• Journal of the Korea Society for Simulation
• /
• v.32 no.3
• /
• pp.43-53
• /
• 2023

In this detailed and comprehensive study, our primary focus has been placed on accurately gauging the number of visitors and their real-time locations in commercial spaces. Particularly, in a real cafe, using security cameras, we have developed a system that can offer live updates on available seating and predict future congestion levels. By employing YOLO, a real-time object detection and tracking algorithm, the number of visitors and their respective locations in real-time are also monitored. This information is then used to update a cafe's indoor map, thereby enabling users to easily identify available seating. Moreover, we developed a model that predicts the congestion of a cafe in real time. The sophisticated model, designed to learn visitor count and movement patterns over diverse time intervals, is based on Long Short Term Memory (LSTM) to address the vanishing gradient problem and Sequence-to-Sequence (Seq2Seq) for processing data with temporal relationships. This innovative system has the potential to significantly improve cafe management efficiency and customer satisfaction by delivering reliable predictions of cafe congestion to all users. Our groundbreaking research not only demonstrates the effectiveness and utility of indoor location tracking technology implemented through security cameras but also proposes potential applications in other commercial spaces.

• Journal of Intelligence and Information Systems
• /
• v.29 no.3
• /
• pp.383-400
• /
• 2023

Air pollution-related diseases are escalating worldwide, with the World Health Organization (WHO) estimating approximately 7 million annual deaths in 2022. The rapid expansion of industrial facilities, increased emissions from various sources, and uncontrolled release of odorous substances have brought air pollution to the forefront of societal concerns. In South Korea, odor is categorized as an independent environmental pollutant, alongside air and water pollution, directly impacting the health of local residents by causing discomfort and aversion. However, the current odor management system in Korea remains inadequate, necessitating improvements. This study aims to enhance the odor management system by analyzing 1,010,749 data points collected from odor sensors located in Osong, Chungcheongbuk-do, using an Ensemble-Based Multi-Region Integrated Odor Concentration Prediction Model. The research results demonstrate that the model based on the XGBoost algorithm exhibited superior performance, with an RMSE of 0.0096, significantly outperforming the single-region model (0.0146) with a 51.9% reduction in mean error size. This underscores the potential for increasing data volume, improving accuracy, and enabling odor prediction in diverse regions using a unified model through the standardization of odor concentration data collected from various regions.

• International conference on construction engineering and project management
• /
• 2009.05a
• /
• pp.525-536
• /
• 2009

The current residential process adheres to a traditional method of construction involving wood framing on-site on poured concrete foundations which has been widely applied in North America. A conventional residential construction process can include seventeen distinct stages ranging from stake-out to pre-occupancy inspection. The current practice possesses short comings including high construction material wastes, long scheduling timelines, adverse weather conditions, poor quality, low efficiencies and negative environmental impacts from transportation and equipment use. Over CAN $5 billion dollars was spent in the construction sector during 2007 in Canada. Previous findings in CO₂ emissions during the construction process of a conventional dwelling emphasize more than 45 tonnes of CO₂ emissions. Hence, in Alberta alone during 2007, almost 50,000 residential units would release more than two million tonnes of CO₂. These numbers demonstrate the economical and environmental impact in building construction and its relationship with CO₂ emissions. The aim of this paper is to quantify the CO₂ emissions from the current residential construction process in order to establish the baseline for CO₂ emission reduction opportunities. The quantification collection methodology will be approached by identifying the seventeen various stages of construction and quantifying the contributions of CO₂ from specific activities and their impacts of work for each stage. The approach of separating these into separate stages for collection will allow for independent opportunities for analysis from various independent contractors from the entire scope of work. The use of BIM will be implemented to efficiently quantify CO₂ emissions. Based on the CO₂ quantification baseline, emission reduction opportunities such as an industrialized construction process will be introduced that allows homebuilders to reduce the environmental and economical impact of home construction while enabling them to produce higher quality, more energy efficient homes in a safer and shorter period of time.

• Journal of Internet Computing and Services
• /
• v.24 no.4
• /
• pp.117-125
• /
• 2023

Flipped learning is an instructional approach that reverses the traditional order of in-class and after-class activities. It entails students studying course materials before attending class, and then utilizing class time for completing homework tasks. Due to collaborative support available from teachers and peers, flipped learning has gained extensive adoption in computer science and engineering courses, enabling students to effectively engage in homework assignments. Nevertheless, students are responsible for studying class materials independently, which can limit their understanding of advanced topics. We propose an approach that combines both flipped learning and the traditional method, allowing them to mutually enhance each other. In the proposed approach, students acquire foundational concepts prior to attending class, and subsequently delve into advanced topics during classroom sessions through lectures and guidance provided by the teacher. Afterward, students collaborate with their peers to solve problems that involve the application of the concepts they have learned, and exchange a variety of solutions and perspectives. We implemented the proposed approach in four computer science and engineering classes, spanning one to four semesters and observed an enhancement in students' comprehension and satisfaction levels. We anticipate implementation of the proposed approach across various computer science and engineering courses, while enhancing their overall quality.

