• Journal of Korea Multimedia Society
• /
• v.7 no.1
• /
• pp.35-43
• /
• 2004

In this paper, we proposed a vehicle recognition and electronic toll collection system with detection and classification of vehicle identification mark and emblem as well as recognition of vehicle license plate to unman toll fee collection system or incoming/outcoming vehicles to an institution. In the proposed algorithm, we first process pre-processing step such as noise reduction and thinning from the rear side input image of vehicle and detect vehicle mark, emblem and license plate region using intensity variation informations, template masking and labeling operation. And then, we classify the detected vehicle features regions into vehicle mark and emblem as well as recognize characters and numbers of vehicle license plate using hybrid and seven segment pattern vector. To show the efficiency of the proposed algorithm, we tested it on real vehicle images of implemented vehicle recognition system in highway toll gate and found that the proposed method shows good feature detection/classification performance regardless of irregular environment conditions as well as noise, size, and location of vehicles. And also, the proposed algorithm may be utilized for catching criminal vehicles, unmanned toll collection system, and unmanned checking incoming/outcoming vehicles to an institution.

• Journal of the Korean Chemical Society
• /
• v.51 no.6
• /
• pp.513-519
• /
• 2007

A vesicle forming polymer, poly(sodium acrylamidoundecanoate) (PSAU) and a water-soluble distyrylbenzene- based fluorophore, TPADSB-C were synthesized and characterized by using UV-vis and photoluminescence (PL) spectroscopy. An inter-chain vesicle formation of PSAU was observed at ~0.01 g/L from N-phenyl naphthylamine fluorescence measurement with changing PSAU concentration in water. Above critical aggregation concentration of PSAU, optical properties of TPADSB-C were investigated to study the microenvironment modulation through dye incorporation in the polymeric vesicle. The emission of TPADSB-C in the presence of PSAU vesicles was blue-shifted and the PL quantum efficiency was increased to 90% due to the microenvironment (e.g. polarity) change in aqueous solution. This study shows that the polymeric vesicle containing molecular fluorophores has a great potential as an efficient, stable and biocompatible labeling tag in biological cell imaging.

• Journal of Plant Biotechnology
• /
• v.47 no.4
• /
• pp.309-315
• /
• 2020

Advances in biotechnology have led to progress in crop genetic engineering to improve agricultural productivity. The use of genetically modified (GM) crops has increased, as have consumers' and regulators' concerns about the safety of GM crops to human health, and ecological biodiversity. As such, the identification of GM crops is a critical issue for developers and distributors, and their labeling is mandatory. Multiplex polymerase chain reaction (PCR) has been developed and its use validated for the detection and identification of GM crops in quarantine. Herein, we established a simultaneous detection method to identify four GM maize events. Event-specific primers were designed between the junction region of transgene and genome of four GM maize lines, namely 5307, DAS-40278-9, MON87460, and MON87427. To verify the efficiency and accuracy of the multiplex PCR we used specificity analysis, limit of detection evaluation, and mixed certified reference materials identification. The multiplex PCR method was applied to analyze 29 living, modified maize volunteers collected in South Korea in 2018 and 2019. We performed multiplex PCR analysis to identify events and confirmed the result by simplex PCR using each event-specific primer. As a result, rather than detecting each event individually, the simultaneous detection PCR method enabled the rapid analysis of 29 GM maize volunteers. Thus, the novel multiplex PCR method is applicable for living modified organism volunteer identification.

• Journal of Radiopharmaceuticals and Molecular Probes
• /
• v.5 no.1
• /
• pp.11-17
• /
• 2019

Recently, antibody-like scaffold proteins have received a great deal of interest in diagnosis and therapy applications because of their intrinsic features that are often required for tumor imaging and therapy. Intrinsic issues that are associated with therapeutic application of antibody-like scaffold proteins, particularly in cancer treatment, include an efficient and straightforward radiolabeling for understanding in vivo biodistribution and excretion route, and monitoring therapeutic responses. Herein, we report an efficient and straightforward method for radiolabeling of antibody-like scaffold proteins with the $[^{99m}Tc(OH_2)_3(CO)_3]^+$ ($^{99m}Tc$-tricarbonyl) by using a site-specific direct labeling method via hexahistidine-tag, which is a widely used for general purification of recombinant proteins with His-affinity chromatography. Repebody is a new class of antibody-like scaffold protein that consists of highly diverse leucine-rich repeat (LRR) modules. Although all possible biomedical applications with repebody are ongoing, it's in vivo biodistribution and excretion pathway has not yet been explored. In this study, hexahistidine ($His_6$)-tag bearing repebody (rEgH9) was labeled with [$^{99m}Tc$]-tricarbonyl. Repebody protein was radiolabeled with high radiolabeling efficiency (>90%) and radiolabeled compound was more than 99% pure after purification. These results clearly demonstrate that the present radiolabeling method will be useful molecular imaging study.

• Fashion & Textile Research Journal
• /
• v.24 no.1
• /
• pp.117-126
• /
• 2022

This study aims to analyze the sizing information of women's ready-to-wear pants as indicated on online retail websites and to suggest better sizing communication that can assist customers in making successful apparel size selections. We gathered size specifications and size reference information for basic straight pants from 34 online apparel retail websites. Although the Korean standard recommends labeling the body dimension-based sizing code and specification, most websites preferred to use various types of sizing codes. Body measurements were only used by a few websites, and garment dimension descriptions were the most common method to indicate product size. Many websites provided size reference information through customer review boards and fit model images, however, there was insufficient body size information to allow customers to infer the fit of their body type. When using the size guidance tools, the major data input points were stature and weight measurements. However, the waist measurements of pants sizes guided only by stature and weight values revealed inconsistent ease allowance for corresponding body size populations, especially in the overweight group. Based on our findings, we propose a more effective method of communicating the size information of pants online. We expect that this will contribute to the efficiency of online apparel product display and build a better shopping environment that satisfies both sellers and consumers.

