• Knowledge Management Research
• /
• v.25 no.2
• /
• pp.19-47
• /
• 2024

Organizational ability to analyze and utilize data plays an important role in knowledge management and decision-making. This study aims to investigate the potential application of large language models in corporate data analysis. Focusing on the field of human resources, the research examines the data analysis capabilities of these models. Using the widely studied IBM HR dataset, the study reproduces machine learning-based employee turnover prediction analyses from previous research through ChatGPT and compares its predictive performance. Unlike past research methods that required advanced programming skills, ChatGPT-based machine learning data analysis, conducted through the analyst's natural language requests, offers the advantages of being much easier and faster. Moreover, its prediction accuracy was found to be competitive compared to previous studies. This suggests that large language models could serve as effective and practical alternatives in the field of corporate data analysis, which has traditionally demanded advanced programming capabilities. Furthermore, this approach is expected to contribute to the popularization of data analysis and the spread of data-driven decision-making (DDDM). The prompts used during the data analysis process and the program code generated by ChatGPT are also included in the appendix for verification, providing a foundation for future data analysis research using large language models.

• Korean Journal of Radiology
• /
• v.24 no.5
• /
• pp.395-405
• /
• 2023

Objective: This study aimed to develop and validate models using radiomics features on a native T1 map from cardiac magnetic resonance (CMR) to predict left ventricular reverse remodeling (LVRR) in patients with nonischemic dilated cardiomyopathy (NIDCM). Materials and Methods: Data from 274 patients with NIDCM who underwent CMR imaging with T1 mapping at Severance Hospital between April 2012 and December 2018 were retrospectively reviewed. Radiomic features were extracted from the native T1 maps. LVRR was determined using echocardiography performed ≥ 180 days after the CMR. The radiomics score was generated using the least absolute shrinkage and selection operator logistic regression models. Clinical, clinical + late gadolinium enhancement (LGE), clinical + radiomics, and clinical + LGE + radiomics models were built using a logistic regression method to predict LVRR. For internal validation of the result, bootstrap validation with 1000 resampling iterations was performed, and the optimism-corrected area under the receiver operating characteristic curve (AUC) with 95% confidence interval (CI) was computed. Model performance was compared using AUC with the DeLong test and bootstrap. Results: Among 274 patients, 123 (44.9%) were classified as LVRR-positive and 151 (55.1%) as LVRR-negative. The optimism-corrected AUC of the radiomics model in internal validation with bootstrapping was 0.753 (95% CI, 0.698-0.813). The clinical + radiomics model revealed a higher optimism-corrected AUC than that of the clinical + LGE model (0.794 vs. 0.716; difference, 0.078 [99% CI, 0.003-0.151]). The clinical + LGE + radiomics model significantly improved the prediction of LVRR compared with the clinical + LGE model (optimism-corrected AUC of 0.811 vs. 0.716; difference, 0.095 [99% CI, 0.022-0.139]). Conclusion: The radiomic characteristics extracted from a non-enhanced T1 map may improve the prediction of LVRR and offer added value over traditional LGE in patients with NIDCM. Additional external validation research is required.

• Korean Journal of Radiology
• /
• v.24 no.11
• /
• pp.1151-1163
• /
• 2023

Objective: To develop a deep-learning-based bone age prediction model optimized for Korean children and adolescents and evaluate its feasibility by comparing it with a Greulich-Pyle-based deep-learning model. Materials and Methods: A convolutional neural network was trained to predict age according to the bone development shown on a hand radiograph (bone age) using 21036 hand radiographs of Korean children and adolescents without known bone development-affecting diseases/conditions obtained between 1998 and 2019 (median age [interquartile range {IQR}], 9 [7-12] years; male:female, 11794:9242) and their chronological ages as labels (Korean model). We constructed 2 separate external datasets consisting of Korean children and adolescents with healthy bone development (Institution 1: n = 343; median age [IQR], 10 [4-15] years; male: female, 183:160; Institution 2: n = 321; median age [IQR], 9 [5-14] years; male: female, 164:157) to test the model performance. The mean absolute error (MAE), root mean square error (RMSE), and proportions of bone age predictions within 6, 12, 18, and 24 months of the reference age (chronological age) were compared between the Korean model and a commercial model (VUNO Med-BoneAge version 1.1; VUNO) trained with Greulich-Pyle-based age as the label (GP-based model). Results: Compared with the GP-based model, the Korean model showed a lower RMSE (11.2 vs. 13.8 months; P = 0.004) and MAE (8.2 vs. 10.5 months; P = 0.002), a higher proportion of bone age predictions within 18 months of chronological age (88.3% vs. 82.2%; P = 0.031) for Institution 1, and a lower MAE (9.5 vs. 11.0 months; P = 0.022) and higher proportion of bone age predictions within 6 months (44.5% vs. 36.4%; P = 0.044) for Institution 2. Conclusion: The Korean model trained using the chronological ages of Korean children and adolescents without known bone development-affecting diseases/conditions as labels performed better in bone age assessment than the GP-based model in the Korean pediatric population. Further validation is required to confirm its accuracy.

