WoS İndeksli Yayınlar Koleksiyonu
Permanent URI for this collectionhttps://hdl.handle.net/20.500.12573/394
Browse
96 results
Search Results
Article Time Distributed Classification of Alzheimer’s Disease on MRI Scans(John Wiley and Sons Ltd, 2026) Dundar, Mehmet Sait; Yilmaz, BulentThe diagnosis of Alzheimer's disease (AD) has progressively depended on sophisticated neuroimaging methods alongside cognitive assessments. This study combines volumetric feature analysis with computational modeling techniques, focusing on spatial and temporal analysis, to categorize individuals as cognitively normal (CN), mild cognitive impairment (MCI), or AD using magnetic resonance imaging (MRI) data. In the initial phase, volumetric changes, comprising cortical thickness, white matter, grey matter, cerebrospinal fluid, and total intracranial volume, were derived from the Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset utilizing the CAT12 toolbox in statistical parametric mapping (SPM). Linear regression was utilized on these variables over time to create slopes that reflect volumetric change rates, which then served as inputs for machine learning classifiers. The slopes of cortical thickness exhibited the greatest classification accuracy, reaching 82.5% with a random forest model for differentiating AD from CN individuals. During the second phase, a deep learning methodology was utilized, relying solely on the MRI scans and excluding the outcomes from the first phase. A pre-trained 3D ResNet-101 convolutional neural network (CNN) model extracted spatial characteristics from MRI volumes, whereas long short-term memory (LSTM) networks recorded temporal dynamics across subsequent annual scans. This hybrid CNN-LSTM design markedly improved classification performance, attaining 96.7% accuracy for AD against CN and enhancing the distinction of MCI cases. Nonetheless, discrepancies in MCI categorization were chiefly ascribed to the restricted access to annual MRI data and the model's pre-training on CN and AD cohorts. These findings highlight the potential of integrating volumetric statistical analysis with deep learning for automated AD categorization. This work enhances neuroimaging diagnostic methods by utilizing both spatial and temporal MRI data, enabling early diagnosis and better evaluation of disease development.Article Leveraging Clinical Data for Early Heart Disease Prediction: A Machine Learning Approach With Interpretability Analysis(SAGE Publications Ltd, 2026) Qumsiyeh, Emma; Al-Wirdian, Qassam; Ersoz, Nur SebnemBackground: Heart disease remains one of the leading causes of mortality worldwide, highlighting the need for early and accurate diagnosis to support effective prevention and treatment strategies. Methods: This study presents a machine-learning-based approach for predicting heart disease using clinical and demographic data from a publicly available dataset. Four widely used classification algorithms-Logistic Regression, Random Forest, K-Nearest Neighbors (KNN), and Decision Trees-were evaluated to identify the most effective predictive model. The dataset underwent comprehensive preprocessing, including handling missing values, categorical encoding, and feature normalization, to enhance data quality and model robustness. Model performance was assessed using accuracy, precision, recall, and AUC-ROC metrics. Results: Findings show that hyperparameter-optimized models, particularly Random Forest and KNN, demonstrated strong predictive performance. Explainability techniques, specifically SHapley Additive exPlanations (SHAP), were incorporated to improve interpretability, transparency, and clinical trust. SHAP values were used to analyze feature importance and provide explanations for individual predictions. Conclusion: The results underscore the potential of interpretable machine-learning models as valuable tools for early diagnosis, risk stratification, and clinical decision support. Future research should employ larger datasets and investigate real-time predictive applications further to enhance the generalizability and clinical utility of these models.Article An Attention-Based Autoencoder Model with Gated Recurrent Unit for Stock Price Movement Prediction(Springer Nature, 2026) Kolukisa, Burak; Bakir-Gungor, Burcu; Akkas, HuseyinPredicting stock movements is crucial for investors looking to maximize their profits in rapidly changing financial markets. However, noise in stock price data makes it harder to detect the trends and ultimately decreases the performance of predictive models. To address these challenges that are caused by noise, this study proposes two novel