• International conference on construction engineering and project management
• /
• 2022.06a
• /
• pp.1243-1244
• /
• 2022

In recent years, the growing interest in off-site construction has led to factories scaling up their manufacturing and production processes in the construction sector. Consequently, continuous large-scale site monitoring in low-variability environments, such as prefabricated components production plants (precast concrete production), has gained increasing importance. Although many studies on computer vision-based site monitoring have been conducted, challenges for deploying this technology for large-scale field applications still remain. One of the issues is collecting and transmitting vast amounts of video data. Continuous site monitoring systems are based on real-time video data collection and analysis, which requires excessive computational resources and network traffic. In addition, it is difficult to integrate various object information with different sizes and scales into a single scene. Various sizes and types of objects (e.g., workers, heavy equipment, and materials) exist in a plant production environment, and these objects should be detected simultaneously for effective site monitoring. However, with the existing object detection algorithms, it is difficult to simultaneously detect objects with significant differences in size because collecting and training massive amounts of object image data with various scales is necessary. This study thus developed a large-scale site monitoring system using edge computing and a small-object detection system to solve these problems. Edge computing is a distributed information technology architecture wherein the image or video data is processed near the originating source, not on a centralized server or cloud. By inferring information from the AI computing module equipped with CCTVs and communicating only the processed information with the server, it is possible to reduce excessive network traffic. Small-object detection is an innovative method to detect different-sized objects by cropping the raw image and setting the appropriate number of rows and columns for image splitting based on the target object size. This enables the detection of small objects from cropped and magnified images. The detected small objects can then be expressed in the original image. In the inference process, this study used the YOLO-v5 algorithm, known for its fast processing speed and widely used for real-time object detection. This method could effectively detect large and even small objects that were difficult to detect with the existing object detection algorithms. When the large-scale site monitoring system was tested, it performed well in detecting small objects, such as workers in a large-scale view of construction sites, which were inaccurately detected by the existing algorithms. Our next goal is to incorporate various safety monitoring and risk analysis algorithms into this system, such as collision risk estimation, based on the time-to-collision concept, enabling the optimization of safety routes by accumulating workers' paths and inferring the risky areas based on workers' trajectory patterns. Through such developments, this continuous large-scale site monitoring system can guide a construction plant's safety management system more effectively.

• Journal of Korean Society for Atmospheric Environment
• /
• v.23 no.3
• /
• pp.286-296
• /
• 2007

Ozone creation potentials suited for Seoul metropolitan area was derived by utilizing the PAMS monitoring data and the source inventory. A simple box model with variable height was developed to calculate the incremental reactivity for all the ozone episode days in the year 2003 and 2004. RIR (Relative Incremental Reactivity) was introduced as a measure of contribution to ozone generation in the Seoul metropolitan area. RIR was defined as a function of ratio of VOC to $NO_x$ and therefore it addresses both VOC and $NO_x$ limited regime. For the days that more than 10 monitoring stations out of 27 monitoring station in Seoul recorded the daily maximum ozone concentrations higher than 70 ppb, toluene had the highest RIR value in all the type II and type III PAMS site and m/p-xylene followed with the second highest RIR value. Analyses using MIR (Maximum Incremental Reactivity) and POCP (Photochemical Ozone Creation Potential) instead of RIR also yields dominance of toluene and m/p-xylene in generating ozone concentrations to demonstrate the validity of RIR.

• The Bulletin of The Korean Astronomical Society
• /
• v.38 no.2
• /
• pp.77.2-77.2
• /
• 2013

We present the interim results of simultaneous time monitoring observations of $^{28}SiO$ v = 1, 2, J = 1-0, $^{29}SiO$ v = 0, J = 1-0 and $H_2O$ $6_{16}-5_{23}$ maser lines toward 10 known water fountain sources at a post-AGB stage. The observations have been carried out from 2009 June to 2013 September using the 21m single dish radio telescopes of the Korean VLBI Network. From six sources, we detected well separated red- and blue-shifted $H_2O$ maser features with large velocity ranges more than 100 km $s^{-1}$. From four sources, we detected red- and/or blue-shifted $H_2O$ maser features depended on observational epochs. However, we could not detected SiO maser emission from any sources and any epochs. For a representative water fountain source W43A, we obtained $H_2O$ maser spectra at 17 epochs which show a clear bipolar and discontinuous mass ejections. They also showed a periodic change between red-shifted and blue-shifted peaks. However, we need a more regular and short-time interval monitoring observations in order to fix the period and peak intensity variation interval.

• Magazine of the Korean Society of Agricultural Engineers
• /
• v.39 no.2
• /
• pp.113-123
• /
• 1997

This study was initiated to build runoff plots, install soil and water quality monitoring systems and collect background data from the plots and neighboring soils as the 1st year study of a 5 year project to assess soil quality and develop the management practices for environmentally sound agriculture in mountainous soils. Eleven $3{\times}15m$ runoff plots and monitoring systems were installed at a field of National Alpine Agricultural Experiment Station to monitor soil quality and discharge of nonpoint source pollutants. Corn and potato were cultivated under different fertilizer, tillage and residue cover treatments. The soil has a single-layered cluster structure that has a relatively good hydrologic properties and can adsorb a large amount of nutrient. Concentrations of T-N, $NH_4$-N, and $NO_3$-N of surface soil sampled in the winter were relatively high. Runoff quality in the winter and thawing season in the spring was largely dependent on surface freezing, snow accumulation, temperature, surface thawing depth and so on. Runoff during the thawing season caused serious soil erosion but runoff quality during the winter was relatively good. Serious wind erosion from unprotected fields after the fall harvest were obserbed and best management practices to reduce the erosion need to be developed.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2017.04a
• /
• pp.673-676
• /
• 2017