• Korean Journal of Radiology
• /
• v.20 no.5
• /
• pp.719-728
• /
• 2019

Objective: To investigate the diagnostic validity of coronary computed tomography angiography (cCTA) in vasospastic angina (VA) and factors associated with discrepant results between invasive coronary angiography with the ergonovine provocation test (iCAG-EPT) and cCTA. Materials and Methods: Of the 1397 patients diagnosed with VA from 2006 to 2016, 33 patients (75 lesions) with available cCTA data from within 6 months before iCAG-EPT were included. The severity of spasm (% diameter stenosis [%DS]) on iCAGEPT and cCTA was assessed, and the difference in %DS (Δ%DS) was calculated. Δ%DS was compared after classifying the lesions according to pre-cCTA-administered sublingual nitroglycerin (SL-NG) or beta-blockers. The lesions were further categorized with %DS ≥ 50% on iCAG-EPT or cCTA defined as a significant spasm, and the diagnostic performance of cCTA on identifying significant spasm relative to iCAG-EPT was assessed. Results: Compared to lesions without SL-NG treatment, those with SL-NG treatment showed a higher Δ%DS (39.2% vs. 22.1%, p = 0.002). However, there was no difference in Δ%DS with or without beta-blocker treatment (35.1% vs. 32.6%, p = 0.643). The significant difference in Δ%DS associated with SL-NG was more prominent in patients who were aged < 60 years, were male, had body mass index < 25 kg/m², and had no history of hypertension, diabetes, or dyslipidemia. Based on iCAG-EPT as the reference, the per-lesion-based sensitivity, specificity, positive predictive value, negative predictive value, and accuracy of cCTA for VA diagnosis were 7.5%, 94.0%, 60.0%, 47.1%, and 48.0%, respectively. Conclusion: For patients with clinically suspected VA, confirmation with iCAG-EPT needs to be considered without completely excluding the diagnosis of VA simply based on cCTA results, although further prospective studies are required for confirmation.

• The Journal of the Convergence on Culture Technology
• /
• v.10 no.2
• /
• pp.215-224
• /
• 2024

The purpose of this study was to examine research trends related to neonatal simulation practice education of domestic nursing students. It was a descriptive research study. For literature collection, a total of 17 journals were selected as a result of a search using ('Newborn Simulation') AND ('Nursing Student' OR 'Nursing College Student' OR 'Student Nurse') in 6 domestic electronic databases. The research results showed that it started with 7 journals from 2011 to 2015 and decreased slightly to 5 journals from 2016 to 2020 and 5 journals from 2021 to 2023. The research design was mostly quantitative with a total of 16 journals(94%). Among them, there were 15 intervention journals(88%), 1 descriptive research journals(6%), and 1 mixed method journals(6%). The key topics in simulation practice were high-risk newborns with 9 journals(52%), respiratory distress syndrome in neonatal intensive care units appeared with 3 journals(18%), neonatal care with 3 journals(18%), normal newborn care with 1 journal(6%), and neonatal emergency airway care with 1 journals(6%). The main outcome variables were clinical performance, accounting for 5 journals(19.2%), followed by practice satisfaction 3 journals(11.5%). clinical competency and practice satisfaction were found to have significant positive effects. In conclusion, various research methods are required, such as expansion of nursing students' neonatal simulation practice education, repeated research, and qualitative research.

• The Journal of the Convergence on Culture Technology
• /
• v.10 no.2
• /
• pp.201-208
• /
• 2024

In this study, we investigated whether the evacuation time according to the exit installation standards specified in the building code during a food factory fire is compatible with the evacuation time based on the performance-based design specified by the fire department, in order to determine if evacuation safety is ensured. We used the Pathfinder program to confirm the evacuation time, and experimented with three scenarios for exit installation standards towards the outside of the building: 60m, 80m, and 100m. The target building in the experiment corresponded to the building code's exit installation standard of 100m from each dwelling. The experimental results showed tt in the cases of 80m and 100m, ASET exceeded RSET, indicating tt evacuation safety was not ensured, while in the case of 60m, evacuation safety was maintained. Through this study, it was confirmed tt even when the exit installation standards towards the outside of the building are met, evacuation safety may not be guaranteed.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.26 no.1
• /
• pp.1-17
• /
• 2024