models, i.e., an Attention-based Autoencoder (ABA) and an Attention-based Variational Autoencoder with Gated Recurrent Units (AGRUA), which uniquely integrate denoising, attention, and GRU layers. Firstly, a data set is created by adding 9 different technical indicators to the historical data of Borsa Istanbul (BIST 30) stocks. Secondly, proposed methods and other well-known deep learning models were used to remove noise from the data sets. Finally, each denoised dataset was fed separately to the Extreme Gradient Boosting model and subjected to a buy-sell process. The results were measured using trading indicators such as amount of the profits and Sharpe Ratio, Sortino Ratio and Maximum Drawdown. The proposed models produced substantial financial gains, with AGRUA achieving the highest total profit and ABA achieving the lowest average Maximum Drawdown, thereby demonstrating superior risk-adjusted performance. Lastly, Friedman and Nemenyi tests confirmed that AGRUA and ABA surpass most of the benchmarks in profit and risk-adjusted returns. The performance of the proposed method demonstrates its value in capturing nonlinear market patterns and improving decision accuracy, emphasizing the need for noise reduction before forecasting.Article Machine Learning and Scenario-Based Forecasting of Türkiye’s Renewable Energy Transition toward Net-Zero 2053(Elsevier Ltd, 2026-05) Sutcu, Muhammed; Yildiz, Baris; Sahin, Nurettin; Almomany, Abedalmuhdi; Gulbahar, Ibrahim TumayThe issue of global warming has been identified as one of the most critical challenges of the 21st century, with the consumption of fossil fuels being identified as a major contributor to greenhouse gas emissions. In response to these challenges, countries worldwide are expediting their transition towards renewable energy sources to meet international climate commitments, such as the Paris Agreement, and to achieve long-term sustainability goals. Türkiye has established a target to achieve net-zero emissions by 2053. This objective is consistent with both the nation's domestic energy strategy and its international commitments. Nevertheless, the transition from fossil fuels to renewable energy sources is impeded by geographical, economic, and technological constraints. The present study aims to assess the capacity and efficiency of renewable energy in Türkiye with environmental protocols and future electricity demand projections. Electricity generation, transmission data, and national energy plans are used to identify future electricity generation and capacity trends. In the context of this study, a range of machine learning models is executed across diverse scenarios, yielding a series of outcomes. Consequently, the repercussions of regulatory measures and financial investments were examined, and prospective inferences were derived. The findings underscore the pivotal role of scenario-based modeling in formulating sustainable energy policies and directing investment decisions within the context of climate change mitigation.Article Citation - WoS: 1Citation - Scopus: 1Machine Learning for V2X-Enabled Microgrids: A Bibliometric and Thematic Review of Intelligent Energy Management Applications(Springer Heidelberg, 2026-03-09) Dogan, Yasemin; Unlu, RamazanModern power systems are evolving due to convergence of electric mobility, artificial intelligence, and renewable energy integration. Electric vehicles serve as dynamic, mobile energy storage units playing a vital role in ensuring resilient microgrid operations, via vehicle-to-everything (V2X) technology. However, despite the rise of machine learning (ML) in energy management, much of the existing literature remains fragmented lacking a holistic perspective across all facets of V2X-enabled microgrids. This study fills this gap by conducting a systematic bibliometric and thematic analysis of 310 articles obtained from Web of Science (2013-2024). By combining bibliometric mapping with thematic synthesis, the research identifies dominant and emerging ML techniques-ranging from reinforcement learning to federated learning-and evaluates their roles in microgrid management. The study highlights underexplored areas, including decentralized coordination, encouraging prosumer participation, understanding user behavior, safeguarding cybersecurity, improving real-time optimization, and the effective integration and adaptation of V2X technology within microgrid ecosystems. These gaps emphasize the need for interdisciplinary research and policy frameworks to address the social dimensions of future energy systems. Beyond a comprehensive overview, this paper proposes a research