• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.47 no.2
• /
• pp.30-39
• /
• 2024

This study introduces a novel approach for identifying potential failure risks in missile manufacturing by leveraging Quality Inspection Management (QIM) data to address the challenges presented by a dataset comprising 666 variables and data imbalances. The utilization of the SMOTE for data augmentation and Lasso Regression for dimensionality reduction, followed by the application of a Random Forest model, results in a 99.40% accuracy rate in classifying missiles with a high likelihood of failure. Such measures enable the preemptive identification of missiles at a heightened risk of failure, thereby mitigating the risk of field failures and enhancing missile life. The integration of Lasso Regression and Random Forest is employed to pinpoint critical variables and test items that significantly impact failure, with a particular emphasis on variables related to performance and connection resistance. Moreover, the research highlights the potential for broadening the scope of data-driven decision-making within quality control systems, including the refinement of maintenance strategies and the adjustment of control limits for essential test items.

• Asia-Pacific Journal of Business
• /
• v.15 no.2
• /
• pp.1-22
• /
• 2024

Purpose - The Chinese fan community includes a significant number of young and middle-aged individuals, playing a crucial role in emotional mobilization and social engagement. In recent years, the impact of Celebrity Pairing or Character Pairing (CP) on Weibo has grown notably, partly due to features like Super Topics and Hot Searches. This phenomenon has enhanced fan engagement, resulting in heightened participation in discussions and interactions on the platform. Our study targets CP fans of movies and television dramas on Weibo and aims to identify the factors that drive their emotional sharing. Design/methodology/approach - The research methodology integrates Self-Determination Theory and Social Sharing of Emotion Theory within the EASI (Emotion, Attachment, and Social Integration) model. This approach aims to uncover how CP fans meet their emotional needs via social media and determine the factors influencing their sharing intentions and behaviours. Data were collected through online surveys, yielding 504 valid responses Findings - The analysis, performed with SPSS and Smart PLS software, reveals that self-determination, interpersonal relationships, and social media tolerance significantly affect fans' intentions to share content. Specifically, intrinsic motivation, driven by self-determination, is a critical factor in CP fans' propensity to share content, highlighting the importance of 'inward socialization.' Additionally, the study finds that external factors, like the social media environment, play a more minor role than internal motivators. Research implications or Originality - This research enhances quantitative research methodologies by identifying intrinsic and extrinsic motivations that satisfy the emotional needs of CP fans. It distinguishes between individual, interpersonal, and collective/social factors as motivational elements, providing insights into the emotional and psychological needs of the Chinese movie and TV drama fan community.

• Journal of Internet Computing and Services
• /
• v.25 no.4
• /
• pp.7-21
• /
• 2024

There are various machine learning techniques such as Reinforcement Learning, Deep Learning, Neural Network Learning, and so on. In recent, Large Language Models (LLMs) are popularly used for Generative AI based on Reinforcement Learning. It makes decisions with the most optimal rewards through the fine tuning process in a particular situation. Unfortunately, LLMs can not provide any explanation for how they reach the goal because the training is based on learning of black-box AI. Reinforcement Learning as black-box AI is based on graph-evolving structure for deriving enhanced solution through adjustment by human feedback or reinforced data. In this research, for mutually exclusive decision-making, Mutually Exclusive Learning (MEL) is proposed to provide explanations of the chosen goals that are achieved by a decision on both ends with specified conditions. In MEL, decision-making process is based on the tree-based structure that can provide processes of pruning branches that are used as explanations of how to achieve the goals. The goal can be reached by trade-off among mutually exclusive alternatives according to the specific contextual conditions. Therefore, the tree-based structure is adopted to provide feasible solutions with the explanations based on the pruning branches. The sequence of pruning processes can be used to provide the explanations of the inferences and ways to reach the goals, as Explainable AI (XAI). The learning process is based on the pruning branches according to the multi-dimensional contextual conditions. To deep-dive the search, they are composed of time window to determine the temporal perspective, depth of phases for lookahead and decision criteria to prune branches. The goal depends on the policy of the pruning branches, which can be dynamically changed by configured situation with the specific multi-dimensional contextual conditions at a particular moment. The explanation is represented by the chosen episode among the decision alternatives according to configured situations. In this research, MEL adopts the tree-based learning model to provide explanation for the goal derived with specific conditions. Therefore, as an example of mutually exclusive problems, employment process is proposed to demonstrate the decision-making process of how to reach the goal and explanation by the pruning branches. Finally, further study is discussed to verify the effectiveness of MEL with experiments.

