• KIPS Transactions on Software and Data Engineering
• /
• v.12 no.11
• /
• pp.481-492
• /
• 2023

This study explores how to build a Korean dataset to extract information from text using generative large language models. In modern society, mixed information circulates rapidly, and effectively categorizing and extracting it is crucial to the decision-making process. However, there is still a lack of Korean datasets for training. To overcome this, this study attempts to extract information using text-based zero-shot learning using a generative large language model to build a purposeful Korean dataset. In this study, the language model is instructed to output the desired result through prompt engineering in the form of "system"-"instruction"-"source input"-"output format", and the dataset is built by utilizing the in-context learning characteristics of the language model through input sentences. We validate our approach by comparing the generated dataset with the existing benchmark dataset, and achieve 25.47% higher performance compared to the KLUE-RoBERTa-large model for the relation information extraction task. The results of this study are expected to contribute to AI research by showing the feasibility of extracting knowledge elements from Korean text. Furthermore, this methodology can be utilized for various fields and purposes, and has potential for building various Korean datasets.

• The Journal of the Convergence on Culture Technology
• /
• v.9 no.6
• /
• pp.967-971
• /
• 2023

Recently, a variety of AI-based platform services are available, and one of them is ChatGPT that processes a large quantity of data in the natural language and generates an answer after self-learning. ChatGPT can perform various tasks including software programming in the IT sector. Particularly, it may help generate a simple program and correct errors using C Language, which is a major programming language. Accordingly, it is expected that ChatGPT is capable of effectively using Verilog HDL, which is a hardware language created in C Language. Verilog HDL synthesis, however, is to generate imperative sentences in a logical circuit form and thus it needs to be verified whether the products are executed properly. In this paper, we aim to select small-scale logical circuits for ease of experimentation and to verify the results of circuits generated by ChatGPT and human-designed circuits. As to experimental environments, Xilinx ISE 14.7 was used for module modeling, and the xc3s1000 FPGA chip was used for module embodiment. Comparative analysis was performed on the use area and processing time of FPGA to compare the performance of ChatGPT products and Verilog HDL products.

• The Journal of the Convergence on Culture Technology
• /
• v.10 no.2
• /
• pp.537-545
• /
• 2024

The importance of University Archives Management is increasing. In this study, we researched cases of collecting and managing educational archival contents in universities. Developed archival contents for software practical education, and implemented it to the Capstone Design course and overseas program. The effect of applying the model was analyzed through surveys and interviews. The Capstone Design Survey, involving 349 participants, indicated the highest satisfaction with the University-Industry Cooperation type. The experience of dissemination and enhancement was aggregated as the second highest satisfaction. In the second survey, 62 students who had participated in the overseas program over the span of two years took part. All nine Likert-type questions showed high satisfaction scores of more than 4 points. The top three satisfaction factors-content, program type, and advanced experience-showed high satisfaction scores of 4.85, 4.74, and 4.71, respectively. Through interviews with professors, mentors, and students, it was also confirmed that instructional methods utilizing archival contents are effective. And the model we developed is applicable for convergence education.

• Advanced Industrial SCIence
• /
• v.3 no.2
• /
• pp.31-37
• /
• 2024

This paper presents a single and 2-patch microstrip array antenna operated on a frequency of 10.3GHz(x-band). It outlines the process of designing a microstrip patch array antenna using CST MWS. Initially, a single microstrip antenna was designed, followed by optimization using CST MWS to attain optimal return losses and gain. Subsequently, the design was expanded to create a 2×1 microstrip inset-fed array antenna for the X-band applications. The construction material is Roger RO4350B, with specific dimensions (h=0.79mm, 𝜖_r = 3.54). The achieved results include an S11 of -18dB at the resonant frequency (10.3GHz), a gain of 9.82dBi, a bandwidth of 0.165GHz, and a 3-dB beamwidth of 30°, 121° in Az(𝜑=0) and El(𝜑=90) plane, respectively. The future plan involves the fabrication of this array antenna and further expansion to a 4×4 array of microstrip antennas. It is then incorporated on the X-band applications for practical uses.

