Investigation and Implementation of New Technology Wearable Mobile Laser Scanning (WMLS) in Transition to an Intelligent Geospatial Cadastral Information System
Yiğit, Abdurahman Yasin | Ulvi, Ali | Yakar, Murat
The human population is constantly increasing throughout the world, and accordingly, construction is increasing in the same way. Therefore, there is an emergence of irregular and unplanned urbanization. In order to achieve the goal of preventing irregular and unplanned urbanization, it is necessary to monitor the cadastral borders quickly. In this sense, the concept of a sensitive, up-to-date, object-based, 3D, and 4D (4D, 3D + time) cadastral have to be a priority. Therefore, continuously updating cadastral maps is important in terms of sustainability and intelligent urbanization. In addition, due to the increase in urbanization, it has become necessary to update the cadastral information system and produce 3D cadastral maps. However, since there are big problems in data collection in urb...
An Adaptive Underwater Image Enhancement Framework Combining Structural Detail Enhancement and Unsupervised Deep Fusion
Kahveci, Semih | Avaroğlu, Erdinç
The underwater environment severely degrades image quality by absorbing and scattering light. This causes significant challenges, including non-uniform illumination, low contrast, color distortion, and blurring. These degradations compromise the performance of critical underwater applications, including water quality monitoring, object detection, and identification. To address these issues, this study proposes a detail-oriented hybrid framework for underwater image enhancement that synergizes the strengths of traditional image processing with the powerful feature extraction capabilities of unsupervised deep learning. Our framework introduces a novel multi-scale detail enhancement unit to accentuate structural information, followed by a Latent Low-Rank Representation (LatLRR)-based simplifi...
Explainable Sinkhole Susceptibility Mapping Using Machine-Learning-Based SHAP: Quantifying and Comparing the Effects of Contributing Factors in Konya, Türkiye
Iban, Muzaffer Can
Sinkholes, naturally occurring formations in karst regions, represent a significant environmental hazard, threatening infrastructure, agricultural lands, and human safety. In recent years, machine learning (ML) techniques have been extensively employed for sinkhole susceptibility mapping (SSM). However, the lack of explainability inherent in these methods remains a critical issue for decision-makers. In this study, sinkhole susceptibility in the Konya Closed Basin was mapped using an interpretable machine learning model based on SHapley Additive exPlanations (SHAP). The Random Forest (RF), eXtreme Gradient Boosting (XGBoost), and Light Gradient Boosting Machine (LightGBM) algorithms were employed, and the interpretability of the model results was enhanced through SHAP analysis. Among the c...
Morphological Characteristics of Grapevine Cultivars and Closed Contour Analysis with Elliptic Fourier Descriptors
Demir, Bünyamin
Morphology is the most visible and distinct character of plant organs and is accepted as one of the most important tools for plant biologists, plant breeders and growers. A number of methods based on plant morphology are applied to discriminate in particular close cultivars. In this study, image processing analysis was used on 20 grape cultivars (“Amasya beyazı“, “Antep karası“, “Bahçeli karası”, “Çavuş“, “Cevşen“, “Crimson“, “Dimrit“, “Erenköy beyazı“, “Hafızali“, “Karaşabi“, “Kırmızı“, “İzabella (Isabella) “, “Morşabi“, “Müşgüle“, “Nuniya“, “Royal“, “Sultani çekirdeksiz (Sultanina)“, “Yalova incisi“, “Yerli beyazv“, “Yuvarlak çekirdeksiz“) to classify them. According to image processing analysis, the longest and the greatest projected area values were observed in “Antep karası“ cultivar....
Capturing the Experience: How Digital Media Affects Memory Retention in Museum Education
Say, Fuat Serkan | Öztürk, İsmail Yavuz
This study investigates the effects of digital media usage, specifically photo-taking and video recording, on memory retention in the context of museum education. Utilizing a quasi-experimental design, this research involved three groups, each exposed to different conditions: observation without media use, photo-taking, and video recording. A total of 120 university students who participated in the study were divided randomly into groups balanced by working memory capacity. Immediate and delayed recall tests were conducted to assess short-term memory and long-term retention. The results reveal that participants who merely observed the objects exhibited considerably better memory performance compared to those who used digital media. This result is consistent with the cognitive offloading hy...
Smart Cities in the Global Context: Geographical Analyses of Regional Differentiations
Tijjani, Kabeer Saleh | Sarıkaya Levent, Yasemin | Levent, Tolga
The increasing urbanisation and technological advancements have driven the global adoption of smart city initiatives, yet regional differences persist due to economic, social, and technological disparities. Despite the numerous studies on smart cities, there remains a research gap in comprehensive global analyses exploring regional differentiations in smart city development. This study aims to examine how smart cities differentiate, especially through associations between regions and smart city dimensions. This study utilises data from the IMD Smart City Index 2023 and applies a multi-step methodology based on the United Nations’ geographic regions, employing geographical and statistical analyses. The findings reveal distinct regional differentiations, highlighting a clear Global North–Sou...