• Journal of Climate Change Research
• /
• v.34 no.16
• /
• pp.6841-6853
• /
• 2021

The leading modes of the North Pacific jet (NPJ) variability include intensity changes and meridional shifts in jet position on low-frequency time scales. These leading modes of NPJ variability are closely associated with weather and climate conditions spanning from Asia to the United States. In this study, we investigated changes in the NPJ's role as a conduit for U.S. surface air temperature (SAT) anomalies during the boreal winter across the late 1990s. We found that the leading mode of NPJ variability changed from the NPJ intensity changes to meridional shifts in NPJ position across the late 1990s. It leads to the change in the role of the NPJ as a conduit for U.S. SAT anomalies. Before the late 1990s, the variability of NPJ intensity significantly impacted western U.S. SAT anomalies related to the anomalous surface cyclonic circulation over the North Pacific. After the late 1990s, however, the variability of the NPJ's meridional shift significantly influenced the eastern U.S. SAT anomalies in association with the anomalous surface cyclonic circulation over the northern North Pacific. Further analysis and model experiments revealed that the western to central North Pacific Ocean has been warming since the late 1990s and modulates atmospheric baroclinicity. This phenomenon mainly leads to a northward NPJ shift and implies that the eddy-driven mechanism on the NPJ's formation, which acts to enhance the meridional variability of NPJ position, becomes dominant. We conclude that this northward shift of NPJ could have contributed to enhancing the NPJ's meridional shift variability, significantly influencing the eastern U.S. SAT anomalies since the late 1990s.

• Wind and Structures
• /
• v.39 no.4
• /
• pp.271-285
• /
• 2024

The multiple-fan wind tunnel is an important facility for reproducing target wind field. Existing control methods for the multiple-fan wind tunnel can generate wind speeds that satisfy the target statistical characteristics of a wind field (e.g., power spectrum). However, the frequency-domain features cannot well represent the nonstationary winds of extreme storms (e.g., downburst). Therefore, this study proposes a multiple-fan wind tunnel control scheme based on Deep Reinforcement Learning (DRL), which will completely transform into a data-driven closed-loop control problem, to reproduce the target wind field in the time domain. Specifically, the control scheme adopts the Deep Deterministic Policy Gradient (DDPG) paradigm in which the strong fitting ability of Deep Neural Networks (DNN) is utilized. It can establish the complex relationship between the target wind speed time series and the current control strategy in the DRL-agent. To address the fluid memory effect of the wind field, this study innovatively designs the system state and control reward to improve the reproduction performance based on historical data. To validate the performance of the model, we established a simplified flow field based on Navier Stokes equations to simulate a two-dimensional numerical multiple-fan wind tunnel environment. Using the strategy of DRL decision maker, we generated a wind speed time series with minor error from the target under low Reynolds number conditions. This is the first time that the AI methods have been used to generate target wind speed time series in a multiple-fan wind tunnel environment. The hyperparameters in the DDPG paradigm are analyzed to identify a set of optimal parameters. With these efforts, the trained DRL-agent can simultaneously reproduce the wind speed time series in multiple positions.