• Journal of The Korean Association For Science Education
• /
• v.44 no.3
• /
• pp.231-248
• /
• 2024

This study developed a chatbot for first-year high school students, employing open-source software and the Korean Sentence-BERT model for AI-powered document classification. The chatbot utilizes the Sentence-BERT model to find the six most similar Q&A pairs to a student's query and presents them in a carousel format. The initial dataset, built from online resources, was refined and expanded based on student feedback and usability throughout over the operational period. By the end of the 2023 academic year, the chatbot integrated a total of 30,819 datasets and recorded 3,457 student interactions. Analysis revealed students' inclination to use the chatbot when prompted by teachers during classes and primarily during self-study sessions after school, with an average of 2.1 to 2.2 inquiries per session, mostly via mobile phones. Text mining identified student input terms encompassing not only science-related queries but also aspects of school life such as assessment scope. Topic modeling using BERTopic, based on Sentence-BERT, categorized 88% of student questions into 35 topics, shedding light on common student interests. A year-end survey confirmed the efficacy of the carousel format and the chatbot's role in addressing curiosities beyond integrated science learning objectives. This study underscores the importance of developing chatbots tailored for student use in public education and highlights their educational potential through long-term usage analysis.

• Korean Journal of Radiology
• /
• v.24 no.8
• /
• pp.807-820
• /
• 2023

Objective: To assess whether computed tomography (CT) conversion across different scan parameters and manufacturers using a routable generative adversarial network (RouteGAN) can improve the accuracy and variability in quantifying interstitial lung disease (ILD) using a deep learning-based automated software. Materials and Methods: This study included patients with ILD who underwent thin-section CT. Unmatched CT images obtained using scanners from four manufacturers (vendors A-D), standard- or low-radiation doses, and sharp or medium kernels were classified into groups 1-7 according to acquisition conditions. CT images in groups 2-7 were converted into the target CT style (Group 1: vendor A, standard dose, and sharp kernel) using a RouteGAN. ILD was quantified on original and converted CT images using a deep learning-based software (Aview, Coreline Soft). The accuracy of quantification was analyzed using the dice similarity coefficient (DSC) and pixel-wise overlap accuracy metrics against manual quantification by a radiologist. Five radiologists evaluated quantification accuracy using a 10-point visual scoring system. Results: Three hundred and fifty CT slices from 150 patients (mean age: 67.6 ± 10.7 years; 56 females) were included. The overlap accuracies for quantifying total abnormalities in groups 2-7 improved after CT conversion (original vs. converted: 0.63 vs. 0.68 for DSC, 0.66 vs. 0.70 for pixel-wise recall, and 0.68 vs. 0.73 for pixel-wise precision; P < 0.002 for all). The DSCs of fibrosis score, honeycombing, and reticulation significantly increased after CT conversion (0.32 vs. 0.64, 0.19 vs. 0.47, and 0.23 vs. 0.54, P < 0.002 for all), whereas those of ground-glass opacity, consolidation, and emphysema did not change significantly or decreased slightly. The radiologists' scores were significantly higher (P < 0.001) and less variable on converted CT. Conclusion: CT conversion using a RouteGAN can improve the accuracy and variability of CT images obtained using different scan parameters and manufacturers in deep learning-based quantification of ILD.

• Journal of Intelligence and Information Systems
• /
• v.26 no.3
• /
• pp.51-69
• /
• 2020

