• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.41 no.4
• /
• pp.441-447
• /
• 2021

Construction sites are complex and dangerous because heavy equipment and workers perform various operations simultaneously within limited working areas. Solitary works of heavy equipment in complex job sites can cause fatal accidents, and thus they should interact with spotters and obtain information about surrounding environments during operations. Recently, many computer vision technologies have been developed to automatically monitor construction equipment and detect their interactions with other resources. However, previous methods did not take into account the interactions between equipment and spotters, which is crucial for identifying solitary works of heavy equipment. To address the drawback, this research develops a computer vision-based solitary work detection model that considers interactive operations between heavy equipment and spotters. To validate the proposed model, the research team performed experiments using image data collected from actual construction sites. The results showed that the model was able to detect workers and equipment with 83.4 % accuracy, classify workers and spotters with 84.2 % accuracy, and analyze the equipment-to-spotter interactions with 95.1 % accuracy. The findings of this study can be used to automate manual operation monitoring of heavy equipment and reduce the time and costs required for on-site safety management.

• Journal of Digital Convergence
• /
• v.19 no.5
• /
• pp.23-30
• /
• 2021

The shift to the digital media era is increasing the importance of the ability to accept, produce and share news through digital media(news literacy), but there is a lack of diagnosis of the level of news literacy among Korean adults and discussions on how to improve news literacy. This study analyzed the news literacy level of Korean adults according to background variables (urbanization degree, gender, age, academic background) and examined the relationship between the amount of news literacy-related practices and the level of news literacy. The results showed that the overall level of news literacy among adults in Korea was not high and that differences between groups were also statistically significant. The significant relevance between the amount of news literacy-related practices and the level of news literacy has also been identified. Based on the findings, it was suggested that the need for policy support to improve news literacy among Korean adults, the need to prioritize the resources of news literacy education according to background variables of adult learners, and the need to continuously monitor news literacy levels of Korean adults.

• Journal of the Korean Geotechnical Society
• /
• v.37 no.8
• /
• pp.25-35
• /
• 2021

Recently, the ground anchor method is commonly applied with nail and rock bolt to secure the stability of slopes and structures in Korea. Among them, permanent anchor which is used for long-term stability should secure bearing capacity and durability during the period of use. However, according to recent studies, phenomenon such as deformation to slope and the reduction of residual tensile load over time have been reported along the long-term behavior of the anchors. These problems of reducing residual tensile load are expected to increase in the future, which will inevitably lead to problems such as increasing maintenance costs. In this study, we identified the factors that affect the tensile load of permanent anchor from a literature study on the domestic and foreign, and investigated the prior studies that analyzed previously conducted load cell monitoring data. Afterwards, using this as basic data, the load cell measurement data collected at the actual site were analyzed to identify the tensile load reduction status of anchors, and the long-term load reduction characteristics were analyzed. Finally, by aggregating the preceding results, proposed a technique to predict the long-term load reduction characteristics of permanent anchors through short-term data to around 100 days after installation.

• The Journal of the Korea Contents Association
• /
• v.21 no.1
• /
• pp.552-560
• /
• 2021

Currently, the domestic aquaculture industry is pursuing smartization, but it is still proceeding with human subjective judgment in many processes in the aquaculture stage. The prerequisite for the smart aquaculture industry is to effectively grasp the condition of fish in the farm. If real-time monitoring is possible by identifying the number of fish populations, size, pathways, and speed of movement, various forms of automation such as automatic feed supply and disease determination can be carried out. In this study, we proposed an algorithm to identify the state of fish in real time using underwater video data. The fish detection performance was compared and evaluated by applying the latest deep learning-based object detection models, and an algorithm was proposed to measure fish object identification, path tracking, and moving speed in continuous image frames in the video using the fish detection results. The proposed algorithm showed 92% object detection performance (based on F1-score), and it was confirmed that it effectively tracks a large number of fish objects in real time on the actual test video. It is expected that the algorithm proposed in this paper can be effectively used in various smart farming technologies such as automatic feed feeding and fish disease prediction in the future.

• Journal of Advanced Navigation Technology
• /
• v.25 no.3
• /
• pp.248-255
• /
• 2021

The main causes of the July 2013 OZ 214 accident were poorly performed approach and the failure to recognize the autothrottle in the HOLD position which the automated speed control was not provided. The pilots late decision for go-around was also a critical factor leading to the accident. The B777 POM restricts the use of FLCH mode beyond the FAF. This research utilized the QAR data of an airline's B777 fleet in the period of two years where 44 cases were found. In many cases, the FLCH mode was used for rapid descent from an higher than normal situation. In addition, in the base turn, continuous use of FLCH mode even when the path was below the glide path were observed. Airports with elevation above 500 ft MSL had a higher rate of occurrence. In this research, the proper descent planning and vertical path monitoring, and the adherence to the limitation set in the manuals and the stabilized approach criteria were re-emphasized as mitigation to reduce event occurences.