Smart Cities in the Global Context: Geographical Analyses of Regional Differentiations
Tijjani, Kabeer Saleh | Sarıkaya Levent, Yasemin | Levent, Tolga
The increasing urbanisation and technological advancements have driven the global adoption of smart city initiatives, yet regional differences persist due to economic, social, and technological disparities. Despite the numerous studies on smart cities, there remains a research gap in comprehensive global analyses exploring regional differentiations in smart city development. This study aims to examine how smart cities differentiate, especially through associations between regions and smart city dimensions. This study utilises data from the IMD Smart City Index 2023 and applies a multi-step methodology based on the United Nations’ geographic regions, employing geographical and statistical analyses. The findings reveal distinct regional differentiations, highlighting a clear Global North–Sou...
Automating an Encoder–Decoder Incorporated Ensemble Model: Semantic Segmentation Workflow on Low-Contrast Underwater Images
Bektaş, Jale
Numerous methods have been proposed for semantic segmentation and the state-of-the-art part is likely to be incorporated by deep learning-based methods which show a salient performance. This study addresses the challenge of semantic segmentation in low-contrast imbalanced under water images. Moreover, it employs nine model fusions as a downstream workflow task using encoder–decoder architectures with Dice Loss and Focal Loss training focusing on the imbalance data. Afterwards, the most effective two encoder–decoder fusion models, Res34+Unet and VGG19+FPN, by 0.592%, 0.590% mIoU on average and by 0.510%, 0.491% F1-score yielded better performance, respectively, than other models. Using a weight-optimization algorithm, the ensemble model with recreated IoU results improves the accuracy for b...
Assessment of Groundwater Potential Zones Utilizing Geographic Information System-Based Analytical Hierarchy Process, Vlse Kriterijumska Optimizacija Kompromisno Resenje, and Technique for Order Preference by Similarity to Ideal Solution Methods: A Case Study in Mersin, Türkiye
Çelik, Mehmet Özgür | Kuşak, Lütfiye | Yakar, Murat
The indiscriminate use of surface water has heightened the demand for groundwater supplies. Therefore, it is critical to locate potential groundwater sources to develop alternative water resources. Groundwater detection is tremendously valuable, as is sustainable groundwater management. Mersin, in southern Türkiye, is expected to confront drought shortly due to increased population, industry, and global climate change. The groundwater potential zones of Mersin were determined in this study by GIS-based AHP, VIKOR, and TOPSIS methods. Fifteen parameters were used for this goal. The study area was separated into five categories. The results show that the study area can be divided into “Very High” zones (4.98%, 5.94%, 7.96%), followed by “High” zones (10.89%, 10.32%, 16.50%), “Moderate” zones...
Machine Learning for Out-of-Sample Prediction of Industry Portfolio Returns Within Multi-Factor Asset Pricing Models
Duran, Esra Sarıoğlu | Korkmaz, Turhan
Accurately predicting asset returns remains a central challenge in finance, with significant implications for portfolio optimization and risk management. In response to the challenge, this study evaluates the predictive performance of machine learning algorithms in estimating excess returns of U.S. industry portfolios, within the out-of-sample prediction framework of the Fama–French three-, four-, five- and six-factor asset pricing models. In the analysis, Support Vector Regression, Multilayer Perceptron, Linear Regression, and k-Nearest Neighbor were employed using monthly return data from 1992 to 2022, covering 5-, 10-, 12-, 17-, 30-, 38-, 48-, and 49-portfolio configurations composed of NYSE, AMEX, and NASDAQ-listed firms. The findings reveal that support vector regression achie...
Suppressing Calcium Deactivation in Selective Catalytic Reduction of NOx from Diesel Engines Using Antimony
Suppressing Calcium Deactivation in Selective Catalytic Reduction
Resitoglu, Ibrahim Aslan
The selective catalytic reduction (SCR) of NOx emissions by hydrocarbons (HCs) using a silver (Ag)-based catalyst offers significant advantages over conventional SCR systems that rely on ammonia reductants and vanadium-based catalysts. However, the conversion rate of SCR is influenced by several factors, among which catalyst poisoning is a major concern. Toxic metals such as sodium (Na), potassium (K), magnesium (Mg), and calcium (Ca) can degrade catalyst activity and lead to deactivation. Poisoned catalysts suffer from reduced conversion rates and premature deactivation before reaching their intended operational lifespan. In particular, calcium poisoning results in the formation of CaO (calcium oxide), which reacts to produce a CaWO4 compound that severely impairs SCR performance. This st...