• The Journal of the Convergence on Culture Technology
• /
• v.9 no.2
• /
• pp.561-568
• /
• 2023

Various defects occur in concrete structures due to internal and external environments. If there is a defect, it is important to efficiently identify and maintain it because there is a problem with the structural safety of concrete. However, recent deep learning research has focused on cracks in concrete, and studies on exfoliation and contamination are lacking. In this study, focusing on exfoliation and contamination, which are difficult to label, four models were developed and their performance evaluated through unlabelling method, filtering method, the convergence of transfer learning based k-means clustering. As a result of the analysis, the convergence model classified the defects in the most detail and could increase the efficiency compared to direct labeling. It is hoped that the results of this study will contribute to the development of deep learning models for various types of defects that are difficult to label in the future.

• Biomedical Science Letters
• /
• v.29 no.4
• /
• pp.211-219
• /
• 2023

Caffeic acid phenethyl ester (CAPE) is an active component of propolis obtained from honeybee hives. CAPE possesses anti-mitogenic, anti-carcinogenic, anti-inflammatory, and immunomodulatory activities in diverse systems, which know as displays antioxidant activity and inhibits lipoxygenase activities, protein tyrosine kinase, and nuclear factor kappa B (NF-κB) activation. This study aimed to investigate the effect of CAPE on lipopolysaccharide (LPS)-induced human neutrophil phagocytosis. Human neutrophils were cultured with various concentrations of CAPE (1, 10, and 100 µM) with or without LPS. The pro-inflammatory proteins (tumor necrosis factor-alpha [TNF-α], interleukin [IL]-6 and IL-8) levels were measured after 4 h incubation. To investigate the intracellular signaling pathway, we measured the levels of mitogen-activated protein kinases (MAPK), including phosphorylation of p38, extracellular signal-regulated protein kinases 1 and 2 (ERK1/2) and c-Jun N-terminal kinase (JNK). Next, to evaluate the potential phagocytosis, neutrophils were labeled with iron particles of superparamagnetic iron oxide nanoparticles (SPIONs, 40 nm) for 1 h in culture medium containing 5 mg/mL of iron. The labeling efficiency was determined by Prussian blue staining for intracellular iron and 3T-wighted magnetic resonance imaging. CAPE decreased the activation of intracellular signaling pathways, including ERK1/2 and c-Jun, and expression of pro-inflammatory cytokines, including TNF-α and IL-6, but had no effect on the signaling pathways of p38 and cytokine IL-8. Furthermore, images obtained after mannan-coated SPION treatment suggested that CAPE induced significantly higher signal intensities than the control or LPS group. Together, these results suggest that CAPE regulates LPS-mediated activation of human neutrophils to reduce phagocytosis.

• Journal of the Microelectronics and Packaging Society
• /
• v.30 no.4
• /
• pp.69-78
• /
• 2023

With the rapid growth of artificial intelligence, the demand for semiconductors is enormously increasing everywhere. To ensure the manufacturing quality and quantity simultaneously, the importance of automatic defect detection during the packaging process has been re-visited by adapting various deep learning-based methodologies into automatic packaging defect inspection. Deep learning (DL) models require a large amount of data for training, but due to the nature of the semiconductor industry where security is important, sharing and labeling of relevant data is challenging, making it difficult for model training. In this study, we propose a new framework for securing sufficient data for DL models with fewer computing resources through a divide-and-conquer approach. The proposed method divides high-resolution images into pre-defined sub-regions and assigns conditional labels to each region, then trains individual sub-regions and boundaries with boundary loss inducing the globally coherent and seamless images. Afterwards, full-size image is reconstructed by combining divided sub-regions. The experimental results show that the images obtained through this research have high efficiency, consistency, quality, and generality.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.23 no.1
• /
• pp.182-196
• /
• 2024

This study introduces driving pattern analysis and change detection methods using smartphone sensors, based on contrastive learning. These methods characterize driving patterns without labeled data, allowing accurate classification with minimal labeling. In addition, they are robust to domain changes, such as different vehicle types. The study also examined the applicability of these methods to smartphones by comparing them with six lightweight deep-learning models. This comparison supported the development of smartphone-based driving pattern analysis and assistance systems, utilizing smartphone sensors and contrastive learning to enhance driving safety and efficiency while reducing the need for extensive labeled data. This research offers a promising avenue for addressing contemporary transportation challenges and advancing intelligent transportation systems.

• Journal of Biomedical Engineering Research
• /
• v.45 no.2
• /
• pp.90-94
• /
• 2024

Diagnosing wounds presents a significant challenge in clinical settings due to its complexity and the subjective assessments by clinicians. Wound deep learning algorithms quantitatively assess wounds, overcoming these challenges. However, a limitation in existing research is reliance on specific datasets. To address this limitation, we created a comprehensive dataset by combining open dataset with self-produced dataset to enhance clinical applicability. In the annotation process, machine learning based on Gradient Vector Flow (GVF) was utilized to improve objectivity and efficiency over time. Furthermore, the deep learning model was equipped U-net with residual blocks. Significant improvements were observed using the input dataset with images cropped to contain only the wound region of interest (ROI), as opposed to original sized dataset. As a result, the Dice score remarkably increased from 0.80 using the original dataset to 0.89 using the wound ROI crop dataset. This study highlights the need for diverse research using comprehensive datasets. In future study, we aim to further enhance and diversify our dataset to encompass different environments and ethnicities.