Mimarlık ve Şehir Planlama Bölümü, Bildiri & Sunum Koleksiyonu
Bu koleksiyon için kalıcı URI
Güncel Gönderiler
Öğe A novel dynamic path planning method td learning supported modified spatiotemporal gnn-lstm model on large urban networks(Springer Netherlands, 2025) Karaağaç, AbdullahIn this study, a new approach will be discussed in which routing is done by predicting future traffic and the learning algorithm is optimized during navigation. Traffic has a complex structure that is constantly changing. Especially for long-term travel, it is not an optimum approach to suggest a route only by considering the traffic situation at the time the navigation request is made. For this reason, the proposed algorithm recommends a route by taking into account future saturation conditions on the vehicle’s route. Singapore was chosen as the study area. The tests were carried out in a simulation environment. The four selected algorithms were tested spatially and temporally. Especially in long-term travels, the superior success of the proposed method compared to other selected methods has been demonstrated. © The Author(s) 2025.Öğe A feature-based deep learning approach for the extraction of ground points from 3d point clouds(Copernicus Gesellschaft Mbh, 2023) Doğan, Yusuf; Ok, A. O.; Altan, O.; Sunar, F.Extracting ground points from 3D point clouds is important for sustainable development goals, infrastructure planning, disaster management, and more. However, the irregularity and complexity of the data make it challenging. Deep learning techniques, particularly end-to-end and non-end-to-end approaches, have shown promise for 3D point cloud segmentation and classification, but both require a comprehensive understanding of the features and their relationship to the problem. This paper presents a study on the filtering of 3D LiDAR point clouds into ground and non-ground points using a non-end-to-end deep learning approach. The aim of this research is to investigate the effectiveness of utilizing geometric features and a binary classifier-based deep learning model in accurately classifying point clouds. The publicly available ACT benchmark datasets were employed for training, validation, and testing purposes. The study utilized a k-fold cross-validation method to address the limited availability of training data. The results demonstrated highly satisfactory performance, with validation averages reaching 96.83% for the divided Dataset-1 and an accuracy of 97% for the test set. Furthermore, an independent dataset, Dataset-2, was used to evaluate the generalizability of the trained model, achieving an accuracy of 93%. These findings highlight the potential of the proposed non-end-to-end approach to filtering point cloud data and its applicability in various domains such as DEM and DTM production, city modeling, urban planning, and disaster management. Moreover, this study emphasizes the need for accurate data to achieve sustainable development goals, positioning the proposed approach as a viable option in various studies.
