• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.41 no.6
• /
• pp.751-760
• /
• 2021

Most bridges in Korea are over 20 years old, and many problems linked to their deterioration are being reported. The current practice for bridge inspection mainly depends on expert evaluation, which can be subjective. Recent studies have introduced data-driven methods using building information modeling, which can be more efficient and objective, but these methods require manual procedures that consume time and money. To overcome this, this study developed an image-based automaticbridge component classification network to reduce the time and cost required for converting the visual information of bridges to a digital model. The proposed method comprises two convolutional neural networks. The first network estimates the type of the bridge based on the superstructure, and the second network classifies the bridge components. In avalidation test, the proposed system automatically classified the components of 461 bridge images with 96.6 % of accuracy. The proposed approach is expected to contribute toward current bridge maintenance practice.

• The Journal of the Korea Contents Association
• /
• v.21 no.11
• /
• pp.135-144
• /
• 2021

Recently, data-driven decision-making technology has become a key technology leading the data industry, and machine learning technology for this requires high-quality training datasets. However, real-world data contains missing values for various reasons, which degrades the performance of prediction models learned from the poor training data. Therefore, in order to build a high-performance model from real-world datasets, many studies on automatically imputing missing values in initial training data have been actively conducted. Many of conventional machine learning-based imputation techniques for handling missing data involve very time-consuming and cumbersome work because they are applied only to numeric type of columns or create individual predictive models for each columns. Therefore, this paper proposes a new data imputation technique called 'Denoising Self-Attention Network (DSAN)', which can be applied to mixed-type dataset containing both numerical and categorical columns. DSAN can learn robust feature expression vectors by combining self-attention and denoising techniques, and can automatically interpolate multiple missing variables in parallel through multi-task learning. To verify the validity of the proposed technique, data imputation experiments has been performed after arbitrarily generating missing values for several mixed-type training data. Then we show the validity of the proposed technique by comparing the performance of the binary classification models trained on imputed data together with the errors between the original and imputed values.

• KIPS Transactions on Software and Data Engineering
• /
• v.11 no.8
• /
• pp.331-338
• /
• 2022

Successor representation (SR) is a model of human reinforcement learning (RL) mimicking the underlying mechanism of hippocampal cells constructing cognitive maps. SR utilizes these learned features to adaptively respond to the frequent reward changes. In this paper, we evaluated the performance of SR under the context where changes in latent variables of environments trigger the reward structure changes. For a benchmark test, we adopted SR-Dyna, an integration of SR into goal-driven Dyna RL algorithm in the 2-stage Markov Decision Task (MDT) in which we can intentionally manipulate the latent variables - state transition uncertainty and goal-condition. To precisely investigate the characteristics of SR, we conducted the experiments while controlling each latent variable that affects the changes in reward structure. Evaluation results showed that SR-Dyna could learn to respond to the reward changes in relation to the changes in latent variables, but could not learn rapidly in that situation. This brings about the necessity to build more robust RL models that can rapidly learn to respond to the frequent changes in the environment in which latent variables and reward structure change at the same time.

• Korean Journal of Culture and Social Issue
• /
• v.17 no.4
• /
• pp.435-459
• /
• 2011

The present study explored Korean parents' perceptions of and behavior toward game use among teenagers in Korea. A total of 600 Korean mothers of teenagers residing in Seoul and five other metropolitan areas participated in the survey. The survey was constructed based on five categories of variables, including the overall perception of games and game use, specific attitudes toward game use, cognitions about and attitudes toward game addiction, factors predicting parental monitoring of children's game use, and views and opinions about what needs to be done to promote healthy game cultures as well as to prevent problematic game use among teenagers in Korea. Results indicate that the respondents' overall perceptions of and attitudes toward games and game use are negative. In contrast, attitudes toward game use of the respondent's own child are contingent upon various comparison standards. Results also indicate that the respondents tend to overestimate the possibility that their own child is addicted to games, and their perceptions of game addiction are based on a narrow range of behavioral symptoms. Additional analyses indicate that parental monitoring of teenagers' game use can be predicted by the theoretical model driven from Ajzen(1991)'s theory of planned behavior. Finally, results also indicate that, in order to deal with the problems associated with teenagers' game use, proactive approaches to promote healthy game cultures as well as various initiatives to prevent problematic game use are necessary. Implications of the findings and future direction were discussed.