Now, it is a stylized fact that a small number of technology firms such as Apple, Alphabet, Microsoft, Amazon, Facebook and a few others have become larger and dominant players in an industry. Coupled with the rise of these leading firms, we have also observed that a large number of young firms have become an acquisition target in their early IPO stages. This indeed results in a sharp decline in the number of new entries in public exchanges although a series of policy reforms have been promulgated to foster competition through an increase in new entries. Given the observed industry trend in recent decades, a number of studies have reported increased concentration in most developed countries. However, it is less understood as to what caused an increase in industry concentration. In this paper, we uncover the mechanisms by which industries have become concentrated over the last decades by tracing the changes in industry concentration associated with a firm's status change in its early IPO stages. To this end, we put emphasis on the case in which firms are acquired shortly after they went public. Especially, with the transition to digital-based economies, it is imperative for incumbent firms to adapt and keep pace with new ICT and related intelligent systems. For instance, after the acquisition of a young firm equipped with AI-based solutions, an incumbent firm may better respond to a change in customer taste and preference by integrating acquired AI solutions and analytics skills into multiple business processes. Accordingly, it is not unusual for young ICT firms become an attractive acquisition target. To examine the role of M&As involved with young firms in reshaping the level of industry concentration, we identify a firm's status in early post-IPO stages over the sample periods spanning from 1990 to 2016 as follows: i) being delisted, ii) being standalone firms and iii) being acquired. According to our analysis, firms that have conducted IPO since 2000s have been acquired by incumbent firms at a relatively quicker time than those that did IPO in previous generations. We also show a greater acquisition rate for IPO firms in the ICT sector compared with their counterparts in other sectors. Our results based on multinomial logit models suggest that a large number of IPO firms have been acquired in their early post-IPO lives despite their financial soundness. Specifically, we show that IPO firms are likely to be acquired rather than be delisted due to financial distress in early IPO stages when they are more profitable, more mature or less leveraged. For those IPO firms with venture capital backup have also become an acquisition target more frequently. As a larger number of firms are acquired shortly after their IPO, our results show increased concentration. While providing limited evidence on the impact of large incumbent firms in explaining the change in industry concentration, our results show that the large firms' effect on industry concentration are pronounced in the ICT sector. This result possibly captures the current trend that a few tech giants such as Alphabet, Apple and Facebook continue to increase their market share. In addition, compared with the acquisitions of non-ICT firms, the concentration impact of IPO firms in early stages becomes larger when ICT firms are acquired as a target. Our study makes new contributions. To our best knowledge, this is one of a few studies that link a firm's post-IPO status to associated changes in industry concentration. Although some studies have addressed concentration issues, their primary focus was on market power or proprietary software. Contrast to earlier studies, we are able to uncover the mechanism by which industries have become concentrated by placing emphasis on M&As involving young IPO firms. Interestingly, the concentration impact of IPO firm acquisitions are magnified when a large incumbent firms are involved as an acquirer. This leads us to infer the underlying reasons as to why industries have become more concentrated with a favor of large firms in recent decades. Overall, our study sheds new light on the literature by providing a plausible explanation as to why industries have become concentrated.

• Journal of Nutrition and Health
• /
• v.42 no.6
• /
• pp.577-595
• /
• 2009

This study aimed to reanalyze energy and nutrient intakes of 2007 Korean Nutrition and Health Examination Survey (KNHANES) using CAN-Pro 3.0, a commonly used nutrient analysis software in Korea. Food items and their codes were selected from 2007 KNHANES dietary intake file and converted to food codes of CAN-Pro 3.0 nutrient database (NDB). Of the 1,324 total food items, 1,155 items were converted by direct matching, 123 items were matched using other items in CAN-Pro 3.0 NDB and 42 items were matched using external sources. Consumption frequencies of items converted by direct matching contributed 94.5% of total consumption. Nutrient intakes of 4,091 participants of 2007 KNHANES, over 1 year old, were recalculated using CAN-Pro 3.0 NDB and compared with intakes in 2007 KNHANES dietary intake file. Intakes for energy and all nutrients except protein and Vitamin C calculated by two NDBs were significantly different by paired t-test (p < 0.001), but significantly correlated by Pearson' correlation coefficients (p < 0.001). Percent differences between the NDBs ranged from 0.3% to 15.1%, low for protein, energy, vitamin C, iron, vitamin B$_2$ (below 5%) but high for phosphorus, retinol, vitamin A, and $\beta$-carotene (over 10%). Age group, sex, and their interactions significantly influenced six nutrients (p < 0.05). Intake levels of zinc, vitamin B6, vitamin E, folate and cholesterol were not available in 2007 KNHANES but were calculated by CAN-Pro 3.0. Mean intake levels of zinc, vitamin B$_6$, vitamin E, and folate by age and sex groups revealed that some groups had mean levels below RI (Recommended Intake) or AI (Adequate Intake) levels. Intake level of cholesterol was higher than the recommended level (below 300 mg/day) in some groups, especially males. Results of the present study indicate the need for comparable and more comprehensive NDB to be used for dietary assessment of KNHANES and other researches. More rigorous evaluation of nutrients which have not been reported in KNHANES is needed.

