor (Coarse-KNN), bagged trees, and artificial neural network (ANN) classifiers, and evaluation is performed using accuracy, precision, recall, F1 score, and Matthew’s correlation coefficient (MCC) metrics. In Scene #4, where the inter-class imbalance is eliminated, Borderline-SMOTE yielded the highest and most consistent results (F1 Score = 0.903–0.937, MCC = 0.830–0.894). Safe level-SMOTE (SL-SMOTE) and SMOTE/Geometric-SMOTE(G-SMOTE) produced second-ranked results. The findings demonstrate that appropriate variant selection provides consistent gains even across classifiers, making Borderline-SMOTE the recommended approach for imbalanced EEG classification. Furthermore, in the detailed analysis of ensemble sampling limits, SMOTE-based combined approaches (e.g., SL + G SMOTE) also produced consistent results. Basic descriptive statistics (mode, median, variance, and kurtosis) of the synthetic samples were found to be comparable to those of the real data, providing additional evidence of distributional consistency. © 2013 IEEE.Article Stylometric Analysis of Sustainable Central Bank Communications: Revealing Authorial Signatures in Monetary Policy Statements(MDPI, 2025) Emekci, Hakan; Ozkan, IbrahimSustainable economic development requires transparent and consistent institutional communication from monetary authorities to maintain long-term financial stability and public trust. This study investigates the latent authorial structure and stylistic heterogeneity of central bank communications by applying stylometric analysis and unsupervised machine learning to official announcements of the Central Bank of the Republic of Turkey (CBRT). Using a dataset of 557 press releases from 2006 to 2017, we extract a range of linguistic features at both sentence and document levels-including sentence length, punctuation density, word length, and type-token ratios. These features are reduced using Principal Component Analysis (PCA) and clustered via Hierarchical Clustering on Principal Components (HCPC), revealing three distinct authorial groups within the CBRT's communications. The robustness of these clusters is validated using multidimensional scaling (MDS) on character-level and word-level n-gram distances. The analysis finds consistent stylistic differences between clusters, with implications for authorship attribution, tone variation, and communication strategy. Notably, sentiment analysis indicates that one authorial cluster tends to exhibit more negative tonal features, suggesting potential bias or divergence in internal communication style. These findings challenge the conventional assumption of institutional homogeneity and highlight the presence of distinct communicative voices within the central bank. Furthermore, the results suggest that stylistic variation-though often subtle-may convey unintended policy signals to markets, especially in contexts where linguistic shifts are closely scrutinized. This research contributes to the emerging intersection of natural language processing, monetary economics, and institutional transparency. It demonstrates the efficacy of stylometric techniques in revealing the hidden structure of policy discourse and suggests that linguistic analytics can offer valuable insights into the internal dynamics, credibility, and effectiveness of monetary authorities. These findings contribute to sustainable financial governance by demonstrating how AI-driven analysis can enhance institutional transparency, promote consistent policy communication, and support long-term economic stability-key pillars of sustainable development.Conference Object Citation - WoS: 1Citation - Scopus: 1Dengesiz Epilepsi Veri Seti İçin Sınıflandırmada Farklı SMOTE Yöntemlerinin Etkileri(Institute of Electrical and Electronics Engineers Inc., 2025) Calis, Ahmet Gokay; Ergezer, HalitIn this study, the effects of different SMOTE methods on machine learning algorithms for the imbalanced epilepsy dataset were investigated. After filtering, the imbalanced dataset was balanced with 5 different SMOTE methods and classified with various machine learning algorithms. Coarse-K-Nearest Neighbor, Bagged Trees, and Artificial Neural Networks models were evaluated in epilepsy detection. The performance of these different models was compared with Matthews Correlation Coefficient (MCC) and F1 Score metrics. The results showed that the Borderline-SMOTE algorithm had the highest F1 Score and MCC values among all machine learning algorithms. © 2025 Elsevier B.V., All rights reserved.Article Detection and Classification of Femoral Neck Fractures From Plain Pelvic X-Rays Using Deep Learning and Machine Learning Methods(Turkish Assoc Trauma Emergency Surgery, 2025) Sevinc, Huseyin Fatih; Ureten, Kemal; Karadeniz, Talha; Gultekin, Gokhan KorayBackground: Femoral neck fractures are a serious health concern, particularly