Serkan Tapkın

In this study, machine learning, deep learning and transfer learning-based approaches have been compared to determine the presence of pavement cracks of the airport runway using a total of 4032 images captured by an unmanned aerial vehicle. In the machine learning approach, Local Binary Pattern, Grey-Level Co-occurrence Matrix, and Histogram of Oriented Gradient are used for feature extraction. For classification, k-Nearest Neighbours and Support Vector Machine are used. Among them, the best performance (82.96%) is achieved whenever the Grey-Level Co-occurrence Matrix and k-Nearest Neighbours combination is used. The convolutional neural network approach gives 83.89% accuracy, which is higher than the machine learning approach. Maximum accuracy is achieved when the convolutional neural network trained with 6-layer blocks, which corresponds to 24 layers in total. In the transfer learning approach, among the nine pretrained models evaluated, VGG-19 achieved the highest validation accuracy under the evaluated runway-specific validation setting, with an accuracy of 90.09%, a precision of 96.63%, a recall of 90.52%, and an F1-score of 93.47%. This study indicates that it is possible to detect the cracks on flexible airport pavements using images captured from an unmanned aerial vehicle, with an F1-score of approximately 93%.

Unmanned aerial vehicles are extensively utilized for image acquisition in a cheap, fast, and effective way. In this study, an automatic crack detection method with non-crack object removal and deep learning-based approaches are developed and tested on images captured by unmanned aerial vehicle. The motivation of this study is to detect either a crack exists or not in the asphalt-runway. The novelty of this study lies in integrating a non-crack artifact removal process with six classical edge detectors and comparing the resulting performance with four lightweight CNN models on the same UAV-acquired runway image dataset, enabling a unified evaluation of classical and learning-based approaches. For deep learning-based approach, four lightweight CNN models, namely GoogleNet, SqueezeNet, MobileNetv2, and ShuffleNet, are trained and the best accuracy of %87.9 is obtained whenever GoogleNet model is used. For the non-crack object removal approach, exclusion of non-crack objects from the images is the first step, where crack-detection which makes use of edge-detection techniques is the latter. In the study, Sobel, Prewitt, Canny, Laplacian of Gaussian, Roberts and Zero Cross edge detection algorithms are examined and their success rates in detecting cracks are comparatively presented. With sensitivity=0.981, specificity=0.744, accuracy=0.917, precision=0.912 and F-score=0.945 values Canny algorithm performs significantly better than others in detecting the cracks. This study provides enough evidence for the practicability of automated crack detection on unprocessed digital photographs by the results of the study conducted on asphalt runway.

This article presents an investigation of the structural behavior of a masonry arch bridge in Turkey. An analytical study has been conducted to provide the geometry of the structure, using laser scanning. A point cloud describing the geometry was obtained and properly transformed into a format that is appropriate for structural analysis software (CAE). Then, nonlinear finite-element models were developed to simulate structural responses of the bridge. The goal of the article is to highlight the influence of both continuum and discrete approaches and related constitutive laws on the responses of the bridge. Thus, continuum damage laws and a discrete model consisting of unilateral contact–friction interfaces were developed. Different load cases were tested and a comparison between the results obtained from the different approaches was considered. The failure mechanisms and the ultimate strengths were derived, and core points of the models were highlighted. The output of this work shows how the different failure models predict the behavior of the masonry arches. It also shows that the three-hinge mechanism, which has been depicted in classical studies for single-span arch masonry bridges under a horizontal settlement of supports, may also be obtained for multiarch bridges. Similarly, downward, vertical settlement of supports may result in the development of two hinges, as in single-span arches. Finally, the beneficial influence of the backfill in limiting the failure in the arch is addressed.

Due to the complex structure of observation based traffic accident data and the absence of an analytic model to define their characteristics, different models are required. Accident characteristics have been modeled for different road segments with two different methods: evolutionary data clustering method and resilient neural networks. In the first method, observation data was clustered using an evolutionary search-based clustering algorithm. The first method is based on determining whether observation based test data have the conditions of a possible death or injury accident based on the distance to the cluster centers obtained. The second one is a regression method that predicts whether an accident will cause death or injury according to observation based traffic data in test road segments by using resilient neural networks. Experiment results show that data analysis methods are very effective in determining the existence of the conditions that may cause accidents resulting in death or injury.

Location selection for offshore wind farms is a major challenge for renewable energy policy, marine spatial planning, and environmental conservation. This selection constitutes a multi-criteria decision-making problem, through which parameters like wind velocity, water depth, shorelines, fishing areas, shipping routes, environmental protection areas, transportation, and military zones should be jointly investigated. The aim of the present study was thus to develop an integrated methodology for assessing the siting of bottom-fixed offshore wind farms in two different countries (with different legal, political, and socio/economic characteristics). Our methodology combined multi-criteria decision-making methods and geographical information systems and was implemented in Cyclades (Greece) and in the sea area of İzmir region (Turkey). Experts used fuzzy sets and linguistic terms to achieve more consistent and independent rankings and results. In the Turkish region, the results showed that 519 km² (10.23%) of the study area is suitable for offshore wind farms, while in the Greek region, only 289 km² (3.22%) of the study area was found to be suitable. This spatial suitability analysis may contribute to provide some useful recommendations for the spatial marine planning at the regional scale, as well as for the preliminary assessment of new offshore wind farms in both countries.

The motivation of this research, development, demonstration, deployment, and diffusion (RD³&D) study is to present the progress of designing the GIS-based location selection module of autonomous investment decision support system and its experimental application for photovoltaic power plants (PVPPs) in Antalya, Burdur, and Isparta planning region Turkey. The other motivation of this RD³&D study is to start investigating in combinations the applicability and usability of weighted linear combination with 4 subjective weighting approaches (rank sum weight method (RS), inverse or reciprocal weights method (RR), rank order centroid (ROC), point allocation (PA)) for 5 main criteria, 14 sub-criteria, and 79 value ranges. The results show that 38.48% of the planning region is unsuitable, 61.52% is suitable. Only 2.07% of this region is very highly suitable according to RS. 7.13%, 9.22%, and 5.58% are respectively very highly suitable according to RR, ROC, and PA. Similarities between RS, RR, ROC, and PA methods are presented such as RS-RR: 0.7834, RS-ROC: 0.8510, and RS-PA: 0.6384 with covariance and correlation analysis. A backward-looking performance verification and validation analysis is also performed with 7 PVPPs for only 4 decisive success factors (capacity factor, annual energy/land use, project cost/capacity, project cost/energy). This study is thus able to evaluate the optimal locations for future investments, as well as the suitability conditions of the available investments. This study will contribute to provide some useful recommendations for decision makers to identify and assess the hotspots which are suitable for PVPPs in the planning region.