• Korean Chemical Engineering Research
• /
• v.61 no.4
• /
• pp.523-541
• /
• 2023

As accessibility to 3D printers increases, there is a growing frequency of exposure to chemicals associated with 3D printing. However, research on the toxicity and harmfulness of chemicals generated by 3D printing is insufficient, and the performance of toxicity prediction using in silico techniques is limited due to missing molecular structure data. In this study, quantitative structure-activity relationship (QSAR) model based on data-centric AI approach was developed to predict the toxicity of new 3D printing materials by imputing missing values in molecular descriptors. First, MissForest algorithm was utilized to impute missing values in molecular descriptors of hazardous 3D printing materials. Then, based on four different machine learning models (decision tree, random forest, XGBoost, SVM), a machine learning (ML)-based QSAR model was developed to predict the bioconcentration factor (Log BCF), octanol-air partition coefficient (Log Koa), and partition coefficient (Log P). Furthermore, the reliability of the data-centric QSAR model was validated through the Tree-SHAP (SHapley Additive exPlanations) method, which is one of explainable artificial intelligence (XAI) techniques. The proposed imputation method based on the MissForest enlarged approximately 2.5 times more molecular structure data compared to the existing data. Based on the imputed dataset of molecular descriptor, the developed data-centric QSAR model achieved approximately 73%, 76% and 92% of prediction performance for Log BCF, Log Koa, and Log P, respectively. Lastly, Tree-SHAP analysis demonstrated that the data-centric-based QSAR model achieved high prediction performance for toxicity information by identifying key molecular descriptors highly correlated with toxicity indices. Therefore, the proposed QSAR model based on the data-centric XAI approach can be extended to predict the toxicity of potential pollutants in emerging printing chemicals, chemical process, semiconductor or display process.

• Journal of Korea Technology Innovation Society
• /
• v.19 no.1
• /
• pp.1-28
• /
• 2016

Current Korean innovation system is facing a new turning point while the growth-oriented and S&T provide-oriented development strategy. Accordingly, there are needs for not only system transition in various area, such as sustainable energy, agriculture, and rural area but also STI policy paradigm shift to create a new innovative pathway. Living lab is being discussed in European country as a new innovative model based on user participation and as a niche experiments for sustainable system transition. This study attempts to analyze the living lab cases which are for the purpose of energy transition, agriculture rural areas system transition, and STI policy paradigm shift. Based on this analysis, the implications were derived in Korea. European Suslab project, C@R project, and Taiwan living lab, promoted diverse transitional experiments successfully by collecting users' background and experiences from pre-planning stage and by maintaining the user-driven innovative actions within the whole development process. This result provides various suggestions to current Korean situation that central government and local governments are considering the introduction of living lab. Living lab can also be utilized as a strategic niche experiments for socio-technical system transition in region or country, as a mean of policy integration, and as a new regional innovation model. In addition, it can be an important platform to realize the policy integration reflecting the user and demand-side which are highlighted in recent innovative policy paradigm.

• Journal of Broadcast Engineering
• /
• v.20 no.1
• /
• pp.122-139
• /
• 2015

Though the digital transition of terrestrial TV has been completed, the transmission system for terrestrial radio has not been determined and terrestrial radio still keeps its analog transmission. This study, under coorientation model, aims to explore the cognitive difference in recognizing important factors to be considered in deciding the digital radio transmission system between the employees of terrestrial broadcasters and then crucial issues related to the factors are driven. It has been found that the most big cognitive difference among the employees of three major terrestrial broadcasters lies in selecting frequency band for digital radio transmission. But there was little difference of opinion on simultaneous production-transmission, efficiency of frequency usage, broadcast quality and standards of service. The most disputable point in transition to digital radio broadcasting is selecting the frequency band for digital radio between the frequency bands used for FM radio broadcast (88-108MHz), terrestrial DMB (VHF Ch7~13) and FM radio adjacent broadcast band (76~88MHz: VHF Ch5~6). So, the question concludes into the selection issue between DAB+, HD-Radio, and DRM+. To improve the quality of radio broadcasting service and enhance the satisfaction of listeners, it is desirable to allow to operate both production system and transmission station, to enhance high transmission efficiency with minimum transmission facility, and to permit new entrance of broadcasters.

