Search Results (31)

Urban air pollution results from complex interactions between vehicle emissions, meteorological conditions, and atmospheric chemistry. While machine learning models achieve high accuracy in air quality prediction, their limited transparency hinders policy adoption. We present an integrated (M-ETAQI) framework combining multiple XAI techniques, temporal decomposition, and causal inference to quantify traffic and meteorological contributions to PM₁₀, PM_2.5, NO_X, and NO₂ concentrations in the Istanbul FSM Bridge corridor (2022–2023 hourly data). Five machine learning models, including XGBoost, LightGBM, CatBoost, Random Forest, and CNN–LSTM–Attention, were trained with temporal cross-validation. SHAP, LIME, PDP, and ALE were applied for interpretability; STL decomposition isolated temporal components, and CCM tested causal links. Tree-based models achieved R² > 0.80 for all pollutants, with CatBoost reaching PM_2.5 R² = 0.876. SHAP confirmed Lag1 as the dominant feature. Wind speed had a significant negative effect on NO_X, while traffic contributed ~20% to NO_X, twice that of other pollutants. STL showed the trend component dominated total variance; NO₂ trend variance = 56.3%. CCM revealed wind speed as the strongest causal driver of NO_X (ρ = 0.37) and confirmed direct traffic–NO_X links. Knowledge distillation from CatBoost improved CNN–LSTM–Attention performance. The four XAI methods yielded consistent attributions, providing robust, cross-validated evidence for traffic management and air-quality policy. Full article

Map conflation is essential for integrating heterogeneous road datasets, but it often requires region- and data-specific algorithm design to automate the complex identification of feature-to-feature correspondences. This effort is increased when only cartographic products are available instead of GIS-ready vectors since both digitization or matching corresponding features manually are labor-intensive. In this study, we assess the performance of a multimodal LLM, GPT-5 “thinking” mode for map conflation directly on a PDF map where road networks from TomTom and OpenStreetMap are embedded as colored polylines. We instruct the LLM to interpret the PDF, extract road geometries and their identifiers, and generate both strict 1:1 and flexible M:N matches. In any hybrid-patterned network cases located around Bosphorus, Istanbul, while M:N matching process increased the number of matches, it also increased false positives and lowered overall F1 scores. In contrast, 1:1 matching produced more balanced correctness-completeness results. The model achieves its highest performance in the cellular-patterned networks. The results show that LLM-based matching can detect a substantial share of true correspondences in such a challenging hybrid setting, but performance clearly depends on the matching strategy: strict or flexible. It highlights both the potential promise and the current limitations of matching embedded road lines. Full article

The increase in population and demand for the various needs of citizens increases the interaction with the geo-environment. Thus, the rate of natural events affecting daily human life increases. Such an event occurred on a rock cliff in a densely populated area in İstanbul (Türkiye). More than four rock blocks (approximately 3–5 m³) belonging to the Paleozoic sequence of İstanbul, composed of nodular limestone with sandy-clay interlayers, detached and fell. The blocks traveled along a path of approximately 60 m and stopped by crushing a couple of buildings downslope. The path was rough and contained various surface conditions (e.g., bedrock, talus, and plants). This study was initiated by the examination of the dimensions of failed rock blocks, their paths, and topographic conditions. Unmanned vehicles (drones) facilitated the generation of 3D numerical models of topographic changes on the site. Quantifying discontinuity properties (such as persistence, spacing, roughness, etc.) and defining weathering properties comprises the second stage, along with sampling. Based on digital topographic data and field observations, cross-sections were defined by means of possible rockfall areas within the area of potentially unstable blocks. Numerical analysis and rockfall analysis were conducted along these critical sections. Interpretation of laboratory data and results obtained from numerical studies leads to an understanding of the mechanism of the recent rockfall event and demonstrates the most critical areas to be considered and reinforced. The research comprises proposing appropriate reinforcement techniques due to the strong Turkish regulations along the “Bosphorus Waterfront Protected Zone”. The study advises pre-cleaning of potentially unstable blocks after a fence production on paths where rocks could fall, and rock anchors in some localities with varying lengths. The latest part of the research covers the re-assessment of mitigation processes with numerical models, which shows that the factor of safety increased to the desired levels. The reinforcement applications at the site match well with the proposed prevention methods. Full article