Analyzing the tunnel excavation behavior and its effect on the surrounding ground involves large deformation behavior. Therefore, in order to properly simulate the tunnel excavation process and rigorously investigate the actual effect of excavation on surrounding ground and tunnel structure large deformation analysis method is required. In this study, two major numerical approaches capable of considering large deformations behavior were applied to investigate the effect of tunnel boring machine excavation on the surrounding ground: coupled Eulerian-Lagrangian (CEL) and the automatic remeshing (AR) method. Relative performance of both approaches was evaluated through the ground response due to TBM excavation. The ground response will be quantified by estimating the range of the excavation damaged zone (EDZ). By comparing the results, the range of the EDZ will be suggested on the vertical and horizontal direction along the TBM excavation surface. Based on the computed results, it was found that the size of EDZ around the excavation surface and the tendencies was in good agreement among the two approaches. Numerical results clearly show that the size of the EDZ around the tunnel tends to be larger for rock with higher RMR rating. The size of the EDZ is found to be direct proportional to the tunnel diameter, whereas the depth of the tunnel is inversely proportional due to higher confinement stress around the excavation surface.

• Resources Recycling
• /
• v.33 no.3
• /
• pp.38-47
• /
• 2024

Molybdenite is the primary molybdenum resource and is extracted via flotation due to its unique hydrophobic surface. Meanwhile, the grade and crystal size of mined molybdenite are decreasing. As a result, the size of the molybdenum ore required for liberation is decreasing, and the flotation process's feed size input is also decreasing. Therefore, in order to secure molybdenum, it is necessary to perform research on the flotation for the fine molybdenite. In this study, we developed a method to enhance the flotation efficiency of fine molybdenite particles in the range of 5-30 ㎛. The methodology involved implementing bubble size reduction and particle aggregation. Through simulations of bubble-particle collision probability and flotation experiments, we were able to find the ranges of bubble size and particle aggregate size that make fine particles float more effectively. This range provided the conditions for effective flotation of fine molybdenite particles. Therefore, we will implement the flotation conditions established in this study for fine molybdenum ore to improve the flotation process in molybdenum mineral processing plants in the future.

• The Journal of the Convergence on Culture Technology
• /
• v.10 no.4
• /
• pp.645-661
• /
• 2024

Today, the development of new technologies due to the 4th industrial revolution requires work performance methods such as non-face-to-face collaboration. In response to this, various VR collaboration tools are emerging, but VR collaboration tools for brainstorming, which are used in collaboration or design development work, are not provided. Therefore, despite the advantages and possibilities of VR for non-face-to-face collaboration, there are limitations in practical use. Accordingly, the development of VR collaboration tools in a digitalized work environment is necessary, and research on UI design development for this is required. The purpose of this study is to propose a VR collaboration tool prototype by developing an interaction UI design that applies user hand behavior elements that appear during collaboration sessions through user research. This study was a qualitative study. The research method was to conduct user research through observation and in-depth interviews, and as a result of analyzing the data obtained from this, five types of user hand behavior elements were derived. In this study, an interaction UI design was developed that reflects hand gestures as behavioral elements. And using Unity and the Oculus Integration SDK Kit, we created a prototype VR collaboration tool that can be used without a controller. As a result of conducting a user evaluation of the prototype produced in this study, it was found that users had difficulty making hand gestures accurately, and it was possible to find areas for improvement in UI design. It is expected that this study will help develop interaction UI design for VR collaboration tools that can increase work efficiency.

• Journal of the Korean Geotechnical Society
• /
• v.40 no.4
• /
• pp.61-68
• /
• 2024

Monitoring the injection degree of biopolymers in soils is required in estimating the performance of biopolymer-treated grounds. In this study, the degree of saturation and injection process of biopolymer solutions in sandy soils were evaluated using electrical resistivity. To assess the changes in electrical resistivity according to the contents of the biopolymer solutions, electrical resistivities were measured for Jumunjin sand-xanthan gum biopolymer solution (weight concentration of 0.5%) mixtures with different degrees of saturation of 20%, 40%, 60%, 80%, and 100%. In addition, electrical resistivities were measured at eight layers in oven-dried Jumunjin sand during the upward injection of the xanthan gum biopolymer solution to monitor the injection process. Experimental results showed that the electrical resistivity decreased as the degree of saturation of the mixture increased, and their relationship was constructed. During the injection of the xanthan gum biopolymer solution into the sandy soils, the electrical resistivity decreased and converged and the degree of saturation at each layer could be estimated on the basis of the above-constructed relationship. This study demonstrated that electrical resistivity may be an effective physical property for monitoring the injection degree of biopolymer solutions in the ground.