among the elderly. The aim of this study is to diagnose and classify femoral neck fractures from plain pelvic X-rays using deep learning and machine learning algorithms, and to compare the performance of these methods. Methods: The study was conducted on a total of 598 plain pelvic X-ray images, including 296 patients with femoral neck fractures and 302 individuals without femoral neck fractures. Initially, transfer learning was applied using pre-trained deep learning models: VGG-16, ResNet-50, and MobileNetv2. Results: The pre-trained VGG-16 network demonstrated slightly better performance than ResNet-50 and MobileNetV2 for detecting and classifying femoral neck fractures. Using the VGG-16 model, the following results were obtained: 95.6% accuracy, 95.5% sensitivity, 93.3% specificity, 95.7% precision, 95.5% F1 Score, a Cohen's kappa of 0.91, and the Receiver Operating Characteristic (ROC) curve of 0.99. Subsequently, features extracted from the convolution layers of VGG-16 were classified using common machine learning algorithms. Among these, the k-nearest neighbor (k-NN) algorithm outperformed the others and exceeded the accuracy of the VGG-16 model by 1%. Conclusion: Successful results were obtained using deep learning and machine learning methods for the detection and classification of femoral neck fractures. The model can be further improved through multi-center studies. The proposed model may be especially useful for physicians working in emergency departments and for those not having sufficient experience in evaluating plain pelvic radiographs.Conference Object Citation - WoS: 10Citation - Scopus: 21Multi-Label Classification of Text Documents Using Deep Learning(Ieee, 2020) Mohammed, Hamza Haruna; Dogdu, Erdogan; Gorur, Abdul Kadir; Choupani, RoyaRecently, studies in the field of Natural Language Processing and its related applications continue to mount up. Machine learning is proven to be predominantly data-driven in the sense that generic model building methods are used and then tailored to specific application domains. Needless to say, this has proven to be a very effective approach in modeling the complicated data dependencies we frequently experience in practice, making very few assumptions, and allowing the information to talk for themselves. Examples of these applications can be found in chemical process engineering, climate science, healthcare, and linguistic processing systems for natural languages, to name a few. Text classification is one of the important machine learning tasks that is used in many digital applications today; such as in document filtering, search engines, document management systems, and many more. Text classification is the process of categorizing of text documents into a given set of labels. Furthermore, multi-label text classification is the task of categorization of text documents into one or more labels simultaneously. Over the years, many methods for classifying text documents have been proposed, including the popularly known bag of words (BoW) method, support vector machine (SVM), tree induction, and label-vector embedding, to mention a few. These kinds of tools can be used in many digital applications, such as document filtering, search engines, document management systems, etc. Lately, deep learning-based approaches are getting more attention, especially in extreme multi-label text classification case. Deep learning has proven to be one of the major solutions to many machine learning applications, especially those involving high-dimensional and unstructured data. However, it is of paramount importance in many applications to be able to reason accurately about the uncertainties associated with the predictions of the models. In this paper, we explore and compare the recent deep learning-based methods for multi-label text classification. We investigate two scenarios. First, multi-label classification model with ordinary embedding layer, and second with Glove, word2vec, and FastText as pre-trained embedding corpus for the given models. We evaluated these different neural network model performances in terms of multi-label evaluation metrics for the two approaches, and compare the results with the previous studies.Article Citation - WoS: 2Citation - Scopus: 2Machine Learning-Driven Approach for Reducing Tool Wear in Die-Sinking Electrical Discharge Machining(Springer Heidelberg, 2025) Cogun, Can; Ayli, EceThis study examines the use of machine learning (ML) techniques to optimize the basic machining parameters and protrusion dimensions that affect tool shape degeneration in die-sinking electric discharge machining (EDM). The primary objective is to decrease errors and enhance prediction and optimization effectiveness. This study introduces a completely novel tool geometry model aimed at minimizing tool shape degeneration, which, to our knowledge, has