Background/Objectives: Orthopedic surgery is among the most frequently litigated medical specialties worldwide. However, high-court malpractice decisions involving orthopedic specialists in Türkiye remain underexplored. This study aims to identify the patterns, causes, and outcomes of malpractice cases involving orthopedists by analyzing Turkish Supreme Court decisions over the past 15 years. Methods: A retrospective review of orthopedic malpractice cases adjudicated by the Turkish Court of Cassation between January 2010 and November 2025 was conducted. Variables included type of alleged offense, clinical context, primary/secondary liability, initial court outcomes, high-court decisions, and fault attribution. Findings were compared with international literature to contextualize national patterns. Results: A total of 71 decisions were analyzed. Negligent injury was the most common allegation. Initial acquittal and conviction rates were 50.7% and 49.3%, respectively. The Supreme Court affirmed 53.5% of decisions and overturned 46.5%. Fault was attributed to orthopedic specialists in 29.6% of cases, while 40.8% were found faultless; the remaining cases required additional expert evaluation. Litigation themes included diagnostic delay, postoperative complications, inadequate monitoring, and documentation deficiencies. Comparative analysis revealed substantial alignment between Turkish and international malpractice patterns. Conclusions: Orthopedic malpractice litigation in Türkiye mirrors global trends, with most claims stemming from trauma-related care and diagnostic errors. Although many cases undergo prolonged appeals, ultimate conviction rates remain low. Strengthened documentation, improved communication, and enhanced clinical guideline adherence may reduce litigation risk and improve patient safety. Full article

The development of deep learning-based 3D face recognition has been constrained by the limited availability of large-scale 3D facial datasets, which are costly and labor-intensive to acquire. To address this challenge, we propose a novel 2D-aided framework that reconstructs 3D face geometries from abundant 2D images, enabling scalable and cost-effective data augmentation for 3D face recognition. Our pipeline integrates 3D face reconstruction with normal component image encoding and fine-tunes a deep face recognition model to learn discriminative representations from synthetic 3D data. Experimental results on four public benchmarks, i.e., the BU-3DFE, FRGC v2, Bosphorus, and BU-4DFE databases, demonstrate competitive rank-1 accuracies of 99.2%, 98.4%, 99.3%, and 96.5%, respectively, despite the absence of real 3D training data. We further evaluate the impact of alternative reconstruction methods and empirically demonstrate that higher-fidelity 3D inputs improve recognition performance. While synthetic 3D face data may lack certain fine-grained geometric details, our results validate their effectiveness for practical recognition tasks under diverse expressions and demographic conditions. This work provides an efficient and scalable paradigm for 3D face recognition by leveraging widely available face images, offering new insights into data-efficient training strategies for biometric systems. Full article

The prediction of real estate values is vital for taxation, transactions, mortgages, and urban policy development. Values can be predicted more accurately by statistical or advanced methods together when the size of the data is huge. In metropolitan cities like İstanbul, where size of the real estate data is vast and complex, mass appraisal methods supported by Machine Learning offer a scalable and consistent alternative. This study employs six algorithms: Artificial Neural Network, Extreme Gradient Boosting, K-Nearest Neighbors, Support Vector Regression, Random Forest, and Semi-Log Regression, to estimate the values of real estate on both the Asian and European continent parts of İstanbul. In total, 168,099 residential properties were utilized along with 30 of their features from both sides of the Bosphorus. The results show that RF yielded the best performance in Beşiktaş, while XGBoost performed best in Üsküdar. ANN also produced competitive results, although slightly less accurate than those of XGBoost and RF. In contrast, traditional SVR and SLR models underperformed, especially in terms of R² and RMSE values. With its large-scale dataset, focusing on one of the greatest metropolitan areas, Istanbul, and the usage of multiple ML algorithms, this study stands as a comprehensive and practical contribution to the field of automated real estate valuation. Full article

