• Applied Chemistry for Engineering
• /
• v.31 no.6
• /
• pp.624-629
• /
• 2020

For more effective temperature control of atmospheric plasma sprayed (APS) zirconia thermal barrier coating, understanding of the parameters, which influence the substrate temperature, is essential and also more numerical results based on the experimental data are required. This study aims to investigate the substrate temperature control during an APS process. The APS process deals with air-cooled systems, plasma-gas flow, powder feed rate, robot velocity, and substrate effect on the substrate surface temperature control during the process. This systematic approach will help to handle the temperature control, and thus lead to better coating quality.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.44 no.2
• /
• pp.15-23
• /
• 2021

Most of the open-source decision tree algorithms are based on three splitting criteria (Entropy, Gini Index, and Gain Ratio). Therefore, the advantages and disadvantages of these three popular algorithms need to be studied more thoroughly. Comparisons of the three algorithms were mainly performed with respect to the predictive performance. In this work, we conducted a comparative experiment on the splitting criteria of three decision trees, focusing on their interpretability. Depth, homogeneity, coverage, lift, and stability were used as indicators for measuring interpretability. To measure the stability of decision trees, we present a measure of the stability of the root node and the stability of the dominating rules based on a measure of the similarity of trees. Based on 10 data collected from UCI and Kaggle, we compare the interpretability of DT (Decision Tree) algorithms based on three splitting criteria. The results show that the GR (Gain Ratio) branch-based DT algorithm performs well in terms of lift and homogeneity, while the GINI (Gini Index) and ENT (Entropy) branch-based DT algorithms performs well in terms of coverage. With respect to stability, considering both the similarity of the dominating rule or the similarity of the root node, the DT algorithm according to the ENT splitting criterion shows the best results.

• Journal of Korea Society of Digital Industry and Information Management
• /
• v.18 no.4
• /
• pp.67-75
• /
• 2022

Recently, e-learning has been attracting significant attention due to COVID-19. However, while e-learning has many advantages, it has disadvantages as well. One of the main disadvantages of e-learning is that it is difficult for teachers to continuously and systematically monitor learners. Although services such as personalized e-learning are provided to compensate for the shortcoming, systematic monitoring of learners' concentration is insufficient. This study suggests a method to evaluate the learner's concentration by applying machine learning techniques. In this study, emotion and gaze data were extracted from 184 videos of 92 participants. First, the learners' concentration was labeled by experts. Then, statistical-based status indicators were preprocessed from the data. Random Forests (RF), Support Vector Machines (SVMs), Multilayer Perceptron (MLP), and an ensemble model have been used in the experiment. Long Short-Term Memory (LSTM) has also been used for comparison. As a result, it was possible to predict e-learners' concentration with an accuracy of 90.54%. This study is expected to improve learners' immersion by providing a customized educational curriculum according to the learner's concentration level.

• Journal of Platform Technology
• /
• v.11 no.1
• /
• pp.3-10
• /
• 2023

Unmanned Aerial Vehicles (UAVs) have gained significant attention in 5G and 6G wireless networks due to their high flexibility and low hardware costs. However, UAV communication is still challenged by blockage and energy consumption issues. Reconfigurable Intelligent Surfaces (RISs) have emerged as a promising solution to these challenges, enabling improved spectral efficiency and reduced energy consumption by transmitting signals to users who cannot receive signals because of the obstacles. Many previous studies have focused on minimizing power consumption and data transmission delay through phase shift and power optimization. This paper proposes an algorithm that maximizes the sum rate by including bandwidth optimization. Simulation results demonstrate the effectiveness of the proposed algorithm.

• Journal of the Korean Society of Industry Convergence
• /
• v.26 no.6_3
• /
• pp.1205-1213
• /
• 2023

This study delves into methods for enhancing the power efficiency of air compressor systems, with the primary objective of significantly impacting industrial energy consumption and environmental preservation. The paper scrutinizes Shinhan Airro Co., Ltd.'s power efficiency optimization technology and employs machine learning ensemble models to simulate power efficiency optimization. The results indicate that Shinhan Airro's optimization system led to a notable 23.5% increase in power efficiency. Nonetheless, the study's simulations, utilizing machine learning ensemble techniques, reveal the potential for a further 51.3% increase in power efficiency. By continually exploring and advancing these methodologies, this research introduces a practical approach for identifying optimization points through data-driven simulations using machine learning ensembles.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.26 no.5
• /
• pp.422-430
• /
• 2023

To build an automated system detecting toxic chemicals from Raman spectra, we have to obtain sufficient data of toxic chemicals. However, it usually costs high to gather Raman spectra of toxic chemicals in diverse situations. Tackling this problem, we develop methods to generate synthetic Raman spectra of DMMP and 2-CEES without actual experiments. First, we propose certain mathematical transforms to augment few original Raman spectra. Then, we train deep generative models to generate more realistic and diverse data. Analyzing synthetic Raman spectra of toxic chemicals generated by our methods through visualization, we qualitatively verify that the data are sufficiently similar to original data and diverse. For conclusion, we obtain a synthetic dataset of DMMP and 2-CEES with the proposed algorithm.

