• Journal of Digital Contents Society
• /
• v.10 no.1
• /
• pp.97-105
• /
• 2009

For effective remote education using multimedia, it is necessary to develop efficient management techniques of video information. This requires real-time processing of video information which should be managed and retrieved in a compressed forms. The main technology of compressing video is currently MPEG-2. This implies that it is very important to manage and retrieve video compressed in MPEG-2, and then to process the video in real-time for the remote education environment using multimedia. This paper is to develop the management system of video information which is one of the most critical requirements in remote education systems for managing and retrieving MPEG-2 video.

• Korean Journal of Food Science and Technology
• /
• v.42 no.3
• /
• pp.355-360
• /
• 2010

Vibrio parahaemolyticus (V. parahaemolyticus), which is commonly found in raw seafood, causes gastroenteritis in humans. Rapid and effective methods have been developed as culture methods require up to 5-7 days. In this study, real-time PCR was compared with the standard culture method for detecting V. parahaemolyticus in seafood and radish sprout samples. Five hundred grams of the samples were artificially contaminated with V. parahaemolyticus then divided into 20 samples. The samples were incubated in alkaline peptone water and then streaked onto thiosulfate-citrate-bile saltssucrose agar. Biochemical tests for suspicious colonies were performed using the API 20NE strip. In parallel, real-time PCR was performed targeting the toxR gene using the enrichment broth. The real-time PCR was sensitive in discriminating V. parahaemolyticus from other foodborne pathogens. The detection limit of the real-time PCR was $10^3\;CFU/mL$ in phosphate-buffered saline. Although the real-time PCR detected more positive samples (76 out of 180, 42%) than the culture method (66 out of 180, 37%), there was no significant statistical difference (p>0.05) between the two methods. In conclusion, real-time PCR assays could be an alternative to the standard culture method for detecting V. parahaemolyticus in seafood and radish sprouts, which has many advantages in terms of detection time, labor, and sensitivity.

• Magazine of RCR
• /
• v.12 no.1
• /
• pp.39-43
• /
• 2017

• Broadcasting and Media Magazine
• /
• v.17 no.4
• /
• pp.69-80
• /
• 2012

• Korean Journal of Artificial Intelligence
• /
• v.11 no.3
• /
• pp.17-22
• /
• 2023

In this paper, we propose a black ice detection system using Convolutional Neural Networks (CNNs). Black ice poses a serious threat to road safety, particularly during winter conditions. To overcome this problem, we introduce a CNN-based architecture for real-time black ice detection with an encoder-decoder network, specifically designed for real-time black ice detection using thermal images. To train the network, we establish a specialized experimental platform to capture thermal images of various black ice formations on diverse road surfaces, including cement and asphalt. This enables us to curate a comprehensive dataset of thermal road black ice images for a training and evaluation purpose. Additionally, in order to enhance the accuracy of black ice detection, we propose a multi-scale dilation convolution feature fusion (MsDC-FF) technique. This proposed technique dynamically adjusts the dilation ratios based on the input image's resolution, improving the network's ability to capture fine-grained details. Experimental results demonstrate the superior performance of our proposed network model compared to conventional image segmentation models. Our model achieved an mIoU of 95.93%, while LinkNet achieved an mIoU of 95.39%. Therefore, it is concluded that the proposed model in this paper could offer a promising solution for real-time black ice detection, thereby enhancing road safety during winter conditions.

• Korean Journal of Artificial Intelligence
• /
• v.11 no.4
• /
• pp.1-8
• /
• 2023

In this paper, we propose a black ice detection platform framework using Convolutional Neural Networks (CNNs). To overcome black ice problem, we introduce a real-time based early warning platform using CNN-based architecture, and furthermore, in order to enhance the accuracy of black ice detection, we apply a multi-scale dilation convolution feature fusion (MsDC-FF) technique. Then, we establish a specialized experimental platform by using a comprehensive dataset of thermal road black ice images for a training and evaluation purpose. Experimental results of a real-time black ice detection platform show the better performance of our proposed network model compared to conventional image segmentation models. Our proposed platform have achieved real-time segmentation of road black ice areas by deploying a road black ice area segmentation network on the edge device Jetson Nano devices. This approach in parallel using multi-scale dilated convolutions with different dilation rates had faster segmentation speeds due to its smaller model parameters. The proposed MsCD-FF Net(2) model had the fastest segmentation speed at 5.53 frame per second (FPS). Thereby encouraging safe driving for motorists and providing decision support for road surface management in the road traffic monitoring department.