• Herbal Formula Science
• /
• v.26 no.3
• /
• pp.207-221
• /
• 2018

Objectives : Present study investigated hepatoprotective effect of Haegan-jeon extract (HE) and tried to elucidate molecular mechanism involved. According to molecular mechanism, present study optimized herbal composition of HE (op-HE) and compared in vitro and in vivo hepatoprotective effects of op-HE to HE. Methods : For in vitro experiments, HepG2 cells were exposed to arachidonic acid (AA, $10{\mu}M$) and iron ($5{\mu}M$) for inducing oxidative stress. Cell viability, GSH contents, $H_2O_2$ production, mitochondrial membrane potential, immunoblot and reporter gene assay were performed to investigate cytoprotective effects and responsible molecular mechanisms. For in vivo experiments, hepatoprotective effect of HE and op-HE were assessed on $CCl_4-induced$ liver injury mice model. Results : HE pretreatment prevented AA+iron-mediated hepatocytes apoptosis. In addition, AA+iron-induced mitochondrial dysfunction, $H_2O_2$ production, glutathione depletion were reduced by HE pretreatment. In addition, nuclear factor erythroid 2-related factor 2 (Nrf2) phosphorylation, antioxidant response element (ARE)-driven reporter gene activity, and antioxidant genes expression were increased by HE. Based on reporter gene and MTT assays, we found that op-HE consisting three medicinal herbs also significantly increased transactivation of Nrf2 and reduced the AA+iron-mediated cytotoxicity. Moreover, in $CCl_4-induced$ liver injury mice model, HE-op had an ability to ameliorate $CCl_4-mediated$ increases in serum alanine transferase and aspartate aminotransferase activity, hepatic degeneration, inflammatory cell infiltration, and collagen deposition. Hepatoprotective effects of op-HE were comparable to those of HE. Conclusions : Present study suggests that op-HE as well as HE exhibit hepatoprotective effect against oxidative stress-mediated liver injury via Nrf2 activation.

• Health Policy and Management
• /
• v.10 no.2
• /
• pp.41-77
• /
• 2000

This study aimed at the analysis, from the perspective of rationality, of policy making process in the separation of prescribing and dispensing. This study is to identify the characteristics and problems of the policy process to introduce the new durg-prescription system, and make policy recommendations. In terms of separation of prescribing and dispensing, the development of policy making process can be divided into two periods; periods before and after the inauguration of the govemment of people. In the period before the govermment of poeple, one of the major characteristics of policy decision on the new system was the poweful influence of interset groups. At that time, the ministry lacked the problem-solving ability and commitment on the policy. Consequently, during the former period, the policy making process had been driven by interest groups. Therefore, the original purpose of the policy to secure the pulic health was lost. During the latter period, there was also the strong influence of interst groups, complexity of interest, the ministry's inability of problem solving. However, in this period, it is notable that this has drawn nation-wide attention, severl civic grouos have participated in the policy making process, and that the number and voice of these groups have remarkably increased. With regards to rationality, incrementalish model is highly sutable to explain the policy making process in the former period. But in the latter period when the new drugperscripition system became a national issue and civic groups began to participte in this matter more actively, rational model is more explanatory that incrementalism to understand the process. During the latter period, the original goal of this policy was not distored by a few interest groups thanks to the rapid development of civil movement and therebly a big influence of civic groups on the policy making. For that reson, a jigh level of rationality is found in the policy-making process of the latter period. Some suggestions to achieve the rationality in the policy making process based on the results of this study are as follows; Frist, the public's participation should be enered in the policy making process. Second, the govermment should make contiuns efforts to enhance its ability of long-term planning and policy implementation, and increase rationality of policy making process. Third, balance among interset groups should take place in the process of policy making. Forth, sound, constructive, and logical activity of interest groups is necessary to express and promote their interests.