Accompanying the Internet of Things (IoT) is a demand of advanced applications and services utilizing the potential of the IoT environment. Monitoring the environment for a provision of context-aware services to the human beings is one of the new trends in our future life. The IoTivity Cloud is one of the most notable open-source platform bringing an opportunity to collect, analyze, and interpret a huge amount of data available in the IoT environment. Based on the IoTivity Cloud, we aim to develop a novel platform for comprehensive monitoring of a future network, which facilitates on-demand data collection to enable the network behavior prediction and the quality of user experience maintenance. In consideration of performance evaluation of the monitoring platform, this paper presents results of a preliminary test on the data acquisition/supply process in the IoTivity Cloud.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.59 no.9
• /
• pp.1549-1559
• /
• 2010

Modern power system is operated and managed in closed network environment with treating a great variety of data, and requirement of real time power system data is more increasing. However, it is difficult for operators to fast evaluate the condition of power system using only isolation network system such as SCADA or EMS regarding unexpecting situations occurring. Recent technology achievement in areas of distributed computing, networking high speed communications and digital control as well as the availability of accurate GPS time source are rapidly becoming the enabling factors for the development of a new generation of real time power grid monitoring tools. In this paper, architecture of WAMAC which is the wide area monitoring and control system not only to control but also to monitoring in real time is proposed and the plan of integration interface with legacy system such as EMS for providing power system analysis base data effectively is suggested.

• Journal of the Korean Society of Hazard Mitigation
• /
• v.7 no.4
• /
• pp.107-113
• /
• 2007

The Kuem-River, one of the largest rivers in Korea, is the primary water source for more than 4 million people in Kongju city and surrounding area. To study the effect of stormwater runoff to CSOs, twelve monitoring sites were selected in two large cities (City of Kongju and City of Buyeo) near the Kuem-River. Monitoring was reformed by collecting grab samples, measuring flow rates during dry and wet seasons during over two rainy seasons. Generally the flow rate of wastewater in combined sewers was rapidly decreased after 23:00 P.M. and gradually increased from 06:30 A.M. in all sites during the dry season. The concentrations of pollutant increase approximately 5 to 7 fold for TSS and 1.5 to 2.5 fold for BOD during the rainy season. Monitoring and statistical analysis show that the groundwater contributes on sewage volume increase (average 25-45% more) during dry periods and the stormwater runoff contributes approximately 51-72% increase during rainy periods. Generally the concentrations of combined sewage were more polluted during the first flush period than after the first flush during a storm event.

• Journal of Welding and Joining
• /
• v.28 no.6
• /
• pp.51-57
• /
• 2010

Fiber laser is a heat source which is introduced recently, and so has a little researched data compare with conventional laser processing. Moreover basic data for welding monitoring are also insufficient. Therefore, in this study, the change of signal with measuring position and angle of plasma emission signals were analysed as a basic experiment for real time monitoring in fiber laser welding. As a result, the signals measured from the side, front and rear had the biggest intensity at $60^{\circ}$, and frequency peak to reflect the behavior of keyhole and swing of plasma by shield gas was detected at $45{\sim}60^{\circ}$. However, both intensity of signal and the result of FFT for monitoring were satisfied at the angle of $45^{\circ}$ from the side.

• The Bulletin of The Korean Astronomical Society
• /
• v.39 no.2
• /
• pp.60.1-60.1
• /
• 2014

In the center of an Active Galactic Nuclei(AGN) is a supermassive black hole which accretes matter from its surroundings. The radio-loud AGN launch two relativistic jets perpendicular to the accretion disk which terminates into radio lobes located up to megaparsec away. Blazars form a small subset of radio-loud AGNs with one of two relativistic jets pointing toward the observer's line of sight. Many blazars often show flares at different frequencies. And these flares at different frequencies are known that they often correlate with each other. In 2013 December, there was a gamma-ray flare in 3C 279, one of the brightest blazars, Dec 2013. So we want to reveal that whether this flare correlates with radio flare or not, and where the flare originate. With polarization observation at radio frequencies, we can study the physical properties of the magnetic field in the innermost regions of the relativistic jets. Therefore, we have conducted polarization monitoring of this source from Dec. 2013 to Jun. 2014 with KVN(Korea VLBI Network) radio telescopes at 22, 43 and 86GHz. Here we present the initial results of the monitoring of 3C 279. We prospect that we can reveal the origin of this gamma-ray flare by comparing with our radio data.

• Proceedings of the KWS Conference
• /
• 2010.05a
• /
• pp.94-94
• /
• 2010

Fiber laser is a heat source which is introduced recently, and so has a little researched data compare with conventional laser processing. Moreover basic data for welding monitoring are also insufficient. Therefore, in this study, the change of signal with measuring position and angle of plasma emission signals were analysed as a basic experiment for real time monitoring in fiber laser welding. As a result, the signals measured from the side, front and rear had the biggest intensity at $60^{\circ}$, and frequency peak to reflect the behavior of keyhole and swing of plasma by shield gas was detected at $45{\sim}60^{\circ}$. However, both intensity of signal and the result of FFT for monitoring were satisfied at the angle of $45^{\circ}$ from the side.