Search

Your search keyword '"Istrati, Denis"' showing total 25 results
Start Over Author "Istrati, Denis"
25 results on '"Istrati, Denis"'

2. Tsunami Runup Attenuation By Onshore Obstacles

Author

VAN BALEN, IVO, primary, CELS, JONAS, additional, ADAMS, KEITH, additional, BAIGUERA, MARCO, additional, ROSSETTO, TIZIANA, additional, ANTONINI, ALESSANDRO, additional, WÜTHRICH, DAVIDE, additional, ISTRATI, DENIS, additional, BULDAKOV, EUGENY, additional, CHANDLER, IAN, additional, and MCGOVERN, DAVID, additional

Published
2024
Full Text
View/download PDF

4. Vision Transformer for Flood Detection Using Satellite Images from Sentinel-1 and Sentinel-2.

Author

Chamatidis, Ilias, Istrati, Denis, and Lagaros, Nikos D.

Subjects
TRANSFORMER models, NATURAL language processing, SYNTHETIC aperture radar, IMAGE recognition (Computer vision), EMERGENCY management, REMOTE-sensing images
Abstract

Floods are devastating phenomena that occur almost all around the world and are responsible for significant losses, in terms of both human lives and economic damages. When floods occur, one of the challenges that emergency response agencies face is the identification of the flooded area so that access points and safe routes can be determined quickly. This study presents a flood detection methodology that combines transfer learning with vision transformers and satellite images from open datasets. Transformers are powerful models that have been successfully applied in Natural Language Processing (NLP). A variation of this model is the vision transformer (ViT), which can be applied to image classification tasks. The methodology is applied and evaluated for two types of satellite images: Synthetic Aperture Radar (SAR) images from Sentinel-1 and Multispectral Instrument (MSI) images from Sentinel-2. By using a pre-trained vision transformer and transfer learning, the model is fine-tuned on these two datasets to train the models to determine whether the images contain floods. It is found that the proposed methodology achieves an accuracy of 84.84% on the Sentinel-1 dataset and 83.14% on the Sentinel-2 dataset, revealing its insensitivity to the image type and applicability to a wide range of available visual data for flood detection. Moreover, this study shows that the proposed approach outperforms state-of-the-art CNN models by up to 15% on the SAR images and 9% on the MSI images. Overall, it is shown that the combination of transfer learning, vision transformers, and satellite images is a promising tool for flood risk management experts and emergency response agencies. [ABSTRACT FROM AUTHOR]

Published
2024
Full Text
View/download PDF

5. Safeguarding Our Heritage—The TRIQUETRA Project Approach

Author

Ioannidis, Charalabos, primary, Verykokou, Styliani, additional, Soile, Sofia, additional, Istrati, Denis, additional, Spyrakos, Constantine, additional, Sarris, Apostolos, additional, Akritidis, Dimitris, additional, Feidas, Haralambos, additional, Georgoulias, Aristeidis K., additional, Tringa, Efstathia, additional, Zanis, Prodromos, additional, Georgiadis, Charalampos, additional, Martino, Salvatore, additional, Feliziani, Federico, additional, Marmoni, Gian Marco, additional, Cerra, Daniele, additional, Ottinger, Marco, additional, Bachofer, Felix, additional, Anastasiou, Anastasia, additional, Charalampopoulou, Vasiliki (Betty), additional, Krebs, Patrick, additional, Mizaikoff, Boris, additional, Roulet, Jean-Christophe, additional, Bulliard, Xavier, additional, Dudnik, Gabriela, additional, and Anyfantis, George C., additional