• Journal of Internet Computing and Services
• /
• v.22 no.1
• /
• pp.41-50
• /
• 2021

Cyber Kill Chain is derived from Kill chain of traditional military terms. Kill chain means "a continuous and cyclical process from detection to destruction of military targets requiring destruction, or dividing it into several distinct actions." The kill chain has evolved the existing operational procedures to effectively deal with time-limited emergency targets that require immediate response due to changes in location and increased risk, such as nuclear weapons and missiles. It began with the military concept of incapacitating the attacker's intended purpose by preventing it from functioning at any one stage of the process of reaching it. Thus the basic concept of the cyber kill chain is that the attack performed by a cyber attacker consists of each stage, and the cyber attacker can achieve the attack goal only when each stage is successfully performed, and from a defense point of view, each stage is detailed. It is believed that if a response procedure is prepared and responded, the chain of attacks is broken, and the attack of the attacker can be neutralized or delayed. Also, from the point of view of an attack, if a specific response procedure is prepared at each stage, the chain of attacks can be successful and the target of the attack can be neutralized. The cyber command and control system is a system that is applied to both defense and attack, and should present defensive countermeasures and offensive countermeasures to neutralize the enemy's kill chain during defense, and each step-by-step procedure to neutralize the enemy when attacking. Therefore, thist paper proposed a cyber kill chain model from the perspective of defense and attack of the cyber command and control system, and also researched and presented the threat classification/analysis/prediction framework of the cyber command and control system from the defense aspect

• Radiation Oncology Journal
• /
• v.21 no.4
• /
• pp.299-305
• /
• 2003

Purpose: In order to develop the national guide-lines for the standardization of radiotherapy we are planning to establish a web-based, on-line data-base system for laryngeal cancer. As a first step this study was performed to accumulate the basic clinical information of laryngeal cancer and to determine the items needed for the data-base system. Materials and Methods: We analyzed the clinical data on patients who were treated under the diagnosis of laryngeal cancer from January 1998 through December 1999 In the South-west area of Korea. Eligiblity criteria of the patients are as follows: 18 years or older, currently diagnosed with primary epithelial carcinoma of larynx, and no history of previous treatments for another cancers and the other laryngeal diseases. The items were developed and filled out by radiation oncologlst who are members of forean Southwest Radiation Oncology Group. SPSS vl0.0 software was used for statistical analysis. Results: Data of forty-five patients were collected. Age distribution of patients ranged from 28 to 88 years(median, 61). Laryngeal cancer occurred predominantly In males (10 : 1 sex ratio). Twenty-eight patients (62$\%$) had primary cancers in the glottis and 17 (38$\%$) in the supraglottis. Most of them were diagnosed pathologically as squamous cell carcinoma (44/45, 98$\%$). Twenty-four of 28 glottic cancer patients (86$\%$) had AJCC (American Joint Committee on Cancer) stage I/II, but 50$\%$ (8/16) had In supraglottic cancer patients (p=0.02). Most patients(89$\%$) had the symptom of hoarseness. indirect laryngoscopy was done in all patients and direct laryngoscopy was peformed in 43 (98$\%$) patients. Twenty-one of 28 (75$\%$) glottic cancer cases and 6 of 17 (35$\%$) supraglottic cancer cases were treated with radiation alone, respectively. The combined treatment of surgery and radiation was used in 5 (18$\%$) glottic and 8 (47$\%$) supraglottic patients. Chemotherapy and radiation was used in 2 (7$\%$) glottic and 3 (18$\%$) supraglottic patients. There was no statistically significant difference in the use of combined modality treatments between glottic and supraglottic cancers (p=0.20). In all patients, 6 MV X-ray was used with conventional fractionation. The iraction size was 2 Gy In 80$\%$ of glottic cancer patients compared with 1.8 Gy in 59$\%$ of the patients with supraglottic cancers. The mean total dose delivered to primary lesions were 65.98 ey and 70.15 Gy in glottic and supraglottic patients treated, respectively, with radiation alone. Based on the collected data, 12 modules with 90 items were developed or the study of the patterns of care In laryngeal cancer. Conclusion: The study Items for laryngeal cancer were developed. In the near future, a web system will be established based on the Items Investigated, and then a nation-wide analysis on laryngeal cancer will be processed for the standardization and optimization of radlotherapy.