• Journal of Institute of Control, Robotics and Systems
• /
• v.3 no.5
• /
• pp.497-502
• /
• 1997

In this study an automatic rolling-coil labeling system using robot vision system and peripheral mechanism is proposed and implemented, which instead of the manual labor to attach labels Rolling-coils in a steel mill. The binary image process for the image processing is performed with the threshold, and the contour line is converted to the binary gradient which detects the discontinuous variation of brightness of rolling-coils. The moments invariant algorithm proposed by Hu is used to make it easy to recognize even when the position of the center are different from the trained data. The position error compensation algorithm of six degrees of freedom industrial robot manipulator is also developed and the data of the position of the center rolling-coils, which is obtained by floor mount camera, are transferred by asynchronous communication method. Therefore, even if the position of center is changed, robot moves to the position of center and performs the labeling work successfully. Therefore, this system can be improved the safety and efficiency.

• Molecular & Cellular Toxicology
• /
• v.1 no.2
• /
• pp.92-98
• /
• 2005

DNA microarray analysis of gene expression in toxicogenomics typically requires relatively large amounts of total RNA. This limits the use of DNA microarray when the sample available is small. To confront this limitation, different methods of linear RNA amplification that generate antisense RNA (aRNA) have been optimized for microarray use. The target preparation strategy using amplified RNA in DNA microarray protocol can be divided into direct-incorporation labeling which resulted in cDNA targets (Cy-dye labeled cDNA from aRNA) and indirect-labeling which resulted in cRNA targets (i.e. Cy-dye labeled aRNA), respectively. However, despite the common use of amplified targets (cDNA or cRNA) from aRNAs, no systemic assessment for the use of amplified targets and bias in terms of hybridization performance has been reported. In this investigation, we have compared the hybridization performance of cRNA targets with cDNA targets from aRNA on a 10 K cDNA microarrays. Under optimized hybridization conditions, we found that 43% of outliers from cDNA technique and 86% from the outlier genes were reproducibly detected by both targets hybridization onto cDNA microarray. This suggests that the cRNA labeling method may have a reduced capacity for detecting the differential gene expression when compared to the cDNA target preparation. However, further validation of this discordant result should be pursued to determine which techniques possesses better accuracy in identifying truly differential genes.

• International Journal of Oral Biology
• /
• v.40 no.4
• /
• pp.183-187
• /
• 2015

The present study was aimed to evaluate the influence of glutaraldehyde (GA) concentration on multiple electron microscopic (EM) immunostaining using pre-embedding peroxidase and post-embedding immunogold method. Influence of various concentrations of GA included in the fixative on immuoreactivity was assessed in the multiple immunostaining using antisera against anti-transient receptor potential vanilloid 1 (TRPV1) for peroxidase staining and anti-GABA for immunogold labeling in the rat trigeminal caudal nucleus. Anti-TRPV1 antiserum had specificity in pre-embedding peroxidase staining when tissues were fixed with fixative containing paraformaldehyde (PFA) alone. Immunoreactivity for TRPV1 was specific in tissues fixed with fixative containing 0.5% GA at both perfusion and postfixation steps, though the immunoreactivity was weaker than in tissues fixed with fixative containing PFA alone. Tissues fixed with fixative containing 0.5% GA at the perfusion and postfixation steps showed specific immunogold staining for GABA. The results of the present study indicate that GA concentration is critical for immunoreactivity to antigens such as TRPV1 and GABA. This study also suggests that the appropriate GA concentration is 0.5% for multiple immunostaining with peroxidase labeling for TRPV1 and immunogold labeling for GABA.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.17 no.1
• /
• pp.80-89
• /
• 1992

This paper presents algorithms which are region labeling and data structure of a boundary segmentation as image intermediate description process. In the method, the algorithms are region labeling, boundary segmentation, line and curve fitting and extracting data structure of each segment. As a result, a data structure of image is described by a set of region number, segment number, line or curve, starting point and end point of each segment and coefficient of line or curve. These data structures would serve for higher level processing as object recognition. For example we will use this data structure to solve the correspondence problem of stereoscopic image information. And we verified these algorithms through the image reconstruction of data structure.

• KIEAE Journal
• /
• v.13 no.2
• /
• pp.141-149
• /
• 2013

This paper aims to provide pragmatic application guidelines of the interior finish materials for apartment houses with newly-established evaluation methodology of the sustainable degree of interior products. With reference to the standards and criteria of domestic eco-labeling accreditation schemes for sustainable products in the area of architecture which focus on the sustainable elements classified as the health, recyclability, durability, and energy efficiency, in this study, a systematic evaluation method has been established for interior finish products with quantifiable indicators for sustainable performance. Base on the evaluation system introduced here, most interior finish products can be classified into a database and applied effectively to the realities from the perspective of the sustainability. There are the necessities of enforcement issues with the idea of revising or taking remedial measures of the current performance criteria of domestic eco-labeling accreditation to bolster their reliability. As well as already-commercialized products, hereafter, continued efforts are needed to control the whole process of manufacturing new interior finish products from their designing, constructing, consuming, recycling and to dismantling in terms of sustainability, which promises more pragmatic follow-up measures for the detail embodiment of the environment-friendly spaces.