Multivariate Analysis Approaches for Dimension and Shape Discrimination of Vitis vinifera Varieties
Demir, Bünyamin
In this study, berry dimensions and shape traits, which are important for the design of the grape processing system and the classification of 10 different grape varieties grown in same ecological conditions (‘Ata Sarısı’, ‘Barış’, ‘Dımışkı’, ‘Hatun Parmağı’, ‘Helvani’, ‘Horoz Karası’, ‘Hönüsü’, ‘İtalia’, ‘Mevlana Sarısı’, and ‘Red Globe’) were determined; differences between the varieties were identified with the use of discriminant analysis. The largest grape varieties were identified as ‘Ata Sarısı’ and ‘Red Globe’. The ‘Red Globe’ and ‘Helvani’ varieties had geometrically sphere-like shape. The ‘Barış’ variety had the lowest size averages. According to elliptic Fourier analysis, the primary source of shape variation was ellipse and sphere-looking varieties. However, shape variation was ...
A Feature Selection-Based Multi-Stage Methodology for Improving Driver Injury Severity Prediction on Imbalanced Crash Data
Çiğdem İnan ACI | Gizen Mutlu | Murat Ozen | Esra Sarac | Vahide Nida Kılıç Uzel
Predicting driver injury severity is critical for enhancing road safety, but it is complicated because fatal accidents inherently create class imbalance within datasets. This study conducts a comparative analysis of machine-learning (ML) and deep-learning (DL) models for multi-class driver injury severity prediction using a comprehensive dataset of 107,195 traffic accidents from the Adana, Mersin, and Antalya provinces in Turkey (2018–2023). To address the significant imbalance between fatal, injury, and non-injury classes, the hybrid SMOTE-ENN algorithm was employed for data balancing. Subsequently, feature selection techniques, including Relief-F, Extra Trees, and Recursive Feature Elimination (RFE), were utilized to identify the most influential predictors. Various ML models (K-Nearest ...
Enhanced Multi-Class Driver Injury Severity Prediction Using a Hybrid Deep Learning and Random Forest Approach
Çiğdem İnan Acı | Gizen Mutlu | Murat Ozen | Mehmet Acı
Predicting driver injury severity and identifying factors influencing crash outcomes are crucial for developing effective traffic safety measures. This study focuses on estimating driver injury severity (uninjured, injured, or killed) and determining critical factors affecting crash outcomes. A hybrid framework combining Deep Neural Networks (DNNs) and Random Forest (RF) is proposed, where a DNN extracts features and RF performs the final classification, leveraging ensemble methods. The results were compared with those of well-known methods (e.g., kNN, XGBoost), with the hybrid approach achieving the best performance (0.92 accuracy, 0.89 F1-macro, 0.91 F1-micro scores) in predicting injury severity. The results showed that crash type, vehicle type, driver fault, intersection type, season, ...
Customized Insulation Strategies for Türkiye: Life Cycle Cost Analysis and Impact on Business Competitiveness
Saygın, Muhammet | Say, Fuat Serkan | Öztürk, İsmail Yavuz
A significant portion of energy consumption in buildings is allocated to heating, with substantial losses resulting from inadequate insulation, poor sealing, and thermal bridging. While proper insulation plays a crucial role in mitigating these losses, determin- ing its optimal thickness is essential to reduce energy consumption and increase energy efficiency. This study employs life cycle cost analysis and average heating degree day values to calculate the optimum insulation thickness for 81 provinces in Türkiye. The findings highlight the absence of a one-fits-all insulation solution, emphasizing the need for customized approaches tailored to specific conditions that consider specific factors, such as environmental conditions, heating sources, costs, economic parameters and the materials...
A Step towards Sustainable Education: Does an Entrepreneurial Teacher Nurture Creativity?
Saygın, Muhammet | Say, Serkan | Öztürk, İsmail Yavuz
This study explores the relationship between teachers’ entrepreneurial behaviors and their creativity-nurturing behaviors, with a particular emphasis on sustainability in education. While previous studies have typically examined entrepreneurship and creativity as separate concepts, often focusing on their individual dimensions, this study underscores the significance of integrating entrepreneurial and creative competencies to promote sustainable educational practices. By highlighting how teachers’ entrepreneurial and creative skills contribute to sustainable education, this study addresses the broader impact these competencies have on meeting the evolving needs and expectations of students, families, and society. This approach supports the development of a more resilient and adaptive educa...