• Journal of radiological science and technology
• /
• v.33 no.4
• /
• pp.387-394
• /
• 2010

In the field of healthcare, the conventional sterilization treatments have been replaced by irradiation methods which are in accordance with internationally well established quality standards. The quality control in radiation sterilization assures that the absorbed dose of the irradiated material is in agreement with its requirements and standards. The electron beam irradiation requires technical assessments of more process parameters than gamma irradiation does. Korea has witnessed wide uses of electron accelerators since early 2000 but there hasn't been research experiences relating to quality system in accordance with international standards. The new large scale e-beam irradiation system with the specification of 10 MeV, 8 kW was installed and operated in 2008 by Seoul Radiology Services Co. It consists of the electron accelerator, product handling system, safety, documentation and control subsystems into an integrated system to meet the requirement of the Good Manufacturing Practice such as process quality assurance and management of product tracking records. To implement the international standard such as EN ISO11137, it is necessary to understand the purposes aimed in the standard and carry out the tests following the procedures required. This study presented the specification of the e-beam facility and showed what its design requirements and features are. The test results on a variety of process parameters were presented and validated it they are within the required limits.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.20 no.10
• /
• pp.54-61
• /
• 2019

This paper reports a comparative review of the service quality attributes of Electronic Customs Clearance (UNI-PASS) by applying the Kano model, Timko's BW coefficients, and IGA model, as reported by Tontini et al. in terms of a service quality evaluation of electronic customs clearance as the comprehensive national customs administration information system. In addition, this study examined which quality attributes should be focused on to improve the service quality and enhance customer satisfaction using the electronic customs clearance service. The Kano, Timko, and IGA models were classified into the four common quality attributes: attractive quality, one-dimensional quality, must-be quality, and indifferent quality. Because the integrated approach was used, one-dimensional quality was included in the area for critical improvement, while the must-be quality was included in the area for intensive maintenance. In addition, the indifferent quality was included in the area of carefree, while the attractive quality was included in the area of competitive advantage.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.22 no.3
• /
• pp.446-452
• /
• 2021

As a higher standard for food consumption is required, the consumption of chicken meat that can satisfy the subdivided food preferences is increasing. In March 2003, the quality criteria for chicken carcasses notified by the Livestock Quality Assessment Service suggested quality grades according to fecal contamination and the size and weight of blood and bruises. On the other hand, it is too difficult for human inspection to qualify mass products, which is key to maintaining consistency for grading thousands of chicken carcasses. This paper proposed the computer vision algorithm as a non-destructive inspection, which can identify chicken carcass parts according to the detailed standards. To inspect the chicken carcasses conveyed at high speed, the image calibration was involved in providing robustness to the side effect of external lighting interference. The separation between chicken and background was achieved by a series of image processing, such as binarization based on Expectation Maximization, Erosion, and Labeling. In terms of shape analysis of chicken carcasses, the features are presented to reveal geometric information. After applying the algorithm to 78 chicken carcass samples, the algorithm was effective in segmenting chicken carcass against a background and analyzing its geometric features.

• Journal of Intelligence and Information Systems
• /
• v.29 no.4
• /
• pp.165-184
• /
• 2023

Recently, Deep learning analysis of unstructured text data using language models, such as Google's BERT and OpenAI's GPT has shown remarkable results in various applications. Most language models are used to learn generalized linguistic information from pre-training data and then update their weights for downstream tasks through a fine-tuning process. However, some concerns have been raised that privacy may be violated in the process of using these language models, i.e., data privacy may be violated when data owner provides large amounts of data to the model owner to perform fine-tuning of the language model. Conversely, when the model owner discloses the entire model to the data owner, the structure and weights of the model are disclosed, which may violate the privacy of the model. The concept of offsite tuning has been recently proposed to perform fine-tuning of language models while protecting privacy in such situations. But the study has a limitation that it does not provide a concrete way to apply the proposed methodology to text classification models. In this study, we propose a concrete method to apply offsite tuning with an additional classifier to protect the privacy of the model and data when performing multi-classification fine-tuning on Korean documents. To evaluate the performance of the proposed methodology, we conducted experiments on about 200,000 Korean documents from five major fields, ICT, electrical, electronic, mechanical, and medical, provided by AIHub, and found that the proposed plug-in model outperforms the zero-shot model and the offsite model in terms of classification accuracy.

• Economic and Environmental Geology
• /
• v.53 no.5
• /
• pp.609-617
• /
• 2020

After introducing the industry 4.0 policy, Korean government announced 'Digital New Deal' and 'Green New Deal' as 'Korean New Deal' in 2020. We analyzed Korea Institute of Geoscience and Mineral Resources (KIGAM)'s research projects related to that policy and conducted markets analysis focused on Digital Twin and environmental monitoring technologies. Regarding 'Data Dam' policy, we suggested the digital geo-contents with Augmented Reality (AR) & Virtual Reality (VR) and the public geo-data collection & sharing system. It is necessary to expand and support the smart mining and digital oil fields research for '5th generation mobile communication (5G) and artificial intelligence (AI) convergence into all industries' policy. Korean government is suggesting downtown 3D maps for 'Digital Twin' policy. KIGAM can provide 3D geological maps and Internet of Things (IoT) systems for social overhead capital (SOC) management. 'Green New Deal' proposed developing technologies for green industries including resource circulation, Carbon Capture Utilization and Storage (CCUS), and electric & hydrogen vehicles. KIGAM has carried out related research projects and currently conducts research on domestic energy storage minerals. Oil and gas industries are presented as representative applications of digital twin. Many progress is made in mining automation and digital mapping and Digital Twin Earth (DTE) is a emerging research subject. The emerging research subjects are deeply related to data analysis, simulation, AI, and the IoT, therefore KIGAM should collaborate with sensors and computing software & system companies.