• International conference on construction engineering and project management
• /
• 2022.06a
• /
• pp.814-822
• /
• 2022

The deployment of sensors for Structural Health Monitoring requires a complicated network arrangement, ground truthing, and calibration for validating sensor performance periodically. Any conventional sensor on a structural element is also subjected to static and dynamic vertical loadings in conjunction with other environmental factors, such as brightness, noise, temperature, and humidity. A structural model with strain gauges was built and tested to get realistic sensory information. This paper investigates different deep learning architectures and algorithms, including unsupervised, autoencoder, and supervised methods, to benchmark blind drift calibration methods using deep learning. It involves a fully connected neural network (FCNN), a long short-term memory (LSTM), and a gated recurrent unit (GRU) to address the blind drift calibration problem (i.e., performing calibrations of installed sensors when ground truth is not available). The results show that the supervised methods perform much better than unsupervised methods, such as an autoencoder, when ground truths are available. Furthermore, taking advantage of time-series information, the GRU model generates the most precise predictions to remove the drift overall.

• International conference on construction engineering and project management
• /
• 2020.12a
• /
• pp.443-452
• /
• 2020

Worker's awkward postures and unreasonable physical load can be corrected by monitoring construction activities, thereby increasing the safety and productivity of construction workers and projects. However, manual identification is time-consuming and contains high human variance. In this regard, an automated activity recognition system based on inertial measurement unit can help in rapidly and precisely collecting motion data. With the acceleration data, the machine learning algorithm will be used to train classifiers for automatically categorizing activities. However, input acceleration data are extracted either from designed experiments or simple construction work in previous studies. Thus, collected data series are discontinuous and activity categories are insufficient for real construction circumstances. This study aims to collect acceleration data during long-term continuous work in a construction project and validate the feasibility of activity recognition algorithm with the continuous motion data. The data collection covers two different workers performing formwork at the same site. An accelerator, as well as portable camera, is attached to the worker during the entire working session for simultaneously recording motion data and working activity. The supervised machine learning-based models are trained to classify activity in hierarchical levels, which reaches a 96.9% testing accuracy of recognizing rest and work and 85.6% testing accuracy of identifying stationary, traveling, and rebar installation actions.

• Korea Trade Review
• /
• v.46 no.4
• /
• pp.61-76
• /
• 2021

This study focuses on three logistics-related news (Logistics Newspaper, Korea Shipping Gadget, and Korea Shipping Newspaper) in order to present changes in logistics issues, centering on Corona 19, which has recently had the greatest impact in the world. For data collection, two-year news articles in 2019 and 2020 (title, article, content, date, article classification, article URL) were collected through web crawling (using Python's BeautifulSoup, requests module) on the homepages of three representative logistics-related media companies. As for the data analysis methods, fundamental statistical analysis, Latent Dirichlet Allocation (LDA) for topic modeling, and Scattertext were performed. The analysis results were as follows. First, among the three news media related to logistics, the Korea Shipping Newspaper was carrying out the most active media activities. Second, through topic modeling with LDA, eight logistics-related topics were identified, and keywords and significant issues of each topic were presented. Third, the keywords were visually expressed through Scattertext. This is the first study to present changes in the logistics field, focusing on articles from representative logistics-related media in 2019 and 2020. In particular, 2019 and 2020 can be divided into before and after the outbreak of Corona 19, which has had a great impact not only on the logistics field but also on our lives as a whole. For future work, a multi-faceted approach is required, such as comparative studies of logistics issues between countries or presenting implications based on long-term time-series articles.

• New & Renewable Energy
• /
• v.20 no.1
• /
• pp.102-109
• /
• 2024

The Typical Meteorological Year (TMY) dataset compiles 12 months of data that best represent long-term climate patterns, focusing on global horizontal irradiance and other weather-related variables. However, the irradiance measured on the plane of the array (POA) shows certain distinct distribution characteristics compared with the irradiance in the TMY dataset, and this may introduce some biases. Our research recalculated POA irradiance using both the Isotropic and DIRINT models, generating an updated dataset that was tailored to POA characteristics. Our analysis showed a 28% change in the selection of typical meteorological months, an 8% increase in average irradiance, and a 40% reduction in the range of irradiance values, thus indicating a significant shift in irradiance distribution patterns. This research aims to inform stakeholders about accurate use of TMY datasets in potential decision-making. These findings underscore the necessity of creating a typical dataset by using the time series of POA irradiance, which represents the orientation in which PV panels will be deployed.

