• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.46 no.2
• /
• pp.22-31
• /
• 2023

Governments around the world are enacting laws mandating explainable traceability when using AI(Artificial Intelligence) to solve real-world problems. HAI(Human-Centric Artificial Intelligence) is an approach that induces human decision-making through Human-AI collaboration. This research presents a case study that implements the Human-AI collaboration to achieve explainable traceability in governmental data analysis. The Human-AI collaboration explored in this study performs AI inferences for generating labels, followed by AI interpretation to make results more explainable and traceable. The study utilized an example dataset from the Ministry of Oceans and Fisheries to reproduce the Human-AI collaboration process used in actual policy-making, in which the Ministry of Science and ICT utilized R&D PIE(R&D Platform for Investment and Evaluation) to build a government investment portfolio.

• Journal of Animal Science and Technology
• /
• v.65 no.3
• /
• pp.627-637
• /
• 2023

As the population and income levels rise, meat consumption steadily increases annually. However, the number of farms and farmers producing meat decrease during the same period, reducing meat sufficiency. Information and Communications Technology (ICT) has begun to be applied to reduce labor and production costs of livestock farms and improve productivity. This technology can be used for rapid pregnancy diagnosis of sows; the location and size of the gestation sacs of sows are directly related to the productivity of the farm. In this study, a system proposes to determine the number of gestation sacs of sows from ultrasound images. The system used the YOLOv7-E6E model, changing the activation function from sigmoid-weighted linear unit (SiLU) to a multi-activation function (SiLU + Mish). Also, the upsampling method was modified from nearest to bicubic to improve performance. The model trained with the original model using the original data achieved mean average precision of 86.3%. When the proposed multi-activation function, upsampling, and AutoAugment were applied, the performance improved by 0.3%, 0.9%, and 0.9%, respectively. When all three proposed methods were simultaneously applied, a significant performance improvement of 3.5% to 89.8% was achieved.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2021.06a
• /
• pp.146-146
• /
• 2021

A contamination event occurring in water distribution networks (WDNs) needs to be handled with the appropriate mitigation strategy to protect public health safety and ensure water supply service continuation. Typically the mitigation phase consists of contaminant sensing, public warning, network inspection, and recovery. After the contaminant source has been detected and treated, contaminants still exist in the network, and the contaminated water should be flushed out. The recovery period is critical to remove any lingering contaminant in a rapid and non-detrimental manner. The contaminant flushing can be done in several ways. Conventionally, the opening of hydrants is applied to drain the contaminant out of the system. Relying on advanced information and communication technology (ICT) on WDN management, warning and information can be distributed fast through electronic media. Water utilities can inform their customers to participate in the contaminant flushing by opening and closing their house faucets to drain the contaminated water. The household draining strategy consists of determining sectors and timeslots of the WDN users based on hydraulic simulation. The number of sectors should be controlled to maintain sufficient pressure for faucet draining. The draining timeslot is determined through hydraulic simulation to identify the draining time required for each sector. The effectiveness of the strategy is evaluated using three measurements, such as Wasted Water (WW), Flushing Duration (FD), and Pipe Erosion (PE). The optimal draining strategy (i.e., group and timeslot allocation) in the WDN can be determined by minimizing the measures.

• Convergence Security Journal
• /
• v.22 no.4
• /
• pp.147-159
• /
• 2022

This study conducted a patent analysis to explore the trend of technology development in the field of smart car security. As a result of the analysis, it was confirmed that along with the growth of the smart car market, the development of smart car security related technology is also increasing. In particular, as related technology development has been rapidly taking place in recent years, it has been confirmed that competition among leading smart car countries and major companies is also expanding due to the commercialization of smart car. This study is meaningful in that it examines trends related to smart car security through quantitative analysis using patent data and presents implications accordingly.

• Educational Technology International
• /
• v.8 no.1
• /
• pp.57-69
• /
• 2007

The advantages of the Internet enable teachers in the world to break the communication barriers between their schools and collaborate with each other, giving them opportunities for richer educational practices than ever accomplished. I assume that collaborative learning like an international exchange naturally lead the students to acquire the knowledge to communicate with their peers using ICT skills. In this paper, two international exchange projects that have years of practice are reported, i.e., new types of collaborative education projects that the development of the Internet has enabled us to carry out. The international exchanges reported here have been possible because both students and teachers have effectively used the various functions of the Internet. To use English as a "common international communication language" is particularly important for the youth in Asia, and the students have come to realize the importance of English as a communication language through these projects. Also, since these practices are based on the infrastructure of the Internet, they have elucidated what kind of Internet use produces richer educational results .At the final stage of the exchanges, "joint presentation in English" is designed. Students communicate and collaborate over the network, and finally meet with each other and try to give a presentation as a product of their collaborative work. The files and scenes of their presentations are stored on the network and used as educational materials in Asia as well as models for the activities in the following years. We will report how to design international exchange education in this Internet age.