• Journal of Korean Clinical Nursing Research
• /
• v.29 no.2
• /
• pp.198-209
• /
• 2023

Purpose: The purpose of this study was to develop a Korean Adult Patients Delirium Screening Tool (K-APDS) for those admitted to general wards, and to verify its reliability and validity. Methods: For the development of the tool, 12 items were derived through the results of literature review and focus group interviews with general ward nurses, and the content validity was confirmed by experts. To verify the reliability and validity of the developed tool, 317 adult patients who were admitted to general wards of three tertiary general hospitals from October to November 2022 were evaluated by the attending nurse and data were collected. Results: After factor analysis for construct validity verification, two factors were extracted, which explained 60.1% of the total variance. After the validation of the control group, the difference in the delirium incidence scores calculated using the K-APDS between the delirium group and non-delirium group was very significant (Z=-10.82, p<.001). To verify the criterion validity, K-APDS, Delirium Observation Screening, and Pearson's correlation coefficient were checked and found to be .94 (p<.001). The predictive validity test reported that the sensitivity was 91.1%, specificity was 82.4%, positive predictive value was 52.6%, and negative predictive value was 97.8%. The reliability of K-APDS was found to be high with Cronbach's ⍺=.91. Conclusion: K-APDS can screen for delirium with 2 or more points, excellent validity and reliability have been verified. Therefore, this tool could be applied immediately in the clinical field, and will contribute to the early detection of delirium, enabling rapid interventions.

• Journal of Korean Society of Coastal and Ocean Engineers
• /
• v.35 no.4
• /
• pp.75-83
• /
• 2023

Apart from implementing hardware solutions like raising the crest freeboard of coastal structures to efficiently counter wave-overtopping, there is a simultaneous requirement for software-driven disaster mitigation strategies. These tactics involve the swift and accurate dissemination of wave-overtopping information to the inland regions of coastal zones, enabling the regulation of evacuation procedures and movement. In this study, a method was proposed to estimate wave-overtopping by utilizing the temporal variation of wave heights exceeding the structure's crown level, with the aim of developing an on-site wave measurement system for providing wave-overtopping information in the field. Laboratory model experiments were conducted on vertical seawall structures to measure wave-overtopping volumes and wave runup heights under different wave conditions and structural freeboard variations. By assuming that the velocity of water inundation on the top of the structure during wave-overtopping events is equivalent to the long-wave velocity, an overtopping discharge coefficient was introduced. This coefficient was utilized to estimate the rate of wave-overtopping based on the temporal changes in wave runup heights measured at the top of the structure. Upon reasonably calculating the overtopping discharge coefficient, it was verified that the estimation of wave-overtopping could be achieved solely based on the wave runup heights.

• Korean Journal of Construction Engineering and Management
• /
• v.24 no.5
• /
• pp.52-62
• /
• 2023

The objective of this study is to propose an automated algorithm for precise cutting length of slab rebar complying with regulations such as anchorage length, standard hooks, and lapping length. This algorithm aims to improve the traditional manual quantity take-off process typically outsourced by external contractors. By providing accurate rebar quantity data at BBS(Bar Bending Schedule) level from the bidding phase, uncertainty in quantity take-off can be eliminated and reliance on out-sourcing reduced. In addition, the algorithm allows for early determination of precise quantities, enabling construction firms to preapre competitive and optimized bids, leading to increased profit margins during contract negotiations. The proposed algorithm not only streamlines redundant tasks across various processes, including estimating, budgeting, and BBS generation but also offers flexibility in handling post-contract structural drawing changes. In particular, the proposed algorithm, when combined with BIM, can solve the technical problems of using BIM in the early phases of construction, and the algorithm's formulas and shape codes that built as REVIT-based family files, can help saving time and manpower.

• International conference on construction engineering and project management
• /
• 2022.06a
• /
• pp.1243-1244
• /
• 2022