roadmap integrating technical, social, and policy dimensions. It offers actionable guidance for researchers, stakeholders aiming to unlock the potential of intelligent, human-centered, and socially inclusive energy ecosystems. Furthermore, the findings align with UN Sustainable Development Goals (SDG 7, 11, and 13), while also creating a positive impact on humanity by supporting the well-being of both society and the planet. Ultimately, this reinforces the indispensable role of ML in advancing the zero-carbon transition.Article Supervised Learning-Driven Dead Band Control of Occupant Thermostats for Energy-Efficient Residential HVAC(Elsevier, 2026-03) Savasci, Alper; Ceylan, Oguzhan; Paudyal, SumitHeating, ventilation, and air conditioning (HVAC) systems play a crucial role in demand-side management (DSM) by shaping residential electricity consumption and enabling flexible, grid-responsive operation. Thermostats in HVAC systems regulate indoor temperature as part of a closed-loop control framework, typically incorporating a fixed temperature dead band-a range around the setpoint where no action is taken-to reduce energy use and prevent frequent cycling of the HVAC system. Although essential for efficiency and equipment longevity, fixed dead bands limit adaptability, as dynamically adjusting them under varying environmental conditions remains challenging for occupants. To address this limitation, we propose a machine learning (ML)-based dead band tuning framework that optimally adjusts thermostat settings in real time. The method integrates conventional optimization with data-driven modeling: a mixed-integer linear programming (MILP) model is first used to gen erate optimal dead band values under measured outdoor temperature records (diverse seasonal weather scenarios) which are then employed to train the ML-based predictor to learn a real-time discrete dead band decision policy that approximates the MILP-optimal hysteresis-aware decisions. Among the evaluated models, Random Forest demonstrates superior predictive performance, achieving a mean squared error (MSE) of 0.0399 and a coefficient of determination (R2) of 95.75 %.Article G-S a Prior Biological Knowledge-Based Pattern Detection and Enrichment Framework for Multi-Omics Data Integration(MDPI, 2025-11-29) Unlu Yazici, Miray; Bakir-Gungor, Burcu; Yousef, MalikThe rapid advancements in high-throughput technologies have led to a dramatic increase in diverse -omics data types, enabling comprehensive analyses, especially for complex diseases like cancer. Despite the development of multi-omics approaches, the challenges of scaling integration to massive, heterogeneous -omics datasets suggest that novel computational tools need to be designed. In this study, we propose an approach for integrating microRNA (miRNA) and messenger RNA (mRNA) expression data, incorporating prior biological knowledge (PBK). This approach scores and ranks groups of miRNAs and their associated genes using cross-validation iterations. The proposed method incorporates a Pattern detection (P) component to identify molecular motifs unique to each biological group. The analysis also facilitates the visualization of the groups, facilitating the identification of co-occurring groups and their characteristic features across iterations. Furthermore, the groups are scored using an over-representation analysis through a new Enrichment (E) component in each iteration. The clusters of the groups based on the Enrichment Scores (ESs) are visualized in a heatmap to obtain novel insights into the collective behavior and dependencies of the groups, aiming to understand the molecular mechanisms of complex diseases. The developed G-S-M-E tool not only provides performance metrics and biological scores at the group level but also offers comprehensive insights into intricate multi-omics interactions. In summary, our study emphasizes the importance of mathematical and data science methodologies in elucidating intricate multi-omics integration, yielding a formalized approach that deepens our comprehension of complex diseases.Article Citation - WoS: 2Citation - Scopus: 1A Comprehensive Analysis of Acoustic Emission Signals To Distinguish the Different Damage Types for Fiber-Reinforced Polymers: A Review(Wiley, 2025-12-03) Yilmaz, CagatayFiber-reinforced polymers (FRP) attract the attention of key industries, such as aerospace, wind energy, and automotive, as they can reduce the weight of structural components without compromising their mechanical properties. Due to FRP's anisotropic and non-homogeneous structure, their failure under different loading conditions and