Murat IŞIK

Dr. Murat IŞIK

orcid

Research Focus & Metrics

Academic Career Length

11Years (2016-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
4 November 2024 in PeerJ Computer Science
Verified
Journal Article
Open access
PDF file
MIMurat IŞIK
Murat IŞIK
Feature detection and matching are fundamental components in computer vision, underpinning a broad spectrum of applications. This study offers a comprehensive evaluation of traditional feature detections and descriptors, analyzing methods such as Scale Invariant Feature Transform (SIFT), Speeded-Up Robust Features (SURF), Binary Robust Independent Elementary Features (BRIEF), Oriented FAST and Rotated BRIEF (ORB), Binary Robust Invariant Scalable Keypoints (BRISK), KAZE, Accelerated KAZE (AKAZE), Fast Retina Keypoint (FREAK), Dense and Accurate Invariant Scalable descriptor for Yale (DAISY), Features from Accelerated Segment Test (FAST), and STAR. Each feature extractor was assessed based on its architectural design and complexity, focusing on how these factors influence computational efficiency and robustness under various transformations. Utilizing the Image Matching Challenge Photo Tourism 2020 dataset, which includes over 1.5 million images, the study identifies the FAST algorithm as the most efficient detector when paired with the ORB descriptor and Brute-Force (BF) matcher, offering the fastest feature extraction and matching process. ORB is notably effective on affine-transformed and brightened images, while AKAZE excels in conditions involving blurring, fisheye distortion, image rotation, and perspective distortions. Through more than 2 million comparisons, the study highlights the feature extractors that demonstrate superior resilience across various conditions, including rotation, scaling, blurring, brightening, affine transformations, perspective distortions, fisheye distortion, and salt-and-pepper noise.

7 January 2026 in Frontiers in Energy Research
Verified
Journal Article
Open access
PDF file
MIMurat IŞIK
Murat IŞIK
MYMehmet Ali Yalcinkaya
Mehmet Ali Yalcinkaya
Accurate wind power forecasting is critical for grid stability and renewable energy integration, yet the inherent variability of atmospheric conditions presents significant challenges. This study proposes a unified and scalable pipeline that integrates wind regime detection, temporal sequence modeling, and regime-conditioned deterministic and probabilistic power forecasting. Using 8 years of high-resolution meteorological data from multiple altitudes, we engineer a comprehensive set of physically interpretable features, including wind shear, temperature gradients, and rolling statistics. Regimes are identified via KMeans and Gaussian Mixture Models, with Principal Component Analysis applied post-clustering for visualization and interpretation. Temporal regime dynamics are characterized through both empirical and Markov transition matrices and modeled using Long Short-Term Memory (LSTM) networks for regime sequence prediction. For power forecasting, regime-specific models are developed using tuned ensemble regressors (XGBoost, LightGBM, CatBoost, and Random Forest), complemented by probabilistic approaches including Quantile Regression Forests, quantile-based XGBoost, and Bayesian neural networks. Results show that regime conditioning significantly enhances forecasting performance, with the stacked meta-learning ensemble achieving R 2 = 0.997 and over 30% reduction in MAE compared to baseline methods. Probabilistic models produce well-calibrated prediction intervals, providing uncertainty-aware forecasts suitable for operational decision-making. This work contributes a novel end-to-end framework that jointly models regime persistence, transitions, and regime-conditioned power output, incorporating uncertainty quantification through Quantile Regression Forests, quantile-based XGBoost, and Bayesian Neural Networks, thereby bridging a gap in the literature where these components are often treated in isolation. The approach advances both accuracy and interpretability, offering practical value for wind farm operation and renewable energy integration.