In recent years, the growing interest in off-site construction has led to factories scaling up their manufacturing and production processes in the construction sector. Consequently, continuous large-scale site monitoring in low-variability environments, such as prefabricated components production plants (precast concrete production), has gained increasing importance. Although many studies on computer vision-based site monitoring have been conducted, challenges for deploying this technology for large-scale field applications still remain. One of the issues is collecting and transmitting vast amounts of video data. Continuous site monitoring systems are based on real-time video data collection and analysis, which requires excessive computational resources and network traffic. In addition, it is difficult to integrate various object information with different sizes and scales into a single scene. Various sizes and types of objects (e.g., workers, heavy equipment, and materials) exist in a plant production environment, and these objects should be detected simultaneously for effective site monitoring. However, with the existing object detection algorithms, it is difficult to simultaneously detect objects with significant differences in size because collecting and training massive amounts of object image data with various scales is necessary. This study thus developed a large-scale site monitoring system using edge computing and a small-object detection system to solve these problems. Edge computing is a distributed information technology architecture wherein the image or video data is processed near the originating source, not on a centralized server or cloud. By inferring information from the AI computing module equipped with CCTVs and communicating only the processed information with the server, it is possible to reduce excessive network traffic. Small-object detection is an innovative method to detect different-sized objects by cropping the raw image and setting the appropriate number of rows and columns for image splitting based on the target object size. This enables the detection of small objects from cropped and magnified images. The detected small objects can then be expressed in the original image. In the inference process, this study used the YOLO-v5 algorithm, known for its fast processing speed and widely used for real-time object detection. This method could effectively detect large and even small objects that were difficult to detect with the existing object detection algorithms. When the large-scale site monitoring system was tested, it performed well in detecting small objects, such as workers in a large-scale view of construction sites, which were inaccurately detected by the existing algorithms. Our next goal is to incorporate various safety monitoring and risk analysis algorithms into this system, such as collision risk estimation, based on the time-to-collision concept, enabling the optimization of safety routes by accumulating workers' paths and inferring the risky areas based on workers' trajectory patterns. Through such developments, this continuous large-scale site monitoring system can guide a construction plant's safety management system more effectively.

• Journal of the Daesoon Academy of Sciences
• /
• v.33
• /
• pp.147-177
• /
• 2019

This article attempts to examine the fundamental perceptions and attitudes of human beings towards others utilizing the concept of 'precariat,' a new word recently created to designate people affected by the inequality and instability brought about by neoliberal globalization. Especially, the precariats within South Korean society noted in this article will be North Korean migrants. When leaving North Korea, they have entered into South Korean society with hurting bodies and minds as they made their way through China or third party countries. After arriving in South Korea, they face difficulties such as inadequate jobs and low-level welfare benefits. Also, considering the social discrimination, exclusion, and indifference towards North Korean migrants which are commonplace, they come to live their lives as precariats. Given their situation, I would like to seek wisdom for North Korean migrants to apply as they escape from insecure lives, and perhaps Sangsaeng (mutual beneficence) would allow them to do that within South Korean society. In this light, I think that the concept of hospitality and Haewon Sangsaeng (the resolution of grievances for mutual beneficence), a code of practical ethics within the Daesoon Thought, as a basis for discussion with other philosophies that are practical in enabling North Korean migrants and South Korean citizens to coexist within modern day South Korean society. This can be achieved because 'Haewon (grievance-resolution)' lowers the boundary between self and others through sharing, and consequently, daily mutual interactions can unfold as 'Sangsaeng', which stands as a new ethical and practical system of values available to all modern individuals. In fact, contrary to the religious implications of Daesoon Thought, the philosophical and existential significance of Daesoon Thought has not received much attention. However, if we pay attention to the question of why human subjects should be hospitable to others, we can grasp how Daesoon Thought presents values that are existential in nature and also consider the specific context that accompanies the religious aspects of this system of thought.

• Journal of Arbitration Studies
• /
• v.32 no.4
• /
• pp.53-85
• /
• 2022

Small and medium-sized enterprises ("SMEs") are vulnerable to trade secret misappropriation. Korea's legislation for the protection of SMEs' trade secrets and provision of civil, criminal, and administrative remedies includes the SME Technology Protection Act, the Unfair Competition Prevention Act, the Industrial Technology Protection Act, the Mutually Beneficial Cooperation Act, and the Subcontracting Act. Among these acts, the revised SME Technology Protection Act of 2018 introduced the "administrative technology misappropriation investigation system" to facilitate a rapid resolution of SMEs' technology misappropriation disputes. On September 27, 2021, Korea's Ministry of SMEs announced that it had reached an agreement to resolve the dispute between Hyundai Heavy Industries and Samyeong Machinery through the administrative technology misappropriation investigation system. However, not until 3 years and a few months passed since the introduction of the system could it be used to resolve an SME's technology misappropriation dispute with a large corporation. So there arose a question on the usefulness of the system. Therefore, we conducted a comparative legal analysis of Korea's laws enacted to protect trade secrets of SMEs and to address technology misappropriation, focusing on their legislative purpose, protected subject matter, types of misappropriation, and legal remedies. Then we analyzed the administrative technology misappropriation investigation system and the cases where this system was applied. We developed a proposal to enhance the usefulness of the system. The expert interviews of 4 attorneys who are experienced in the management of the system to check the practical value of the proposal. Our analysis shows that the lack of compulsory investigation and criminal sanctions is the fundamental limitation of the system. We propose revising the SME Technology Protection Act to provide correction orders, criminal sanctions, and compulsory investigation. We also propose training professional workforces to conduct digital forensics, enabling terminated SMEs to utilize the system, and assuring independence and fairness of the mediation and arbitration of the technology misappropriation disputes.