• The Journal of Bigdata
• /
• v.5 no.2
• /
• pp.17-27
• /
• 2020

District heating system supplies heat from low-cost high-efficiency heat production facilities to heat demand areas through a heat pipe network. For efficient heat supply system operation, it is important to accurately predict the heat demand within the region and optimize the heat production plan accordingly. In this study, a heat demand forecasting model is proposed considering real-time calorimeter information from local heat demands. Previous models considered ambient temperature and heat demand history data to predict future heat demands. To improve forecast accuracy, the proposed heat demand forecast model added big data from real-time calorimeters installed in the heat demands within the target region. By employing calorimeter information directly in the model, it is expected that the proposed forecast model is to reflect heat use pattern of each demand. Computational experiemtns based on the actual heat demand data shows that the forecast accuracy of the proposed model improved when the calorimeter big data is reflected.

• Journal of Environmental Health Sciences
• /
• v.48 no.2
• /
• pp.66-74
• /
• 2022

Background: The health effects of particulate matter (PM_2.5) bonded with various harmful chemicals differ based on their composition, so investigating and managing their concentrations and composition is vital for long-term management. As industrial complexes emit considerable quantities of pollutants, higher PM_2.5 concentrations and chemical component effects are expected than in other places. Objectives: We investigated the concentration distribution ratios of PM_2.5 chemical components to provide basic data to inform future major emissions control and PM_2.5 reduction measures in industrial complexes. Methods: We monitored five sites near the Ansan and Siheung industrial complexes from August 2020 to July 2021. Samples were collected and analyzed twice per week in spring/winter and once per week in summer/autumn according to the National Institute of Environmental Research in the Ministry of Environments' Air Pollution Monitoring Network Installation and Operation Guidelines. We investigated and compared composition ratios of 29 ions, carbon, and elemental components in PM_2.5. Results: The analysis of PM_2.5 components at the five sites revealed that ion components accounted for the greatest total mass at approximately 50% while carbon components and elemental components contributed 23~28% and 8~10%, respectively. Among the ionic components, NO₃^- occupies the greatest proportion. OC occupies the greatest proportion of the carbon components and sulphur occupies the greatest proportion of elemental components. Conclusions: This study investigated the concentration distribution ratios of PM_2.5 chemical components in industrial complexes. We believe these results provide basic chemical component concentration ratio data for establishing future air management policies and plans for the Ansan and Siheung industrial complexes.

• Journal of Navigation and Port Research
• /
• v.46 no.3
• /
• pp.280-288
• /
• 2022

This study examined the diagnostics of abnormalities and faults of equipment, whose rotational speed changes even during regular operation. The purpose of this study was to suggest a procedure that can properly apply machine learning to the time series data, comprising non-stationary characteristics as the rotational speed changes. Anomaly and fault diagnosis was performed using machine learning: k-Nearest Neighbor (k-NN), Support Vector Machine (SVM), and Random Forest. To compare the diagnostic accuracy, an autoencoder was used for anomaly detection and a convolution based Conv1D was additionally used for fault diagnosis. Feature vectors comprising statistical and frequency attributes were extracted, and normalization & dimensional reduction were applied to the extracted feature vectors. Changes in the diagnostic accuracy of machine learning according to feature selection, normalization, and dimensional reduction are explained. The hyperparameter optimization process and the layered structure are also described for each algorithm. Finally, results show that machine learning can accurately diagnose the failure of a variable-rotation machine under the appropriate feature treatment, although the convolution algorithms have been widely applied to the considered problem.

• Tunnel and Underground Space
• /
• v.32 no.3
• /
• pp.194-202
• /
• 2022

An increased number of cases have occurred in applying ICT technology in the resource development field due to factors such as safety, eco-friendliness, and low cost since the 2000s. In Korea, the 2nd mining master plan specified the significance of converging the full cycle of mining and ICT, while the 3rd mining master plan highlighted ICT and smart mining such as supporting the supply of an ICT mining device and introducing demonstrational smart mining. This study introduces the application of an ICT device and safety system operation in the Jangseong underground mine of Korea Cement Co., Ltd. Currently, Jangseong mine combines two different kinds of 3D equipment including the handheld 3D scanner and multi-station that provides both the measurement and 3D scanning to perform a 3D measurement of the mine. Taken from the 3D measurement of the mine, it is now possible to identify any hazardous areas and abnormalities in different directions and analyze the safety of the crown pillar between two stopes in different level. Besides, the real-time location tracking and communications system have established highly efficient rescue and evacuation plans to effectively deal with any accidents in the mine.

• Journal of Korea Entertainment Industry Association
• /
• v.15 no.4
• /
• pp.383-390
• /
• 2021

Recently, the drone industry is rapidly expanding as it is suggested that it will be used in various fields. As the size of the drone market grows, interest in drone-related certificates is also increasing. However, the current drone-related qualification system and education system are insufficient. Thus this study, analyzed the necessity of drone training, the features of functional games, and the effectiveness of educational training using AR through related technical studies to solve the practical difficulties of drone educational training. Later, drone educational training game contents using AR were divided into practice mode and test mode based on the drone national qualification course practical test, and the result screen was displayed at the end of the curriculum so that players could learn by level and evaluate the results on their own. In addition, constructed a hybrid processing system and network and AR operation system for response rate and response speed, implemented drone training game contents utilizing AR based on the design contents. It is expected that the use of game content using AR presented in this paper for drone training will further alleviate environmental difficulties and improve the sense of immersion in play, which will lead to a more effective drone educational training experience.