• Korean Journal of Fisheries and Aquatic Sciences
• /
• v.35 no.4
• /
• pp.451-453
• /
• 2002

The rotation of the flagellar motor is powered by the electrochemical gradient of specific ions across the cytoplasmic membrane. Recently, the gents of the Na'-driven motor have been cloned from marine bacterium of Vibrio sp. and some of the motor proteins have been purified and characterized. Also, motx gene encoding a channel component of the sodium type flagellar motor was identified from Vibrio Huuiaiis (KTCC 2473). The amino acid sequence of MotX protein from V, Huvialis shared 90, 85, $85\%$ identity with V, cholerae, V. alginolyticus, V parahaemolyticus, respectively. We have studied the localization of the expressed MotX protein in Escherichia coli by immune-gold labeling of ultra-thin frozen section. Our observation of the expressed protein indicated that MotX protein could be existed as attachment to inner membrane in E. coli.

• Proceedings of the KIEE Conference
• /
• 1996.07b
• /
• pp.1266-1268
• /
• 1996

In this study an automatic roiling-coli labeling system using robot vision system and peripheral mechanism is proposed and implemented, which instead of the manual labor to attach labels Rolling-coils in a steel miil. The binary image process for the image processing is performed with the threshold, and the contour line is converted to the binary gradient which detects the discontinuous variation of brightness of rolling-coils. The moment invariants algorithm proposed by Hu is used to make it easy to recognize even when the position of the center are different from the trained data. The position error compensation algorithm of six degrees of freedom industrial robot manipulator is also developed and the data of the position of the center rolling-coils, which is obtained by floor mount camera, are transfered by asynchronous communication method. Therefore even if the position of center is changed, robot moves to the position of center and performs the labeling work successfully. Therefore, this system can be improved the safety and efficiency.

• The Journal of Korea Robotics Society
• /
• v.14 no.1
• /
• pp.31-39
• /
• 2019

A robot usually adopts ANN (artificial neural network)-based object detection and instance segmentation algorithms to recognize objects but creating datasets for these algorithms requires high labeling costs because the dataset should be manually labeled. In order to lower the labeling cost, a new scheme is proposed that can automatically generate a training images and label them for specific objects. This scheme uses an instance segmentation algorithm trained to give the masks of unknown objects, so that they can be obtained in a simple environment. The RGB images of objects can be obtained by using these masks, and it is necessary to label the classes of objects through a human supervision. After obtaining object images, they are synthesized with various background images to create new images. Labeling the synthesized images is performed automatically using the masks and previously input object classes. In addition, human intervention is further reduced by using the robot arm to collect object images. The experiments show that the performance of instance segmentation trained through the proposed method is equivalent to that of the real dataset and that the time required to generate the dataset can be significantly reduced.

• The Transactions of the Korea Information Processing Society
• /
• v.13 no.4
• /
• pp.181-188
• /
• 2024

Traditional profanity detection methods have limitations in identifying intentionally altered profanities. This paper introduces a new method based on Named Entity Recognition, a subfield of Natural Language Processing. We developed a profanity detection technique using sequence labeling, for which we constructed a dataset by labeling some profanities in Korean malicious comments and conducted experiments. Additionally, to enhance the model's performance, we augmented the dataset by labeling parts of a Korean hate speech dataset using one of the large language models, ChatGPT, and conducted training. During this process, we confirmed that filtering the dataset created by the large language model by humans alone could improve performance. This suggests that human oversight is still necessary in the dataset augmentation process.

• International conference on construction engineering and project management
• /
• 2024.07a
• /
• pp.1065-1072
• /
• 2024

Previous approaches to 3D excavator pose estimation via synthetic data training utilized a single virtual excavator model, low polygon objects, relatively poor textures, and few background objects, which led to reduced accuracy when the resulting models were tested on differing excavator types and more complex backgrounds. To address these limitations, the authors present a realism-centric synthetization and labeling approach that synthesizes results with improved image quality, more detailed excavator models, additional excavator types, and complex background conditions. Additionally, the data generated includes dense pose labels and depth maps for the excavator models. Utilizing the realism-centric generation method, the authors achieved significantly greater image detail, excavator variety, and background complexity for potentially improved labeling accuracy. The dense pose labels, featuring fifty points instead of the conventional four to six, could allow inferences to be made from unclear excavator pose estimates. The synthesized depth maps could be utilized in a variety of DNN applications, including multi-modal data integration and object detection. Our next step involves training and testing DNN models that would quantify the degree of accuracy enhancement achieved by increased image quality, excavator diversity, and background complexity, helping lay the groundwork for broader application of synthetic models in construction robotics and automated project management.