Türkiye represents an important biogeographic region connecting Southeast Europe with Southwest Asia, where pig domestication began in the western Palearctic. We studied the phylogenetic relationships and spatial distribution of new and published mitochondrial D-loop sequences of wild boars from Türkiye, other parts of the Middle East, and from around the world to understand migration patterns within Asia Minor and other parts of the Middle East as well as across the Bosphorus/Sea of Marmara/Dardanelles, a current migration barrier to Southwest Europe. Our phylogenetic (ML, BI) and spatial (Geneland) analyses revealed haplotypes both endemic to Anatolia and with a wider distribution in the Middle East as well as European (E1) lineages. The latter suggested possible rare immigration into Anatolia at present times and prehistorical/historical anthropogenic translocations of wild boars or pigs, such as during the pre-Hellenic, Roman, and Byzantine periods or during the European crusades, and subsequent introgression into Anatolian wild boars. Import of pigs with E1 haplotypes and introgression into wild boars during the medieval Empire of Trebizond particularly by Italian merchants or settlers, is also suggested. Anatolian lineages that may have formed the basis of the archaic domestication process of pigs in the western Palearctic are discussed. Full article

Maritime transportation is responsible for most global trade and is generally considered more environmentally efficient compared to other modes of transport, particularly for long-distance trade. With increasingly stringent emission regulations, however, accurately quantifying emissions and identifying their key determinants has become essential for effective environmental management. This study introduced a structured and comparative statistical modeling framework for ship-based emission modeling using gross tonnage (GT) as the primary predictor variable, due to its strong correlation with emission levels. Emissions for hydrocarbon (HC), carbon monoxide (CO), particulate matter with an aerodynamic diameter of less than 10 μm (PM10), carbon dioxide (CO₂), sulfur dioxide (SO₂), nitrogen oxides (NO_x), and volatile organic compounds (VOC) were estimated using a bottom-up approach based on emission factors and formulas defined by the U.S. Environmental Protection Agency (EPA), using data from 38,304 vessel movements through the Bosphorus in 2021. These EPA-estimated values served as dependent variables in the modeling process. The modeling framework followed a three-step strategy: (1) outlier detection using Rosner’s test to reduce the influence of outliers on model accuracy, (2) curve fitting with 12 regression models representing four curve types—polynomial (e.g., linear, quadratic), concave/convex (e.g., exponential, logarithmic), sigmoidal (e.g., logistic, Gompertz, Weibull), and spline-based (e.g., cubic spline, natural spline)—to capture diverse functional relationships between GT and emissions, and (3) model comparison using difference performance metrics to ensure a comprehensive assessment of predictive accuracy, consistency, and bias. The findings revealed that nonlinear models outperformed polynomial models, with spline-based models—particularly natural spline and cubic spline—providing superior accuracy for HC, PM₁₀, SO₂, and VOC, and the Weibull model showing strong predictive performance for CO and NO_x. These results underscore the necessity of using pollutant-specific and flexible modeling strategies to capture the intricacies of maritime emission dynamics. By demonstrating the advantages of flexible functional forms over standard regression techniques, this study highlights the need for tailored modeling strategies to better capture the complex relationships in maritime emission data and offers a scalable and transferable framework that can be extended to other vessel types, emission datasets, or maritime regions. Full article