the corresponding failure mechanisms must be investigated. One method that progressively monitors the failure of FRP underload is Acoustic Emission (AE). AE can register the elastic stress waves in the form of digitized waveforms, released by the discontinuous events that occur in the FRP under load. These discontinuities can be clustered and identified as transverse cracking, fiber/matrix interface debonding, delamination, and fiber failure by analyzing the AE waveforms. Recently, numerous clustering approaches using machine learning algorithms, along with the varying features of AE waveforms, have been developed and are being used. These algorithms include supervised and unsupervised clustering, deep learning algorithms, and neural network methods, among others. While supervised algorithms require a training dataset to classify AE signals, unsupervised algorithms can perform clustering without training datasets. Deep learning and neural network algorithms can train themselves to cluster data, but they may require a significant amount of computer power when the dataset is large. This review paper provides comprehensive information on the clustering algorithm, along with the AE wave features, the range of features for different damage types, and the type of reinforcer.Article Forecasting the Consumer Price Index in Türkiye Using Machine Learning Models: A Comparative Analysis(Gazi Univ, 2025-09-01) Söylemez, İsmet; Ünlü, Ramazan; Nalici, Mehmet ErenThis study utilizes machine learning models to forecast Türkiye's Consumer Price Index (CPI), thereby addressing a critical gap in inflation prediction methodologies. The central research problem involves the forecasting of CPI in a volatile economic environment, which is essential for informed policymaking. The primary objective of this study is to evaluate the performance of three machine learning models, such as Decision Tree (DT), Random Forest (RF), and Support Vector Machine (SVM), in forecasting CPI over periods ranging from one to six months, utilizing data from 2012 to 2024. The study's unique contribution lies in the application of the \"SelectKBest\" method, which identifies the most relevant indices, thereby enhancing the efficiency of the models. An ensemble method, Averaging Voting, is also employed to combine the strengths of these models, producing more accurate and robust predictions. The findings indicate that while the RF model consistently generates the most accurate forecasts across all shifts, the SVM model demonstrates a particular strength in the domain of short-term predictions. The ensemble model demonstrates a substantial performance improvement, with a R2 value of 0.962 for one-month ahead of estimates and 0.956 for five-month forecasts. This combined approach has been shown to outperform individual models, offering a more reliable framework for CPI forecasting. The findings offer valuable insights for economic policymakers, enabling more precise and stable inflation predictions in Türkiye.Article Developing a Label Propagation Approach for Cancer Subtype Classification Problem(Tubitak Scientific & Technological Research Council Turkey, 2022-01-01) Guner, Pinar; Bakir-Gungor, Burcu; Coskun, MustafaCancer is a disease in which abnormal cells grow uncontrollably and invade other tissues. Several types of cancer have various subtypes with different clinical and biological implications. Based on these differences, treatment methods need to be customized. The identification of distinct cancer subtypes is an important problem in bioinformatics, since it can guide future precision medicine applications. In order to design targeted treatments, bioinformatics methods attempt to discover common molecular pathology of different cancer subtypes. Along this line, several computational methods have been proposed to discover cancer subtypes or to stratify cancer into informative subtypes. However, existing works do not consider the sparseness of data (genes having low degrees) and result in an ill-conditioned solution. To address this shortcoming, in this paper, we propose an alternative unsupervised method to stratify cancer patients into subtypes using applied numerical algebra techniques. More specifically, we applied a label propagation based approach to stratify somatic mutation profiles of colon, head and neck, uterine, bladder, and breast tumors. We evaluated the performance of our method by comparing it to the baseline methods. Extensive experiments demonstrate that our approach highly renders tumor classification tasks by largely outperforming the state-of-the-art unsupervised and supervised approaches.