• Journal of Korean Society for Quality Management
• /
• v.51 no.4
• /
• pp.691-700
• /
• 2023

Purpose: This study aims to analyze the diffusion pattern of the Mongolian mobile phone market. In particular, we used a generalized diffusion model to explore the factors affecting market potenial. Methods: We used three diffusion models to estimate the number of mobile subscribers in Mongolia. Based on the Logistic model with the best fitness, we introduced time-varying market potential and explored the influence of various independent variables such as GDP and inflation. Results: Among the basic diffusion models, the Logistic model was the best in terms of estimation performance and statistical significance. The estimation results of the Generalized Logistic model confirm that investment in the telecommunication sector has a significant positive effect on market potential. The estimation of the Generalized Logistic model effectively describes the continuous growth of the Mongolian telecommunications market until recently. Conclusion: We have analyzed the diffusion pattern of the Mongolian telecommunications market and found that the amount of investment in the sector leads to the growth of the market size. This study is original in terms of its subject - Mongolian telecommunications market and methodology - time-varying market potential.

• The Journal of the Acoustical Society of Korea
• /
• v.43 no.5
• /
• pp.475-483
• /
• 2024

This paper examines the signal processing parameters of the field differencing method, a technique for estimating the source velocity or distance using a single receiver. The constraints that must be obeyed during the application of the field differencing method and the effect of the parameters on the velocity estimation performance were analyzed. Several cases identified in this study using the SWellEX-96 experiment data show that when applying the sound field differential technique, large errors may occur in the radial source velocity estimation results depending on parameter settings. The study confirmed that the influence of the processing parameters can vary depending on the signal frequency, and presented guidelines for selecting parameter values of the field differencing method for correct radial velocity estimation.

• Journal of Conservation Science
• /
• v.37 no.5
• /
• pp.440-450
• /
• 2021

Temperature and humidity data collection using real-time sensors and data loggers was conducted for integrated pest management in the collection storage and exhibition space of the Jeongnimsaji Museum, Buyeo. The real-time temperature and humidity monitoring system collected measurement data every 30 minutes and enabled real-time confirmation of the data through a linked application. If the temperature and humidity data measured in the real-time temperature and humidity monitoring system exceeds the set range, a push notification was sent to the mobile phone of the person in charge to provide status information to establish a continuous management system. Through this, it was possible to immediately recognize and take action when the temperature range exceeded the recommended relic temperature in August. We performed data visualization on the concentration of airborne fungus in the storage area and the inflow path and density of insects. Based on the recommended criteria presented by the National Institute of Cultural Heritage, The data on the spatial and temporal concentration of airborne fungus inside the collection storage were found to be maintained at a value below the standard recommended by the National Institute of Cultural Heritage (80 CFU/m³). Also, as a result of the insect inflow survey, no insects were captured inside the storage area, and in the case of the exhibition space, insects such as Scutigera coleoptrata, Loxoblemmus arietulus, Diestrammena asynamora, Koreoniscus racovitzai were captured. Based on this, as a result of visualization according to the individual density of captured insects by area, it was confirmed that the main inflow paths of insects were the external entrance and the toilet area.

• The Journal of the Convergence on Culture Technology
• /
• v.9 no.3
• /
• pp.311-320
• /
• 2023

This paper analyzes viewers' perception of investigative journalism before and after COVID-19, and examines the direction of investigative journalism using big data. Based on the previous research set as a social science model, the relationship between words related to big data TV current affairs programs and investigative journalism in this paper was investigated before and after the appearance of COVID-19. We visualized changes in viewers' perception of investigative journalism by analyzing text data obtained through the use of Textom, with TV current affairs programs and investigative journalism as keywords. Data was collected from 2017 to June 2022 and refined for analysis. We visualized connectivity centrality using Ucinet 6.0 and Netdraw, and clustered the number of keywords and their frequency using Concor analysis. Our study found a clear change in viewer perception before and after the pandemic. As an implication of this thesis, big data analysis was conducted with the investigative journalism as the main keyword, and the direction of the investigative journalism was presented based on the analysis. Furthermore, based on previous research, we suggest effective approaches for investigative journalism after the pandemic to better engage viewers.