• Smart Structures and Systems
• /
• v.31 no.4
• /
• pp.311-323
• /
• 2023

Ever since ancient times, earthquakes have been a major threat to the civil infrastructures and the safety of human beings. The majority of casualties in earthquake disasters are caused by the damaged civil infrastructures but not by the earthquake itself. Therefore, the efficient and accurate post-earthquake assessment of the conditions of structural damage has been an urgent need for human society. Traditional ways for post-earthquake structural assessment rely heavily on field investigation by experienced experts, yet, it is inevitably subjective and inefficient. Structural response data are also applied to assess the damage; however, it requires mounted sensor networks in advance and it is not intuitional. As many types of damaged states of structures are visible, computer vision-based post-earthquake structural assessment has attracted great attention among the engineers and scholars. With the development of image acquisition sensors, computing resources and deep learning algorithms, deep learning-based post-earthquake structural assessment has gradually shown potential in dealing with image acquisition and processing tasks. This paper comprehensively reviews the state-of-the-art studies of deep learning-based post-earthquake structural assessment in recent years. The conventional way of image processing and machine learning-based structural assessment are presented briefly. The workflow of the methodology for computer vision and deep learning-based post-earthquake structural assessment was introduced. Then, applications of assessment for multiple civil infrastructures are presented in detail. Finally, the challenges of current studies are summarized for reference in future works to improve the efficiency, robustness and accuracy in this field.

• Spatial Information Research
• /
• v.22 no.4
• /
• pp.59-65
• /
• 2014

Recently, increasing demand for 'Digital Elevation Model(DEM)' to climate change research and various development by global warming in the Arctic region. So we need to verify the accuracy to utilize DEM. In this research, we verified 'ASTER GDEM' and 'GIMP DEM' in several DEM which constructed in the Greenland that most of the area is covered ice sheet. We divided greenland into two part, ice sheet area and non ice sheet area by using the ESA globcover. Then, comparing a difference between 'ASTER DEM', 'GIMP DEM' and ICESat elevation data to verify the accuracy. As a result, GIMP DEM has higher accuracy in ice sheet area and ASTER GDEM has higher accuracy in non-ice sheet area.

• Journal of Korean Society on Water Environment
• /
• v.32 no.6
• /
• pp.582-588
• /
• 2016

The hydrological simulation program FORTRAN (HSPF) is a comprehensive watershed model that employs the hydraulic function table (FTABLE) (depth-area-volume-flow relationship) to represent the geometric and hydraulic properties of water bodies. The hydraulic representation of the HSPF model mainly depends on the accuracy of the FTABLES. These hydraulic representations determine the response time of water quality state variables and also control the scour, deposition, and transport of sediments in the water body. In general, FTABLES are automatically generated based on reach information such as mean depth, mean width, length, and slope along with a set of standard assumptions about the geometry and hydraulics of the channel, so these FTABLES are unable to accurately describe the geometry and hydraulic behavior of rivers and reservoirs. In order to compensate the weakness of HSPF for hydraulic modeling, we generated alternate method to improve the accuracy of FTABLES for rivers, using the surveyed cross sections and rating curves. The alternative method is based on the hydraulics simulated by HEC-RAS using the surveyed cross sections and rating curves, and it could significantly improve the accuracy of FTABLES. Although the alternate FTABLE greatly improved the hydraulic accuracy of the HSPF model, it had little effect on the hydrological simulation.

• Journal of Korean Neurosurgical Society
• /
• v.56 no.1
• /
• pp.16-20
• /
• 2014

Objective : Two-dimensional fluoroscopy-based computerized navigation for the placement of pedicle screws offers the advantage of using stored patient-specific imaging data in providing real-time guidance during screw placement. The study aimed to describe the accuracy and reliability of a fluoroscopy-based navigation system for pedicle screw insertion. Methods : A total of 477 pedicle screws were inserted in the lower back of 96 consecutive patients between October 2007 and June 2012 using fluoroscopy-based computer-assisted surgery. The accuracy of screw placement was evaluated using a sophisticated computed tomography protocol. Results : Of the 477 pedicle screws, 461 (96.7%) were judged to be inserted correctly. Frank screw misplacement [16 screws (3.3%)] was observed in 15 patients. Of these, 8 were classified as minimally misplaced (${\leq}2mm$); 3, as moderately misplaced (2.1-4 mm); and 5, as severely misplaced (>4 mm). No complications, including nerve root injury, cerebrospinal fluid leakage, or internal organ injury, were observed in any of the patients. Conclusion : The accuracy of pedicle screw placement using a fluoroscopy-based computer navigation system was observed to be superior to that obtained with conventional techniques.

• Journal of the Korean Society of Environmental Restoration Technology
• /
• v.15 no.4
• /
• pp.111-118
• /
• 2012

The purpose of this study is to work out strategy for utilization of Environmental Conservation Value Assessment Map (ECVAM) using the user survey. It surveyed system users of ECVAM about its recognition and satisfaction. The results of the survey, the ECVAM became more popular and were highly satisfied with updated data. Especially, the study found a relationship between the satisfaction of ECVAM and accuracy, utilization, and convenience of the system. However, the satisfaction has a difference between user groups, a government official and a agent for EIA including researchers. The satisfaction of the agent group was affected by the convenience, the accuracy, and the utilization in order. In the other hand, the satisfaction of the government official group was affected by the utilization, the convenience, the accuracy, and recognition in order. Therefore, we need to adopt different strategies for educations of ECVAM and publicity activities depending on user groups. To increase the satisfaction of ECVAM, we should research not only to attain pinpoint accuracy, but also to suggest the guideline to utilize the map for a government official.