• The Journal of Bigdata
• /
• v.6 no.2
• /
• pp.71-84
• /
• 2021

Since small and medium-sized enterprises fell short of the securement of technological competitiveness in the field of big data and artificial intelligence (AI) field-core technologies of the Fourth Industrial Revolution, it is important to strengthen the competitiveness of the overall industry through technology commercialization. In this study, we aimed to propose a priority related to technology transfer and commercialization for practical use of public research results. We utilized public research performance information, improving missing values of 6T classification by deep learning model with an ensemble method. Then, we conducted topic modeling to derive the converging fields of big data and AI. We classified the technology fields into four different segments in the technology portfolio based on technology activity and technology efficiency, estimating the potential of technology commercialization for those fields. We proposed a priority of technology commercialization for 10 detailed technology fields that require long-term investment. Through systematic analysis, active utilization of technology, and efficient technology transfer and commercialization can be promoted.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.28 no.4D
• /
• pp.469-476
• /
• 2008

Recently, TOD gains popularity as a traffic solution measure of high density urban regeneration projects. The purpose of this study is to investigate traffic impacts of high density TOD projects, and to identify the issues to be resolved. For a case study, it chooses Gangnamgucheong station in Gangnam area served by two subway lines, and designates 400m radius from the station as a site for high-density development. The MOEs chosen for this study is traffic volume, time, distance, speed, and mode share. The SECOM model is adopted for traffic simulation. The analysis results show that high-density TOD is an effective tool for traffic improvement even with only one station area being implemented. It is found that the traffic volume increases near the station in nature where high-density development occurs, but it declines overall in the rest of Gangam area. The total travel time and distance of passenger vehicles decline, meaning that the traffic condition becomes better than before. With regulation on parking supply, the improvement becomes more vivid. In terms of the changes of traffic speed, both alternatives show 4.1% increase in speed, but the difference between alternatives is not quite noticeable because of the induced vehicle demand driven to the streets with improved traffic condition. The mode share changes occur for the benefit of subway ridership, because the study station is equipped with two subway line services. When mixed with parking supply restriction, the impact becomes clearer.

• Asia-Pacific Journal of Business Venturing and Entrepreneurship
• /
• v.19 no.2
• /
• pp.1-11
• /
• 2024

In the midst of the current turbulent global economy, traditional investment metrics are undergoing a metamorphosis, signaling the onset of what's often referred to as an "Investment cold season". Early-stage startups, despite their boundless potential, grapple with immediate revenue constraints, intensifying their pursuit of critical investments. While financial indicators once took center stage in investment evaluations, a notable paradigm shift is underway. Organizational culture, once relegated to the sidelines, has now emerged as a linchpin in forecasting a startup's resilience and enduring trajectory. Our comprehensive research, integrating insights from CVF and OCAI, unveils the intricate relationship between organizational culture and its magnetic appeal to investors. The results indicate that startups with a pronounced external focus, expertly balanced with flexibility and stability, hold particular allure for investment consideration. Furthermore, the study underscores the pivotal role of adhocracy and market-driven mindsets in shaping investment desirability. A significant observation emerges from the study: startups, whether they secured investment or failed to do so, consistently display strong clan culture, highlighting the widespread importance of nurturing a positive employee environment. Leadership deeply anchored in market culture, combined with an unwavering commitment to innovation and harmonious organizational practices, emerges as a potent recipe for attracting investor attention. Our model, with an impressive 88.3% predictive accuracy, serves as a guiding light for startups and astute investors, illuminating the intricate interplay of culture and investment success in today's economic landscape.

