• 한국ITS학회:학술대회논문집
• /
• 2002.11a
• /
• pp.161-164
• /
• 2002

• Journal of information and communication convergence engineering
• /
• v.21 no.4
• /
• pp.346-350
• /
• 2023

Trajectory prediction is an essential element for driving autonomous vehicles, and various trajectory prediction models have emerged with the development of deep learning technology. Convolutional neural network (CNN) is the most commonly used neural network architecture for extracting the features of visual images, and the latest models exhibit high performances. This study was conducted to identify an efficient CNN backbone model among the components of deep learning models for trajectory prediction. We changed the existing CNN backbone network of multiple-trajectory prediction models used as feature extractors to various state-of-the-art CNN models. The experiment was conducted using nuScenes, which is a dataset used for the development of autonomous vehicles. The results of each model were compared using frequently used evaluation metrics for trajectory prediction. Analyzing the impact of the backbone can improve the performance of the trajectory prediction task. Investigating the influence of the backbone on multiple deep learning models can be a future challenge.

• Journal of Environmental Impact Assessment
• /
• v.14 no.1
• /
• pp.25-36
• /
• 2005

Actually, prediction formula of road traffic noise for EIA(Environmental Impact Assessment) has been used that proposed by National Institute of Environmental Research in 1999. The prediction formula, however, was calculated predicted noise level according to noise level producing on first floor, then needs to correct noise level at each floor in the case of apartment building. The investigation was carried out to calculate the correction coefficient for commonly using in EIA of large scaled apartment development areas. The noised level at each floor were measured from August 2001 to March 2002 at 31 investigation points of large scaled apartment development area in national wide. Measured data were divided and treated with 4 types as 3th floor, 5th floor, 7th floor and 10th floor and then the correction coefficients of each floor were calculated using by correlation formula according to each floor.

• Journal of Mechanical Science and Technology
• /
• v.20 no.8
• /
• pp.1101-1117
• /
• 2006

In the present article, recent progress of spray-wall interaction research has been reviewed. Studies on the spray-wall interaction phenomena can be categorized mainly into three groups: experiments on single drop impact and spray (multiple-drop) impingement, and development of comprehensive models. The criteria of wall-impingement regimes (i.e., stick, rebound, spread, splash, boiling induced breakup, breakup, and rebound with breakup) and the post-impingement characteristics (mostly for splash and rebound) are the main subjects of the single-drop impingement studies. Experimental studies on spray-wall impingement phenomena cover examination of the outline shape and internal structure of a spray after the wall impact. Various prediction models for the spray-wall impingement phenomena have been developed based on the experiments on the single drop impact and the spray impingement. In the present article, details on the wall-impingement criteria and post-impingement characteristics of single drops, external and internal structures of the spray after the wall impact, and their prediction models are reviewed.

• Atmosphere
• /
• v.33 no.2
• /
• pp.73-104
• /
• 2023

Over the past 60 years, Korean numerical weather prediction (NWP) has advanced rapidly with the collaborative effort between the science community and the operational modelling center. With an improved scientific understanding and the growth of information technology infrastructure, Korea is able to provide reliable and seamless weather forecast service, which can predict beyond a 10 days period. The application of NWP has expanded to support decision making in weather-sensitive sectors of society, exploiting both storm-scale high-impact weather forecasts in a very short range, and sub-seasonal climate predictions in an extended range. This article gives an approximate chronological account of the NWP over three periods separated by breakpoints in 1990 and 2005, in terms of dynamical core, physics, data assimilation, operational system, and forecast application. Challenges for future development of NWP are briefly discussed.

• Journal of the Korean Society of Environmental Restoration Technology
• /
• v.26 no.3
• /
• pp.43-55
• /
• 2023

The railway project is an essential green transportation tool that is considered suitable for the domestic and foreign policy direction of carbon neutrality, but there are some limitations, such as damaging important carbon absorption sources during construction. This study analyzed the environmental impact assessment related to carbon absorption sources of greenhouse gas evaluation items conducted during the railway project, and limitations and implications were derived. The analysis of environmental impact assessment guidelines related to railway projects and carbon absorption sources dealt with prediction and reduction methods related to carbon absorption sources, but guidelines, including environmentally friendly railway construction guidelines, lacked descriptions. Since the greenhouse gas environmental impact assessment, 83 railway project environmental impact assessments have been reviewed, but in some cases, carbon absorption-related predictions have not been implemented, or carbon absorption-related reduction measures have been insufficient. In addition, there were cases where there was a limit to calculating emissions and reduction or where the reduction value was insignificant compared to emissions. In order to supplement the environmental impact assessment in the field of carbon absorption sources related to railway construction projects, alternatives such as quantitative emission and low reduction calculation, review of the no net loss system using the total environmental resource system, and linkage with climate change impact assessment are needed.