• The Journal of the Convergence on Culture Technology
• /
• v.9 no.5
• /
• pp.737-745
• /
• 2023

This paper discusses a study on developing an artificial intelligence model to detect incidents of fires in distribution switchboard using thermal images. The objective of the research is to preprocess collected thermal images into suitable data for object detection models and design a model capable of determining the occurrence of fires within distribution panels. The study utilizes thermal image data from AI-HUB's industrial complex for training. Two CNN-based deep learning object detection algorithms, namely Faster R-CNN and RetinaNet, are employed to construct models. The paper compares and analyzes these two models, ultimately proposing the optimal model for the task.

• Journal of the Korean Society of Industry Convergence
• /
• v.26 no.5
• /
• pp.833-844
• /
• 2023

As technology convergence is recognized as a driver of innovation, the identification of technology convergence opportunities is critical to expanding a firm's technology portfolio. Recently, wearable technology has emerged as an important factor in creating new business opportunities and providing technology investment alternatives for firms in the era of Industry 4.0. Against this background, this study provides a new patent analysis framework for identifying and proposing technology convergence opportunities in the wearable field. Using 8,621 patents filed between 2011 and 2021, a case study was conducted to identify technological convergence opportunities by applying Word2Vec algorithm. The analysis framework can be divided into four stages, with the final stage recommending potential technology convergence opportunities for a specific candidate firm's technology area by calculating similarities between technology codes. This study aims to better understand the current status of wearable technology development as well as to propose a new methodology for capturing technology convergence opportunities in the wearable industry. The case study result suggests that the convergence of healthcare and ICT may provide new development opportunities. Furthermore, the results are expected to provide alternative perspectives on the development of new markets and technologies using wearable technology and can support the strategic decision-making on future technology planning in the wearable field.

• Journal of the Korean Society of Systems Engineering
• /
• v.20 no.spc1
• /
• pp.45-55
• /
• 2024

Amidst the challenges of the global economy, this paper examines the investment tendencies of professional angel investors, who provide venture capital and management consulting, and explores strategies to revitalize angel investment. According to the research findings, professional angel investors are generally older and more educated than regular angel investors, and they are concentrated in the metropolitan region. Additionally, their investment performance before and after registration remains similar, with investment amounts concentrated between 50 million and 100 million won. Their investment portfolios focus on ICT services, bio/medical, and distribution/service sectors. Based on these findings, policy and institutional support measures are required to revitalize angel investment, including easing registration requirements for professional angel investors, expanding tax benefits related to angel investment, strengthening the provision of information and education related to angel investment, and enhancing angel investment networking. This study is expected to contribute to the revitalization of the venture startup ecosystem and economic growth through the revitalization of angel investment.

• International Journal of Advanced Culture Technology
• /
• v.12 no.2
• /
• pp.167-179
• /
• 2024

This study addresses the challenge of objectively evaluating the performance of early-stage startups amidst limited information and uncertainty. Focusing on companies selected by TIPS, a leading private sector-driven startup support policy in Korea, the research develops a new indicator to assess technological efficiency. By analyzing various input and output variables collected from Crunchbase and KIND (Korea Investor's Network for Disclosure System) databases, including technology use metrics, patents, and Crunchbase rankings, the study derives technological efficiency for TIPS-selected startups. A prediction model is then developed utilizing machine learning techniques such as Random Forest and boosting (XGBoost) to classify startups into efficiency percentiles (10th, 30th, and 50th). The results indicate that prediction accuracy improves with higher percentiles based on the technical efficiency index, providing valuable insights for evaluating and predicting startup performance in early markets characterized by information scarcity and uncertainty. Future research directions should focus on assessing growth potential and sustainability using the developed classification and prediction models, aiding investors in making data-driven investment decisions and contributing to the development of the early startup ecosystem.

• Journal of the Korea Safety Management & Science
• /
• v.26 no.1
• /
• pp.1-8
• /
• 2024

This study explores the impact of technostress on the intention to use telemedicine applications (apps) in the post-COVID19 era, a period marked by the rapid popularization of such apps to mitigate COVID19 infection risks. Utilizing the Technology Acceptance Model (TAM), the study identifies variables and proposes a research model. A questionnaire survey involving 364 adults is analyzed through Partial Least Squares-Structural Equation Modeling. Results indicate positive significance for variables linked to the TAM (perceived usefulness, perceived ease of use, attitude, and intention to use). Notably, techno-complexity negatively affects perceived ease of use, while techno-unreliability negatively impacts perceived usefulness and ease of use. Surprisingly, techno-uncertainty has a positive effect on both perceived usefulness and ease of use. Techno-overload, although negatively impacting perceived usefulness and ease of use, does not reach statistical significance. The study underscores the need to consider both positive and negative aspects, including technostress, when evaluating telemedicine app usage. Additionally, recognizing the varying impact of technostress based on users' ICT(Information and Communication Technology) confidence levels is crucial. Overall, these findings contribute academically to telemedicine app adoption literature and hold industrial significance by providing a user perspective on these apps.