Face recognition technology, despite its widespread use in various applications, still faces challenges related to occlusions, pose variations, and expression changes. Three-dimensional face recognition with depth information, particularly using point cloud-based networks, has shown effectiveness in overcoming these challenges. However, due to the limited extent of extensive 3D facial data and the non-rigid nature of facial structures, extracting distinct facial representations directly from point clouds remains challenging. To address this, our research proposes two key approaches. Firstly, we introduce a learning framework guided by a small amount of real face data based on morphable models with Gaussian processes. This system uses a novel method for generating large-scale virtual face scans, addressing the scarcity of 3D data. Secondly, we present a dual-branch network that directly extracts non-rigid facial features from point clouds, using kernel point convolution (KPConv) as its foundation. A local neighborhood adaptive feature learning module is introduced and employs context sampling technology, hierarchically downsampling feature-sensitive points critical for deep transfer and aggregation of discriminative facial features, to enhance the extraction of discriminative facial features. Notably, our training strategy combines large-scale face scanning data with 967 real face data from the FRGC v2.0 subset, demonstrating the effectiveness of guiding with a small amount of real face data. Experiments on the FRGC v2.0 dataset and the Bosphorus dataset demonstrate the effectiveness and potential of our method. Full article

Pier buildings along the coastline of Istanbul City, an ancient city surrounded by the sea on three sides, serve not only as vital transportation nodes but also as hubs for cultural and social life. As an embodiment of their respective topography and culture with distinctive characteristics in terms of location and architecture, the historical pier buildings are incorporated into the social, cultural, and historical fabric of the city. It is important to protect and preserve these buildings and develop sustainable tourism policies for sustainable cultural heritage management. Accordingly, the present study investigated 36 pier buildings in Istanbul using a comprehensive map analysis and on-site discovery. The study results suggested that these buildings preserved their authentic identities and spatial continuum, despite several renovations over time. Today, some of the pier buildings in Istanbul have additional functions, including serving as cafes, libraries, and sightseeing spots along with their transportation functions, contributing to the reinforcement of social interaction and social ties. The study results helped suggest key inferences on how these buildings should be preserved and carried into the future in the scope of urban planning. Full article

In this study, we employed a novel machine learning (ML) methodology to predict water levels (WLs) from their constituent components at both entrances of a sea strait, namely the Bosphorus. The principal components of WLs in the strait are mean sea level pressure (MSLP), wind speeds (W, U, V), discharges from the Danube River (Q), and tidal conditions (T). Following the application of the t-test, SFS, PCA, and VIF analyses, and the consideration of a range of ML techniques (including Linear Regression (LR), Regression Trees (RT), Support Vector Machine Regression (SVMR), Gaussian Process Regression (GPR), and Artificial Neural Networks (ANNs)), the number of predictors was reduced in order to obtain the most flexible and accurate regression model. As a consequence of this process, MSLP, W, and Q were retained, while the remaining variables (tide) were excluded. Furthermore, the order of importance for the optimal regression model was identified as Q_lagged, MSLP, V_lagged, and U at the north entrance model, while at the south entrance model, the order was MSLP, Q_lagged, U, and V. The models were trained using 80%, 50%, and 33% of the data, respectively. The model trained on 80% of the data yielded the most accurate predictions, with a correlation coefficient of R ≅ 0.95 and a root mean square error (RMSE) of 0.02 m. The model demonstrated a markedly superior predictive capacity compared to previous studies in the region, which is attributed to two factors that are regarded as the novelty of the study. The first factor was the random selection of training data from each month of the year, which allowed for the representation of the general pattern of water level (WL) behaviours. The second factor was the selection of the physically most meaningful inputs, which were selected according to the results of the significance and multicollinearity check. Furthermore, the predicted and measured WLs were employed as boundary conditions in a hydrodynamic model to evaluate the predictive capacity of the predicted WLs on the current results in the strait in comparison to the use of observed WLs. The 80% data-trained model exhibited similar current velocities to the observed WL model used, whereas the 50% and 30% data-trained models yielded slightly different results. Full article