• Journal of Ocean Engineering and Technology
• /
• v.9 no.1
• /
• pp.47-56
• /
• 1995

This study is aimed to have a database of system development for the prediction, monitoring, analyzing, and evaluation of tensile strength and damage characteristics through AE technique for CFRP. Therefore the correlations between impact characteristics (such as impact velocity, impact energy, delamination area etc) and AE signals for CFRP laminates were investigated. And also it were accomplished the evaluation of tensile strength and the investigation on correlation with AE signals for impact damaged specimen of CFRP laminates.

• Atmosphere
• /
• v.30 no.2
• /
• pp.141-154
• /
• 2020

Seasonal forecast is growing in demand, as it provides valuable information for decision making and potential to reduce impact on weather events. This study examines how operational climate prediction systems can be reliable, producing the probability forecast in seasonal scale. A reliability diagram was used, which is a tool for the reliability by comparing probabilities with the corresponding observed frequency. It is proposed for a method grading scales of 1-5 based on the reliability diagram to quantify the reliability. Probabilities are derived from ensemble members using hindcast data. The analysis is focused on skill for 2 m temperature and precipitation from climate prediction systems in KMA, UKMO, and ECMWF, NCEP and JMA. Five categorizations are found depending on variables, seasons and regions. The probability forecast for 2 m temperature can be relied on while that for precipitation is reliable only in few regions. The probabilistic skill in KMA and UKMO is comparable with ECMWF, and the reliabilities tend to increase as the ensemble size and hindcast period increasing.

• Atmosphere
• /
• v.31 no.3
• /
• pp.283-294
• /
• 2021

An Observing System Experiment (OSE) using Global Ocean Data Assimilation and Prediction System (GODAPS) was conducted to evaluate the assimilation impact of Argo floats, deployed by National Institute of Meteorological Sciences/Korea Meteorological Administration (NIMS/KMA), in marginal seas around Korean peninsula. A data denial experiment was run by removing Argo floats in the Yellow Sea and the East Sea from an operational run. The assimilation results show that Argo floats bring the positive impact on the analysis of ocean internal structure in both Yellow Sea and East Sea. In the East Sea, overall positive impact in the water temperature and salinity context is found, especially outstanding improvement from 300 to 500 m depth. In the Yellow sea, the assimilation impact on water temperature and salinity is also large within 50 m depth, especially greater impact than the East Sea in salinity. However, in the Yellow Sea, the influence of Argo floats tends to be restricted to the vicinity of Argo floats, because there was only one Argo float in the middle of the Yellow Sea during the experiment period. Given that the only limited number of Argo floats generally contribute in a positive way to the improvement of the GODAPS, further progress could be expected with adding more observations from Argo floats to current observing systems.

• Journal of Electrical Engineering and Technology
• /
• v.9 no.5
• /
• pp.1739-1745
• /
• 2014

Prediction of fault-prone modules continues to attract researcher's interest due to its significant impact on software development cost. The most important goal of such techniques is to correctly identify the modules where faults are most likely to present in early phases of software development lifecycle. Various software metrics related to modules level fault data have been successfully used for prediction of fault-prone modules. Goal of this research is to predict the faulty modules at design phase using design metrics of modules and faults related to modules. We have analyzed the effect of pre-processing and different machine learning schemes on eleven projects from NASA Metrics Data Program which offers design metrics and its related faults. Using seven machine learning and four preprocessing techniques we confirmed that models built from design metrics are surprisingly good at fault proneness prediction. The result shows that we should choose Naïve Bayes or Voting feature intervals with discretization for different data sets as they outperformed out of 28 schemes. Naive Bayes and Voting feature intervals has performed AUC > 0.7 on average of eleven projects. Our proposed framework is effective and can predict an acceptable level of fault at design phases.