15 September 2021 in Fırat Üniversitesi Mühendislik Bilimleri Dergisi
Verified
Journal Article
Closed access
Emrah AydemirEmrah Aydemir
Emrah Aydemir
MIMurat IŞIK
Murat IŞIK
Türker TuncerTürker Tuncer
Türker Tuncer
Hızla gelişen teknoloji ile verilere erişmek oldukça kolaylaşmış ancak elde edilen bu veri yığınlarının işlenmesi ve analiz edilmesi ise büyük bir problem haline gelmiştir. Bu çalışmada çevrimiçi bir haber sitesinden metin halinde toplanan yazıların, metin madenciliği ile daha önceden belirlenmiş haber kategorilerine ayrılması sağlanmıştır. Metin halinde toplanan 2248 haber verisi için iki ayrı yöntem kullanılmış ve birinci yöntemde %95,24'ü ikinci yöntemde ise %99,86'sı doğru olarak sınıflandırılmıştır. Türkçe dilinin özgün yapısından kaynaklı sınıflandırma yapılmasının zorluğundan dolayı bu çalışma ileriki metin madenciliği uygulamaları için faydalı olacaktır. Ayrıca elde edilen sonuçlar, literatürde yer edinmiş benzer çalışmalar ile karşılaştırılarak analiz edilmiştir.

16 July 2025 in PeerJ Computer Science
Verified
Journal Article
Open access
PDF file
MIMurat IŞIK
Murat IŞIK
Accurate prediction of solar irradiance is critical for optimizing solar energy systems, enhancing grid stability, and supporting sustainable energy transitions. While numerous studies have explored various methodologies for solar radiation prediction, challenges remain in achieving high accuracy across diverse geographic locations and temporal resolutions. This study presents a novel hybrid model combining temporal convolutional networks (TCN), Transformer encoders (TE), and artificial neural networks (ANN) to predict global horizontal irradiance (GHI) with high precision. Utilizing a comprehensive dataset from three significant U.S. solar energy sites—Desert Sunlight, Copper Mountain, and Solar Star—spanning 22 years at a 30-min temporal resolution, the proposed model demonstrated superior performance metrics, with R2 ranging from 0.94768 to 0.97417, root mean square error (RMSE) between 0.04776 and 0.06543 W/m2, and mean absolute error (MAE) between 0.02510 and 0.03526 W/m2. By leveraging TCN’s temporal feature extraction, TE’s attention mechanisms, and ANN’s dense layer refinements, the model demonstrates significant advancements over existing methods.

7 January 2025 in Balkan Journal of Electrical and Computer Engineering
Verified
Journal Article
Open access
PDF file
MIMurat IŞIK
Murat IŞIK
Emrah AydemirEmrah Aydemir
Emrah Aydemir
MYMehmet Ali Yalçınkaya
Mehmet Ali Yalçınkaya
FOFahri Orman
Fahri Orman
The integration of technology in educational surroundings has evolved from a supplemental enhancement to an essential element of modern education. In response to this shift, there is a growing need for cost-effective tools that can increase student engagement and streamline the assessment process for primary students. This study presents the design and implementation of a low-cost, real-time assessment system tailored specifically for primary school classrooms. Utilizing Arduino-based receivers and student-operated remote controllers, the system provides an affordable and scalable alternative to traditional student response systems. Field tests were conducted with 26 students aged 9 to 10 in a public primary school, where the system's effectiveness was evaluated through teacher observations and student feedback. Results indicate that the system significantly increased student participation, focus, and enjoyment during assessments compared to traditional paper-based methods. Despite some challenges, the system demonstrates great potential as a practical tool for resource-constrained educational environments, with future development focusing on addressing scalability and technical limitations.

7 July 2021 in Acta Orientalia Academiae Scientiarum Hungaricae
Verified
Journal Article
Open access
PDF file
MIMurat IŞIK
Murat IŞIK
This paper is a continuation of a previous study that presented the names of mammal, insect, and reptile species appearing in the Book of Leviticus of the so-called Gözleve Bible. The present study aims to survey the rest of the animal names in the corpus, representing bird species. The translation shows a mixed vocabulary and therefore the distribution of the Kipchak, Oghuzic, and non-Turkic elements will be compared with their equivalents in some of the other books of the Gözleve Bible, a recently published critical edition of another Crimean Karaim Bible, and some Ottoman Turkish Bible translations.