Published
2024
Full Text
View/download PDF

9. Experimental datasets from large-scale shake table experiments on skew bridges

Author

Wu, Suiwen, Buckle, Ian, Itani, Ahmad, and Istrati, Denis

Abstract

These datasets are from shake table experiments conducted on a series of simply-supported, single-span bridge models with skew angles of 0º, 30º, 45º, and 60º. These experiments were conducted on one of the biaxial shake tables in the Earthquake Engineering Laboratory of the University of Nevada, Reno, from September to November 2015. A total of 876 experiments were performed to investigate the seismic performance of skew bridges. The following data are included in these datasets for each of the 876 experiments: • absolute acceleration (achieved motion) of shake table recorded by table system DAQ in longitudinal and transverse directions (quantity: 2 response histories) • relative displacement of superstructure in longitudinal and transverse directions at each corner (quantity: 8 response histories) • in-plane rotation (quantity: 1 response history) • relative normal displacement of superstructure at each corner (quantity: 4 response history) • impact force at each corner (quantity: 4 response histories) • absolute acceleration normal to and parallel with the abutment at each corner (quantity: 8 response histories) • absolute acceleration at center of mass of the superstructure (quantity: 2 response histories), and • absolute acceleration (achieved motion) of shake table recorded by an accelerometer on the table platen (quantity: 2 response histories). The sampling frequency for achieved table accelerations recorded by table system DAQ was 256 Hz. All other response data were recorded on a high-speed data acquisition system, which had a sampling frequency of 20,000 Hz.

Published
2022
Full Text
View/download PDF

10. Short-Term Forecasting of Rainfall Using Sequentially Deep LSTM Networks: A Case Study on a Semi-Arid Region.

Author

Chamatidis, Ilias, Tzanes, Georgios, Istrati, Denis, Lagaros, Nikos D., and Stamou, Anastasios

Subjects
RAINFALL, WEATHER forecasting, ARTIFICIAL neural networks, TRANSPORTATION, REGRESSION analysis
Abstract

Weather prediction is a key aspect of today's society and its activities. Accurate predictions are crucial for efficiently organizing human activities, particularly in the agricultural, transportation and energy sectors. In this paper, two deep neural networks, designed based on a long short-term memory architecture, are developed to predict the occurrence of rainfall events and the respective amount of rainfall on the island of Nisyros in the south Aegean Sea. Two deep neural networks are developed, serving two different learning tasks. The first network acts as a classifier that assesses whether it is going to rain or not and, sequentially, the second network performs a regression task, quantifying the anticipated amount of rainfall. The performance of such prediction models is highly dependent on input sequences. Among others, the lookback time window shapes those input sequences by determining the number of past time steps to be taken into account. The ideal time window for the classifier involves 24 time steps (i.e., 4 h), resulting in increased accuracy levels exceeding 96.45%. The predictions of the regression model, which has the same lookback time window, feature low errors, measured as 6.635 and 1.411 mm using the mean-square-error and mean-absolute-error indices, respectively. [ABSTRACT FROM AUTHOR]

Published
2023
Full Text
View/download PDF

25. Performance of Transportation Infrastructure During Kumamoto Earthquakes of April 14 and 16, 2016— A Reconnaissance Report

Author

United States. Department of Transportation. Federal Highway Administration. Office of Infrastructure Research and Development, Harris, Jamie, Bromenschenkel, Ron, Buckle, Ian G., Cuthbertson, Jim, Duwadi, Sheila Rimal, Istrati, Denis, Sanders, David H., Turner-Fairbank Highway Research Center, University of Nevada, Reno. Civil and Environmental Engineering, Washington (State). Department of Transportation, California. Department of Transportation, United States. Department of Transportation. Federal Highway Administration. Office of Infrastructure Research and Development, Harris, Jamie, Bromenschenkel, Ron, Buckle, Ian G., Cuthbertson, Jim, Duwadi, Sheila Rimal, Istrati, Denis, Sanders, David H., Turner-Fairbank Highway Research Center, University of Nevada, Reno. Civil and Environmental Engineering, Washington (State). Department of Transportation, and California. Department of Transportation

Abstract

DTFH61-07-00031, This report described a reconnaissance effort to document bridge performance during the Kumamoto earthquakes in Japan in April 2016. More than 180 bridges were damaged by these earthquakes. Of particular interest is the performance of bridges that were relatively new (15–20 yr old) or recently retrofitted. Damage sustained was significant and included bearing and shear key failures, distortion and local buckling of the steel superstructures, and foundation movement. Most of the damage could be attributed to extensive slope failures and intense shaking close to the causative fault. Recommendations for improving bridge performance in future earthquakes are given.

Catalog

Books, media, physical & digital resources
See catalog results