not been previously documented in the literature. Additionally, this research represents the first instance of employing ML techniques to generate data for addressing this specific type of problem, further advancing the field of die-sinking EDM. The pivotal machining parameters include discharge current, pulse time and machining depth. Three ML approaches are implemented in this investigation: Artificial Neural Network (ANN), Adaptive-Network-Based Fuzzy Inference System (ANFIS), and Support Vector Machine (SVM). In comparison with experimental outcomes, the ANN technique exhibited superior predictive ability with an coefficient of determination (R2) of 0.99985 and an Mean Relative Error (MRE) of 0.854%. Four distinct EDM machining scenarios are presented and machining parameters and protrusion dimensions are optimized using the ANN technique to decrease tool shape degeneration. Optimizing the machining parameters and diagonal dimensions of the protrusion substantially reduced tool shape degeneration. This research demonstrates the effectiveness of ANN in optimizing machining parameters and improving tool performance in die-sinking EDM. A significant reduction in total wear area of 66.7% was achieved with a considerably lower time cost through the optimized ANN network. While the study demonstrates promising results, its reliance on specific datasets for training may limit the generalizability of the model to broader machining scenarios.Article Prediction of Noise Generated by Rod-Airfoil Configuration: an Investigation Based on Experiments and Machine Learning(Sage Publications Ltd, 2024) Kocak, Eyup; Ayli, EceThis study investigated the effects of various parameters on the SPL (Sound Pressure Level) levels of rod-airfoil configurations. An experimental study was performed to investigate the effects of the rod parameters, such as the configuration of the rod, the distance between the rod and the airfoil, the diameter effect of the rod, and the geometry of the rod, on the performance of the rod-airfoil configuration. An Artificial Neural Network (ANN) model was then developed and applied to accurately predict the SPL of rod-airfoil configurations. The results of the study revealed that the Levenberg-Marquardt (LM) algorithm with 2 hidden neurons produced the best performance in predicting the SPL level, with a training R-squared value of 0.9998 and a testing R-squared value of 0.998715. The findings also indicated that increasing rod diameter increases sound pressure level while reducing gap width increases SPL levels and decreases frequency values. This method offers a more precise and effective technique to forecast the SPL levels of rod-airfoil designs, allowing designers to enhance their creations and lower noise levels. The findings of this study can also be utilized to direct future research in this area and offer important information for a better understanding of the mechanism of rod-airfoil noise creation. To the best of the authors' knowledge, this is the first study to look into rod-airfoil design predictions made using machine learning approaches.Article Citation - WoS: 3Citation - Scopus: 4Predicting Stability Factors for Rotational Failures in Earth Slopes and Embankments Using Artificial Intelligence Techniques(de Gruyter Poland Sp Z O O, 2024) Cemiloglu, Ahmed; Cao, Yingying; Sabonchi, Arkan K. S.; Nanehkaran, Yaser A.This study focuses on slope stability analysis, a critical process for understanding the conditions, durability, mass properties, and failure mechanisms of slopes. The research specifically addresses rotational-type failure, the primary instability mechanism affecting earth slopes. Identifying and understanding key factors such as slope height, slope angle, density, cohesion, friction, water pore pressure, and tensile cracks are essential for effective stabilization strategies. The objective of this study is to develop accurate predictive models for slope stability analysis using advanced intelligent techniques, including data mining mapping and complex decision tree regression (DTR). The models were validated using performance metrics such as mean absolute error (MAE), mean squared error (MSE), root mean square error (RMSE), and the coefficient of determination (R-2). Additionally, overall accuracy was assessed using a confusion matrix. The predictive model was tested on a dataset of 120 slope cases, achieving an accuracy of approximately 91.07% with DTR. The error rates for the training set were MAE = 0.1242, MSE = 0.1722, and RMSE = 0.1098, demonstrating the model's capability to effectively analyze and predict slope stability in earth slopes and embankments. The study concludes that these intelligent techniques offer a reliable approach for stability analysis, contributing to safer and more efficient slope management.
- «
- 1 (current)
- 2
- 3
- »