• Journal of the Geological Society of Korea
• /
• v.54 no.5
• /
• pp.529-544
• /
• 2018

Dongrae hot spring belongs to the residual magma type and has a long history of bathing since the Silla dynasty in Korea. Due to long development of hot spring water, it is expected that the amount of hot spring water in Dongrae hot spring has been changed. In this study, long-trem water level data of Dongrae hot spring were examined for recognizing the change of the hot spring. By the fluctuation analysis of the hot spring water level from January 1992 to July 2018, the maximum and minimum annual drawdowns of no. 27 well were 137.70 and 71.60 meters, respectively, with an average drawdown of 103.39 m. On the other hand, the maximum and minimum annual drawdowns of no. 29 well were 137.80 and 71.70 meters, with an average drawdown of 103.49 m. Besides, drawdown rate became bigger in recent years. As a result of analyzing autocorrelation of the two wells, the correlation coefficient ranged from 0.919 to 0.991, showing seasonal groundwater level fluctuation. The cross correlation analysis between water level and precipitation as well as water level and hot spring discharge resulted in the correlation coefficients of -0.280 ~ 0.256 and 0.428 ~ 0.553, respectively. Therefore, using Dongnae hot-spring water level data from 1992 to 2018, the Mann-Kendall test and Sen's test showed that the continuous decline of water level was mainly caused by the pumping of the hot spring water among various reasons.

• Proceedings of the KSRS Conference
• /
• v.1
• /
• pp.150-152
• /
• 2006

The DISCOVER Project (${\underline{D}}istributed$ ${\underline{I}}nformation$ ${\underline{S}}ervices$ for ${\underline{C}}limate$ and ${\underline{O}}cean$ products and ${\underline{V}}isualizations$ for ${\underline{E}}arth$ ${\underline{R}}esearch$) is a NASA funded Earth Science REASoN project that strives to provide highly accurate, carefully calibrated, long-term climate data records and near-real-time ocean products suitable for the most demanding Earth research applications via easy-to-use display and data access tools. A key element of DISCOVER is the merging of data from the multiple sensors on multiple platforms into geophysical data sets consistent in both time and space. The project is a follow-on to the SSM/I Pathfinder and Passive Microwave ESIP projects which pioneered the simultaneous retrieval of sea surface temperature, surface wind speed, columnar water vapor, cloud liquid water content, and rain rate from SSM/I and TMI observations. The ocean products available through DISCOVER are derived from multi-sensor observations combined into daily products and a consistent multi-decadal climate time series. The DISCOVER team has a strong track record in identifying and removing unexpected sources of systematic error in radiometric measurements, including misspecification of SSM/I pointing geometry, the slightly emissive TMI antenna, and problems with the hot calibration source on AMSR-E. This in-depth experience with inter-calibration is absolutely essential for achieving our objective of merging multi-sensor observations into consistent data sets. Extreme care in satellite inter-calibration and commonality of geophysical algorithms is applied to all sensors. This presentation will introduce the DISCOVER products currently available from the web site, http://www.discover-earth.org and provide examples of the scientific application of both the diurnally corrected optimally interpolated global sea surface temperature product and the 4x-daily global microwave water vapor product.

• Proceedings of the Korean Geotechical Society Conference
• /
• 2006.03a
• /
• pp.1046-1053
• /
• 2006

In the large scale recent reclaiming works performed within the wide spatial boundary, evaluation of long-term consolidation settlement and residual settlement of the whole construction area is sometimes made with the results of the limited ground investigation and measurement. Then the reliability of evaluation has limitations due to the spatial uncertainty. Additionally, in case of large scale deep excavation works such as urban subway construction, there are a lot of hazardous elements to threaten the safety of underground pipes or adjacent structures. Therefore it is necessary to introduce a damage prediction system of adjacent structures and others. For the more accurate analysis of monitoring information in the wide spatial boundary works and large scale urban deep excavations, it is necessary to perform statistical and spatial analysis considering the geographical spatial effect of ground and monitoring information in stead of using diagrammatization method based on a time-series data expression that is traditionally used. And also it is necessary that enormous ground information and measurement data, digital maps are accumulated in a database, and they are controlled in a integrating system. On the abovementioned point of view, we developed Geomonitor 2.0, an Internet based real time monitoring program with a new concept by adding GIS and geo-statistical analysis method to the existing real time integrated measurement system that is already developed and under useful use. The new program enables the spatial analysis and database of monitoring data and ground information, and helps the construction- related persons make a quick and accurate decision for the economical and safe construction.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.66 no.7
• /
• pp.1066-1071
• /
• 2017