• BMB Reports
• /
• v.57 no.6
• /
• pp.281-286
• /
• 2024

Adult hippocampal neurogenesis plays a pivotal role in maintaining cognitive brain function. However, this process diminishes with age, particularly in patients with neurodegenerative disorders. While small, non-coding microRNAs (miRNAs) are crucial for hippocampal neural stem (HCN) cell maintenance, their involvement in neurodegenerative disorders remains unclear. This study aimed to elucidate the mechanisms through which miRNAs regulate HCN cell death and their potential involvement in neurodegenerative disorders. We performed a comprehensive microarray-based analysis to investigate changes in miRNA expression in insulin-deprived HCN cells as an in vitro model for cognitive impairment. miR-150-3p, miR-323-5p, and miR-370-3p, which increased significantly over time following insulin withdrawal, induced pronounced mitochondrial fission and dysfunction, ultimately leading to HCN cell death. These miRNAs collectively targeted the mitochondrial fusion protein OPA1, with miR-150-3p also targeting MFN2. Data-driven analyses of the hippocampi and brains of human subjects revealed significant reductions in OPA1 and MFN2 in patients with Alzheimer's disease (AD). Our results indicate that miR-150-3p, miR-323-5p, and miR-370-3p contribute to deficits in hippocampal neurogenesis by modulating mitochondrial dynamics. Our findings provide novel insight into the intricate connections between miRNA and mitochondrial dynamics, shedding light on their potential involvement in conditions characterized by deficits in hippocampal neurogenesis, such as AD.

• Journal of Venture Innovation
• /
• v.7 no.2
• /
• pp.101-123
• /
• 2024

Since COVID-19 crisis, health concerns and the need for interpersonal activities have driven many people to engage in leisure activities, which has naturally led to a steady increase in the participation rate of life sports. However, the start-up rate of sports facilities is decreasing and the closure rate is steadily increasing, and to survive in the over-competitive situation, sports facility operators need to develop and provide services with competitive advantages and come up with differentiated marketing plans. The purposes of this study were to (a) identify rapport-building behaviors for bring about relationship quality, customer satisfaction and customer trust, to a service provider in the sports leisure service environment (b) examine the ways in which customer satisfaction and customer trust induces positive behavior intentions in the sports leisure service environment, and (c) empirically verify the path of rapport- building behaviors through customer quality to continuance intention and WTPP(willing to pay premium price). The proposed conceptual model was empirically tested via structural equation modeling analysis using data collected from 350 adults who enjoy sports leisure services nationwide. Based on data analysis, firstly, attentive behavior, connecting behavior, courteous behavior, and information sharing behavior, were found to have a positive effect on relationship quality ,customer satisfaction and customer trust. Second, customer satisfaction was found to have a positive effect on both continuance intention and WTPP. Third, customer trust, a subcomponent of relationship quality, was found to have a positive effect on continuance intention, but not on WTPP. The findings of this study show that, first, rapport building with customers is important for sustainable growth management in the increasingly competitive sports and leisure service environment.

• Journal of Internet Computing and Services
• /
• v.25 no.4
• /
• pp.23-37
• /
• 2024

Digital twin is an M&S (Modeling and Simulation) technology designed to solve or optimize problems in the real world by replicating physical objects in the real world as virtual objects in the digital world and predicting phenomena that may occur in the future through simulation. Digital twins have been elaborately designed and utilized based on data collected to achieve specific purposes in large-scale environments such as cities and industrial facilities. In order to apply this digital twin technology to real life and expand it into user-customized service technology, practical but sensitive issues such as personal information protection and personalization of simulations must be resolved. To solve this problem, this paper proposes a federated learning-based accelerated client training method (FACTS) for personalized digital twins. The basic approach is to use a cluster-driven federated learning training procedure to protect personal information while simultaneously selecting a training model similar to the user and training it adaptively. As a result of experiments under various statistically heterogeneous conditions, FACTS was found to be superior to the existing FL method in terms of training speed and resource efficiency.