• Journal of Korea Water Resources Association
• /
• v.54 no.3
• /
• pp.167-179
• /
• 2021

In order to characterize the mixing process of confluence for understanding the impacts of a river on the other river, it has been crucial to analyze the spatial mixing patterns for main streams depending on various inflow conditions of tributaries. However, most conventional studies have mostly relied upon hydraulic or water quality numerical models for understanding mixing pattern analysis of confluences, due to the difficulties to acquire a wide spatial range of in-situ data for characterizing mixing process. In this study, backscatters (or SNR) measured from ADCPs were particularly used to track sediment mixing assuming that it could be a surrogate to estimate the suspended sediment concentration. Raw backscatter data were corrected by considering the beam spreading and absorption by water. Also, an optical Laser diffraction instrument (LISST) was used to verify the method of acoustic backscatter and to collect the particle size distribution of main stream and tributary. In addition, image-based spatial distributions of sediment mixture in the confluence were monitored in various flow conditions by using an unmanned aerial vehicle (UAV), which were compared with the spatial distribution of acoustic backscatter. As results, we found that when acoustic backscatter by ADCPs were well processed, they could be proper indicators to identify the spatial patterns of the three-dimensional mixing process between two rivers. For this study, flow and sediment mixing characteristics were investigated in the confluence between Nakdong and Nam river.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.26 no.7
• /
• pp.931-941
• /
• 2020

There is a growing interest this paper for ocean sensing where autonomous vehicles can play an essential role in assisting engineers, researchers, and scientists with environmental monitoring and collecting oceanographic data. This study was conducted to develop a rigid sail for the autonomous sailing drone. Our study aims to numerically analyze the aerodynamic characteristics of curvy twin sail and compare it with wing sail. Because racing regulations limit the sail shape, only the two-dimensional geometry (2D) was open for an optimization. Therefore, the first objective was to identify the aerodynamic performance of such curvy twin sails. The secondary objective was to estimate the effect of the sail's spacing and shapes. A viscous Navier-Stokes flow solver was used for the numerical aerodynamic analysis. The 2D aerodynamic investigation is a preliminary evaluation. The results indicated that the curvy twin sail designs have improved lift, drag, and driving force coefficient compared to the wing sails. The spacing between the port and starboard sails of curvy twin sail was an important parameter. The spacing is 0.035 L, 0.07 L, and 0.14 L shows the lift coefficient reduction because of dramatically stall effect, while flow separation is improved with spacing is 0.21 L, 0.28 L, and 0.35 L. Significantly, the spacing 0.28 L shows the maximum high pressure at the lower area and the small low pressure area at leading edges. Therefore, the highest lift was generated.

• Journal of the Korea Convergence Society
• /
• v.12 no.8
• /
• pp.31-37
• /
• 2021

As the size of buildings increases due to urbanization due to the development of industry, the need to purify the air and maintain a comfortable indoor environment is also increasing. With the development of monitoring technology for refrigeration systems, it has become possible to manage the amount of electricity consumed in buildings. In particular, refrigeration systems account for about 40% of power consumption in commercial buildings. Therefore, in order to develop the refrigeration system failure diagnosis algorithm in this study, the purpose of this study was to understand the structure of the refrigeration system, collect and analyze data generated during the operation of the refrigeration system, and quickly detect and classify failure situations with various types and severity . In particular, in order to improve the classification accuracy of failure types that are difficult to classify, a three-step diagnosis and classification algorithm was developed and proposed. A model based on SVM and LGBM was presented as a classification model suitable for each stage after a number of experiments and hyper-parameter optimization process. In this study, the characteristics affecting failure were preserved as much as possible, and all failure types, including refrigerant-related failures, which had been difficult in previous studies, were derived with excellent results.

• The Journal of the Convergence on Culture Technology
• /
• v.7 no.3
• /
• pp.123-134
• /
• 2021

This study was conducted for the purpose of convergence exploration of evidence-based practices for the advancement of performance analysis of the extracurricular activities at Duksung Women's University. The research method consisted of an expert meeting procedure along with a procedure for analyzing previous studies dealing with the performance analysis of the university's extracurricular activities in the field of pedagogy. The contents of this study consisted of presenting some facts that should be based on evidence for the advancement of performance analysis of the extracurricular activities after the establishment of the center for extracurricular activities in Duksung Women's University. And in practices, the development and diagnostic analysis of tools for diagnosing extracurricular customized learning capabilities, data-based multidimensional analysis (IR system), continuous monitoring analysis through extracurricular certification, and analysis based on feedback tools were presented in a convergence perspective and context. As a result of the study, the evidence-based practices for the advancement of the performance analysis of the extracurricular activities at Duksung Women's University guarantees the validity and stability of the performance evaluation and feedback system of the extracurricular activities at Duksung Women's University, and has a close influence on the extracurricular education work of other universities analyzed as possible.

• Journal of Industrial Convergence
• /
• v.20 no.4
• /
• pp.23-30
• /
• 2022

Recently, with the development of artificial intelligence (AI) and deep learning, the importance of conversational artificial intelligence chatbots is being highlighted. In addition, chatbot research is being conducted in various fields. To build a chatbot, it is developed using an open source platform or a commercial platform for ease of development. These chatbot platforms mainly use RNN and application algorithms. The RNN algorithm has the advantages of fast learning speed, ease of monitoring and verification, and good inference performance. In this paper, a method for improving the inference performance of RNNs and applied algorithms was studied. The proposed method used the word group expansion learning technique of key words for each sentence when RNN and applied algorithm were applied. As a result of this study, the RNN, GRU, and LSTM three algorithms with a cyclic structure achieved a minimum of 0.37% and a maximum of 1.25% inference performance improvement. The research results obtained through this study can accelerate the adoption of artificial intelligence chatbots in related industries. In addition, it can contribute to utilizing various RNN application algorithms. In future research, it will be necessary to study the effect of various activation functions on the performance improvement of artificial neural network algorithms.