Recently high voltage impulse (HVI) technique has been extensively studied for desalting processes to control the $CaCO_3$ scale formation in industrial water practices such as power plant, boiler, and heat exchange operations. Investigation of the operational parameters for the HVI is important, however, those had not been reported yet. In this study, the effect of initial feed volume and contact time on reduction of calcium ion concentration by the HVI technique was investigated. Initial feed volumes of artificial hard water which contained 100 mg/L of $Ca^{2+}$, were set to 1, 2, and 3 L respectively. After 24hr of HVI contact with 12kV, $Ca^{2+}$ ion was reduced to 50, 29 and 19 % of their initial concentration, indicating that calcium removal increased as initial feed volume decreased. This implies the applied HVI pulse energy per unit mass of calcium is important parameter determining overall desalting efficiency. A series of extended operations of HVI up to 30 days verified the long term stability of the HVI system. The calcium ion declined to 40 mg/L after 2~3 days, and further reduction of calcium was not achieved, indicating that optimum operation time could be 2~3 days under these experimental conditions. Consequently, it was confirmed that the important operational parameter of HVI technique is initial feed volume and contact time as well as the applied voltage that was already proven in the previous study.

• Journal of Cadastre & Land InformatiX
• /
• v.50 no.1
• /
• pp.125-141
• /
• 2020

This study investigated the time-series relationship between housing consumer sentiment and housing prices in the five major districts in Seoul and also analyzed the effect of the housing consumer sentiment on housing prices using Granger Causality and VEC (Vector Error Correction) models. To describe the key results, first of all, housing consumer sentiment and regional housing market prices were closely related to each other, and the consumer sentiment strongly affected the change of housing prices. Second, the housing consumer sentiment was confirmed to have a discriminatory effect on the housing prices among the districts in Seoul in the short term. Specifically, the housing price of the east southern district (ESD) was the main reason for the change in housing consumer sentiment in Seoul, and that the resulting impact was transferred to other districts. Third, it was analyzed that regions other than the ESD would increase the housing prices in the long term as the housing consumer sentiment turned positive, but that the ESD would see a steady tone. Fourth, in the case of relative influence by district, housing (apartment) price fluctuation in a district was generally found to be most affected by adjacent or competitive districts. Through these findings, this study confirmed that there is a clear causality between housing consumer sentiment and housing prices in each district of Seoul and that there is a discriminatory influence on housing consumer sentiment among the districts.

• International Commerce and Information Review
• /
• v.13 no.3
• /
• pp.377-401
• /
• 2011

Under the WTO system, direct export support system that provides financial and tax related support is altogether prohibited. This presented an obstacle in strengthening competitiveness of Korean export business and in increasing exports continuously. One of the methods used to solve this problem was to actively leverage export insurance. In Korea, export insurance services have been conducted by the Korea Trade Insurance Corporation (k-sure) to promote export. Korea has been among the world's active users of the export insurance system. Given this situation, this paper examines the effectiveness of the Korea export insurance system in the promotion of export. In particular, this study analyzed about discriminating effects of the export insurance on the export of big and small-medium business. In order to analyze, We introduce a Export Supply Function model. In this paper, We construct two model. The one is about big business, the other is small-medium business. For empirical analysis, unit-root test was conducted to understand the safety of time series. The results show that all variables are not I(0) time series. Instead, they are I(1) time series. To this, cointegration verification was conducted based on the use of Johansen verification method to define the existence (or non-existence) of long-term balance relationship among variables. The results come out as follows. The export insurance of big business has a stronger effect on export than that of small-medium business. The cause of these results is due to the distinct structure of Korea industries. In view of the fact that the insurance can make the risk decreased. We can say that the export insurance affects the export of a high-risk country.