• Journal of the Korea institute for structural maintenance and inspection
• /
• v.26 no.5
• /
• pp.127-134
• /
• 2022

In this study, RCPTs (Rapid Chloride Penetration Test) were performed for fly ash concrete with curing age of 4 ~ 6 years. The concrete mixtures were prepared with 3 levels of water to binder ratio (0.37, 0.42, and 0.47) and 2 levels of substitution ratio of fly ash (0 and 30%), and the improved passed charges of chloride ion behavior were quantitatively analyzed. Additionally, the results were trained through the univariate time series models consisted of GRU (Gated Recurrent Unit) algorithm and those from the models were evaluated. As the result of the RCPT, fly ash concrete showed the reduced passed charges with period and an more improved resistance to chloride penetration than OPC concrete. At the final evaluation period (6 years), fly ash concrete showed 'Very low' grade in all W/B (water to binder) ratio, however OPC concrete showed 'Moderate' grade in the condition with the highest W/B ratio (0.47). The adopted algorithm of GRU for this study can analyze time series data and has the advantage like operation efficiency. The deep learning model with 4 hidden layers was designed, and it provided a reasonable prediction results of passed charge. The deep learning model from this study has a limitation of single consideration of a univariate time series characteristic, but it is in the developing process of providing various characteristics of concrete like strength and diffusion coefficient through additional studies.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.14 no.2
• /
• pp.128-133
• /
• 2021

Currently, autonomous vehicle markets are commercializing a third-level autonomous vehicle, but there is a possibility that an accident may occur even during fully autonomous driving due to stability issues. In fact, autonomous vehicles have recorded 81 accidents. This is because, unlike level 3, autonomous vehicles after level 4 have to judge and respond to emergency situations by themselves. Therefore, this paper proposes a vehicle crisis detection system(VCDS) that collects and stores information outside the vehicle through CNN, and uses the stored information and vehicle sensor data to output the crisis situation of the vehicle as a number between 0 and 1. The VCDS consists of two modules. The vehicle external situation collection module collects surrounding vehicle and pedestrian data using a CNN-based neural network model. The vehicle crisis situation determination module detects a crisis situation in the vehicle by using the output of the vehicle external situation collection module and the vehicle internal sensor data. As a result of the experiment, the average operation time of VESCM was 55ms, R-CNN was 74ms, and CNN was 101ms. In particular, R-CNN shows similar computation time to VESCM when the number of pedestrians is small, but it takes more computation time than VESCM as the number of pedestrians increases. On average, VESCM had 25.68% faster computation time than R-CNN and 45.54% faster than CNN, and the accuracy of all three models did not decrease below 80% and showed high accuracy.

• Journal of the Korean Society for Library and Information Science
• /
• v.56 no.4
• /
• pp.181-203
• /
• 2022

This study analyzed domestic and foreign literature and examined cases of foreign Community of Practice(CoP) of experts to find out what benefits researchers can gain from participating in their CoP, how the CoP was established, and how data is shared within the CoP. In addition, this study discussed on how to establish a CoP of experts in Korea for sharing and using research data. By participating in the CoP of experts, members can be provided with the opportunity to build an experts' network and have a chance to meet with various experts, to acquire and share their expertise and information, to receive help from other experts, to learn about their expertise, and to have opportunities for professional experiences. In addition, this study discussed 4 factors such as operation method and management system, memberships and number of members, activities, and management of data and repository for establishing a CoP of experts for sharing and using research data. This study provides a knowledge base for building a CoP of experts in Korea.

• Journal of Convergence for Information Technology
• /
• v.12 no.5
• /
• pp.237-245
• /
• 2022

This study examines the social discourse on the characteristics of the learning community in the untact era, and discusses the directions that learning communities for children could explore and consider in the pandemic situation and beyond. For this purpose, big data for one year, from January 20, 2020 to January 20, 2021, were collected through internet portal sites (includingincluding Google News, Daum, Naver and other News surfaces), using two keywords "untact" and "learning community", and analyzed by employing a word frequency and network analysis method. The analysis results show that several important terms, such as 'village education community', 'operation', 'activity', 'corona 19', 'support', and 'online' are closely related to the learning community in the untact era. The findings from this study also have implications for developing the learning community as an alternative model to fill the existing gaps in public care and education for children during the prolonged pandemic and afterwards. In conclusion, the study findings highlight that it is meaningful to identify key terms and concepts through word frequency analysis in order to examine social trends and issues related to the learning community.

• Journal of Internet Computing and Services
• /
• v.22 no.6
• /
• pp.115-127
• /
• 2021

With the development of science and technology around the world, the realm of cyberspace, following land, sea, air, and space, is also recognized as a battlefield area. Accordingly, it is necessary to design and establish various elements such as definitions, systems, procedures, and plans for not only physical operations in land, sea, air, and space but also cyber operations in cyberspace. In this research, the importance of cyber targets that can be considered when prioritizing the list of cyber targets selected through intermediate target development in the target development and prioritization stage of targeting processing of cyber operations was selected as a factor to be considered. We propose a method to calculate the score for the cyber target and use it as a part of the cyber target prioritization score. Accordingly, in the cyber target prioritization process, the cyber target importance category is set, and the cyber target importance concept and reference item are derived. We propose a TIR (Target Importance Rank) algorithm that synthesizes parameters such as Event Prioritization Framework based on PageRank algorithm for score calculation and synthesis for each derived standard item. And, by constructing the Stuxnet case-based network topology and scenario data, a cyber target importance score is derived with the proposed algorithm, and the cyber target is prioritized to verify the proposed algorithm.