• Journal of Sasang Constitutional Medicine
• /
• v.24 no.3
• /
• pp.1-16
• /
• 2012

Objectives For the methodological review on the accuracy study of questionnaire for Sasang constitution diagnosis, we searched the various diagnostic accuracy study of the questionnaires for Sasang constitution. Methods We searched MEDLINE, the Cochrane Library, KISS, and DBPIA. Additionally, We hand-searched the main oriental medical journals. All articles were independently reviewed and selected by two evaluators. And selected articles were assessed by "Quality Assessment of Diagnostic Accuracy Studies Tool"(QUADAS Tool) for the methodological review. Results The twenty eight studies initially identified studies were included in the methodological review. The part of "Acceptable reference standard", "Uninterpretable results reported" and "Withdrawals explained" was very weak in the risk of bias. The part of "Representative spectrum", "Acceptable delay between tests", "Incorporation avoided", "Reference standard results blinded", "Index test results blinded" was unclear in the description. Conclusions For the further study on the accuracy study of Sasang constitution diagnosis, we have to improve the aforementioned errors. Additionally, the checklist for the description of study might be needed.

• Proceedings of the KSRS Conference
• /
• 2003.11a
• /
• pp.1152-1154
• /
• 2003

The needs of 3-D data have been increasing for various applications like visualization, 3-D modeling, planning and management as well as entertainment. Mobile mapping has become a quick and practical means for acquiring necessary 3-D data for above-mentioned applications. A mobile mapping system mainly consists of two main components, viz. data acquisition devices and positioning devices. The data acquisition devices consist of CCD cameras or/and laser scanners. The positioning devices consist of GPS, INS, Odometer (shaft encoder) and some other referencing devices. The overall accuracy of mobile mapping system depends on the accuracy of positioning devices and their integrated output. Though, GPS is the main input device for the position information, the signal is not available for the computation of position all the times in urban area. The GPS satellites are normally obstructed by high-rise buildings. Thus it is very important to understand the accuracy of such a system in different environments and means to solve such problems. We have developed a mobile mapping system called VLMS (Vehicle-borne Laser Mapping System), which consists of CCD Cameras, Laser scanners, GPS, INS and Odometer. In this paper, we will present and discuss the accuracy of this system with data acquired in different environments (open area, urban area, tunnel, express way etc) by analyzing the data with respect to other existing digital data.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2023.05a
• /
• pp.26-26
• /
• 2023

General circulation models (GCMs) are widely used in hydrological prediction, however their coarse grids make them unsuitable for regional analysis, therefore a downscaling method is required to utilize them in hydrological assessment. As one of the downscaling methods, convolutional neural network (CNN)-based downscaling has been proposed in recent years. The aim of this study is to generate the process of dynamic downscaling using CNNs by applying GCM output as input and RCM output as label data output. Prediction accuracy is compared between different input datasets, and model structures. Several input datasets with key atmospheric variables such as precipitation, temperature, and humidity were tested with two different formats; one is two-dimensional data and the other one is three-dimensional data. And in the model structure, the hyperparameters were tested to check the effect on model accuracy. The results of the experiments on the input dataset showed that the accuracy was higher for the input dataset without precipitation than with precipitation. The results of the experiments on the model structure showed that substantially increasing the number of convolutions resulted in higher accuracy, however increasing the size of the receptive field did not necessarily lead to higher accuracy. Though further investigation is required for the application, this paper can contribute to the development of efficient downscaling method with CNNs.

• Journal of Forest and Environmental Science
• /
• v.40 no.1
• /
• pp.15-23
• /
• 2024

This research aimed to assess the possibility of detecting forest degradation using time-series satellite imagery and three different deep learning-based change detection techniques. The dataset used for the deep learning models was composed of two sets, one based on surface reflectance (SR) spectral information from satellite imagery, combined with Texture Information (GLCM; Gray-Level Co-occurrence Matrix) and terrain information. The deep learning models employed for land cover change detection included image differencing using the Unet semantic segmentation model, multi-encoder Unet model, and multi-encoder Unet++ model. The study found that there was no significant difference in accuracy between the deep learning models for forest degradation detection. Both training and validation accuracies were approx-imately 89% and 92%, respectively. Among the three deep learning models, the multi-encoder Unet model showed the most efficient analysis time and comparable accuracy. Moreover, models that incorporated both texture and gradient information in addition to spectral information were found to have a higher classification accuracy compared to models that used only spectral information. Overall, the accuracy of forest degradation extraction was outstanding, achieving 98%.

• Journal of the Korean Society of Environmental Restoration Technology
• /
• v.14 no.1
• /
• pp.23-33
• /
• 2011

Habitats loss and fragmentation are major threats to biodiversity. There are various kinds of environmental assessment have been developed for various problems to solve. Yet, there are no well-developed methods for quantifying and predicting about biodiversity. To achieve a sustainable conservation for biodiversity, the structural diversity of forest must be assessed by proper indexes. This study aim to quantitatively assess the diversity of forest structure as habitats and results of the verification by bird survey for objective presentation of evidence. As a result of literature review, some indexes were selected as potential prediction tools for biodiversity; area of patch, area of core regions, shape of patch and average age of stand. The assessment results were estimated by monitoring of birds for accuracy verification and the results were almost in agreement with each others. But, 1 and 2 level of forests were showed ambiguous results. Certainly, this study was limited in some valuation indexes on landscape scale. Further studies should be considered that different environmental factors such as land use, disturbances by human and vegetation index. Also, we expect that the additional monitoring of birds should give rise to the result which is improved assessment results.