This study introduces an innovative multichannel approach that focuses on the features and configurations of fingers in isolated sign language recognition. The foundation of this approach is based on three different types of data, derived from finger pose data obtained using MediaPipe and processed in separate channels. Using these multichannel data, we trained the proposed MultiChannel-MobileNetV2 model to provide a detailed analysis of finger movements. In our study, we first subject the features extracted from all trained models to dimensionality reduction using Principal Component Analysis. Subsequently, we combine these processed features for classification using a Support Vector Machine. Furthermore, our proposed method includes processing body and facial information using MobileNetV2. Our final proposed sign language recognition method has achieved remarkable accuracy rates of 97.15%, 95.13%, 99.78%, and 95.37% on the BosphorusSign22k-general, BosphorusSign22k, LSA64, and GSL datasets, respectively. These results underscore the generalizability and adaptability of the proposed method, proving its competitive edge over existing studies in the literature. Full article

Sign Language Recognition (SLR) systems are crucial bridges facilitating communication between deaf or hard-of-hearing individuals and the hearing world. Existing SLR technologies, while advancing, often grapple with challenges such as accurately capturing the dynamic and complex nature of sign language, which includes both manual and non-manual elements like facial expressions and body movements. These systems sometimes fall short in environments with different backgrounds or lighting conditions, hindering their practical applicability and robustness. This study introduces an innovative approach to isolated sign language word recognition using a novel deep learning model that combines the strengths of both residual three-dimensional (R3D) and temporally separated (R(2+1)D) convolutional blocks. The R3(2+1)D-SLR network model demonstrates a superior ability to capture the intricate spatial and temporal features crucial for accurate sign recognition. Our system combines data from the signer’s body, hands, and face, extracted using the R3(2+1)D-SLR model, and employs a Support Vector Machine (SVM) for classification. It demonstrates remarkable improvements in accuracy and robustness across various backgrounds by utilizing pose data over RGB data. With this pose-based approach, our proposed system achieved 94.52% and 98.53% test accuracy in signer-independent evaluations on the BosphorusSign22k-general and LSA64 datasets. Full article

Structural displacement monitoring is one of the major tasks of structural health monitoring and it is a significant challenge for research and engineering practices relating to large-scale civil structures. While computer vision-based structural monitoring has gained traction, current practices largely focus on laboratory experiments, small-scale structures, or close-range applications. This paper demonstrates its applications on three landmark long-span suspension bridges in Turkey: the First Bosphorus Bridge, the Second Bosphorus Bridge, and the Osman Gazi Bridge, among the longest landmark bridges in the world, with main spans of 1074 m, 1090 m, and 1550 m, respectively. The presented studies achieved non-contact displacement monitoring from a distance of 600 m, 755 m, and 1350 m for the respective bridges. The presented concepts, analysis, and results provide an overview of long-span bridge monitoring using computer vision-based monitoring. The results are assessed with conventional monitoring approaches and finite element analysis based on observed traffic conditions. Both displacements and dynamic frequencies align well with these conventional techniques and finite element analyses. This study also highlights the challenges of computer vision-based structural monitoring of long-span bridges and presents considerations such as the encountered adverse environmental factors, target and algorithm selection, and potential directions of future studies. Full article

Three-dimensional face recognition is an important part of the field of computer vision. Point clouds are widely used in the field of 3D vision due to the simple mathematical expression. However, the disorder of the points makes it difficult for them to have ordered indexes in convolutional neural networks. In addition, the point clouds lack detailed textures, which makes the facial features easily affected by expression or head pose changes. To solve the above problems, this paper constructs a new face recognition network, which mainly consists of two parts. The first part is a novel operator based on a local feature descriptor to realize the fine-grained features extraction and the permutation invariance of point clouds. The second part is a feature enhancement mechanism to enhance the discrimination of facial features. In order to verify the performance of our method, we conducted experiments on three public datasets: CASIA-3D, Bosphorus, and Lock3Dface. The results show that the accuracy of our method is improved by 0.7%, 0.4%, and 0.8% compared with the latest methods on these three datasets, respectively. Full article