• Environmental Engineering Research
• /
• v.14 no.1
• /
• pp.63-67
• /
• 2009

Escherichia coli K-12 (E. coli K-12) is a representative indicator globally used for distinguishing and monitoring dynamic fates of pathogenic microorganisms in the environment. This study investigated how to most critically quantify lacZ ($\beta$-galactosidase) gene in E. coli K-12 by two different real-time polymerase chain reaction (real-time PCR) in association with three different DNA extraction practices. Three DNA extractions, i.e., sodium dodecyl sulfate (SDS)/proteinase K, magnetic beads and guanidium thiocyanate (GTC)/silica matrix were each compared for extracting total genomic DNA from E. coli K-12. Among them, GTC/silica matrix and magnetic beads beating similarly worked out to have the highest (22-23 ng/${\mu}L$) concentration of DNA extracted, but employing SDS/proteinase K had the lowest (10 ng/${\mu}L$) concentration of DNA retrieved. There were no significant differences in the quantification of the copy numbers of lacZ gene between SYBR Green I qPCR and QProbe-qPCR. However, SYBR Green I qPCR obtained somewhat higher copy number as $1{\times}10^8$ copies. It was decided that GTC/silica matrix extraction or magnetic beads beating in combination with SYBR Green I qPCR can be preferably applied for more effectively quantifying specific gene from a pure culture of microorganism.

• Nuclear Engineering and Technology
• /
• v.25 no.1
• /
• pp.102-109
• /
• 1993

A PC-computer program RADAP has been developed in this study to perform a quick real-time analysis of dose assessment following an accident in a nuclear facility. RADAP uses an interactive LKagrangian puff model in simulating the transport and diffusion of radioactive plume in the atmosphere. For real-time analysis, RADAP treats one or multiple puffs of ground-level releases, simultaneously. It is assumed to maintain a Gaussian distribution within the puff and the diffusion coefficients are computed using the USNRC's normal sigma curve method. The program, however, does not consider the spatial variations but the temporal variations in wind conditions. Whole body and thyroid doses for 3$\times$31 grid are directed to output files, and they are also displayed through computer graphics on VGA or EGA color monitor. The results show that RADAP can be an excellent tool for quick estimation of accidental doses.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.12 no.1
• /
• pp.115-122
• /
• 1992

Stochastic rainfall-runoff process model which is mainly used in real-time streamflow forecasting is Transfer Function(TF) model that has a simple structure and can be easy to formulate state-space model. However, in order to forecast the streamflow accurately in real-time using the TF model, it is not only necessary to determine accurate structure of the model but also required to reduce forecasting error in early stage. In this study, after introducing 5-day Antecedent Precipitation Index (API5), which represents the initial soil moisture condition of the watershed, by using the threshold concept, the TF models in each API5 are identified by Box-Jenkins method and the results are compared with each other.

• Transactions of the Korean Society of Automotive Engineers
• /
• v.17 no.2
• /
• pp.118-125
• /
• 2009

Calculation of indicated mean effective pressure(IMEP) requires high cylinder pressure sampling rate and heavy computational load. Because of that, it is difficult to implement in a conventional electronic control unit. In this paper, a cylinder pressure based real-time IMEP estimation method is proposed for controller implementation. Crank angle at 10-bar difference pressure($CA_{DP10}$) and cylinder pressure difference between $60^{\circ}$ ATDC and $60^{\circ}$ BTDC($DP_{deg}$) are used for IMEP estimation. These pressure variables can represent effectively start of combustion(SOC) and fuel injection quantity respectively. The proposed IMEP estimation method is validated by transient engine operation using a common-rail direct injection diesel engine.