• Advanced Industrial SCIence
• /
• v.2 no.4
• /
• pp.11-16
• /
• 2023

The subway is a means of public transportation that plays an important role in the transportation system of modern cities. However, congestion often occurs due to sudden breakdowns and system outages, causing inconvenience. Therefore, in this paper, we conducted a study on failure prediction and prevention using machine learning to efficiently operate the subway system. Using UC Irvine's MetroPT-3 dataset, we built a subway breakdown prediction model using logistic regression. The model predicted the non-failure state with a high accuracy of 0.991. However, precision and recall are relatively low, suggesting the possibility of error in failure prediction. The ROC_AUC value is 0.901, indicating that the model can classify better than random guessing. The constructed model is useful for stable operation of the subway system, but additional research is needed to improve performance. Therefore, in the future, if there is a lot of learning data and the data is well purified, failure can be prevented by pre-inspection through prediction.

• Journal of Animal Environmental Science
• /
• v.18 no.2
• /
• pp.99-110
• /
• 2012

The purpose of the study is to collect basis data for to establish standard administrative processes of liquid fertilizer treatment. From this survey we could make out the key point of each step through a case of effective liquid manure treatment system in pig house. It is divided into six step; 1. piggery slurry management step, 2. Solid-liquid separation step, 3. liquid fertilizer treatment (aeration) step, 4. liquid fertilizer treatment (microorganism, recirculation and internal return) step, 5. liquid fertilizer treatment (completion) step, 6. land application step. From now on, standardization process of liquid manure treatment technologies need to be develop based on the six steps process.

• Fire Science and Engineering
• /
• v.29 no.3
• /
• pp.59-64
• /
• 2015

This study analyzed results of the causes of failure in 1,022 fire trucks currently being used in South Korea (aerial ladder, aerial platform, pumper, and chemical fire trucks). The results show that 46% of aerial ladder trucks have defective in the elevator brake systems, 29% of aerial platform trucks have contamination in the hydraulic oil, 37% of pumpers have defective in the pneumatic cylinders of the air supply system, and 39% of chemical fire trucks have defective in the powder fire extinguishing systems. The principal reasons for malfunctions are deterioration of the apparatuses, and accumulated fatigue from repetitive use of certain components, such as pneumatic cylinders in the air supply system and wire rope jamming in rollers in the ladder apparatus. These manufacturing defects should be improved upon in the manufacturing process. As a result, the fire trucks, which are used for 5 years or more, need precise inspections in accordance with the Regulation on Fire Apparatus Maintenance. Fire apparatuses have a service life of 10 to 12 years or more. They need to be replaced or require life extension, and they should be kept in top shape with the best maintenance for public safety.

• Journal of the Korean GEO-environmental Society
• /
• v.21 no.6
• /
• pp.13-17
• /
• 2020

In the era of the fourth industrial revolution, drones are being used in various civil engineering fields. Currently, the construction and maintenance of slopes are generally managed by manpower. This method has a risk of safety accidents, and it is difficult to accurately evaluate the slope because it is difficult to secure the vision. In this paper, the effects of RTK and GCP on the 3D model of the slope were studied by using digital images taken by the drone. GNSS coordinates were measured for nine points to compare the quality of the slope 3D model, three points of which were used as the check points and the remaining points were used as GCPs. When making the 3D model of the slope using high-accuracy geotagging images using RTK, it was found that the error at the check point decreases as the number of GCP increases. Even if GNSS was used, it was found that the error at the check points of the 3D slope model was not significant when the GCPs were applied. However, it was found that even if high-accuracy geotagging images are used using the RTK module, a significant error occur when the 3D slope model is created without applying GCPs. Therefore, it can be stated that GCP must be applied to create the 3D slope model in which information about the height as well as plane information is important.

• Journal of Wetlands Research
• /
• v.16 no.2
• /
• pp.235-243
• /
• 2014

According to the "Safety Evaluation Detailed Instructions (Dam)", precise safety inspection is carried out for dams that exceed a certain scale. However, as the Hydrological Safety Evaluation from various evaluation standards is designed to evaluate the safety of existing dams considering PMF, the evaluation is much less applicable for most agricultural reservoirs. Therefore, the Hydrological Safety Guidelines for agricultural reservoirs are expected to be re-evaluated considering the diverse risk factors with the coefficient model and AHP in this study. The coefficient model has been developed by selecting the hydrological safety superordinate subordinate evaluation factors to reflect diverse risk factors of agricultural reservoirs. After calculating the sum of indicators score for each evaluation factors, validation procedures were performed for the questionnaire which a panel answered. The practical coefficient has eventually been estimated for the hydrological safety evaluation considering the diverse risk factors. The conclusions acquired based on the study done are that both most agricultural reservoirs were classified as flood defense capability is insufficient and agricultural reservoirs which meet embankment-freeboard standards considering PMF was overestimated.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.11 no.5
• /
• pp.521-530
• /
• 2018

This paper proposes "The Agriculture Decision-making System(ADS) based on Deep Learning for improving crop productivity" that collects weather information based on location supporting precision agriculture, predicts current crop condition by using the collected information and real time crop data, and notifies a farmer of the result. The system works as follows. The ICM(Information Collection Module) collects weather information based on location supporting precision agriculture. The DRCM(Deep learning based Risk Calculation Module) predicts whether the C, H, N and moisture content of soil are appropriate to grow specific crops according to current weather. The RNM(Risk Notification Module) notifies a farmer of the prediction result based on the DRCM. The proposed system improves the stability because it reduces the accuracy reduction rate as the amount of data increases and is apply the unsupervised learning to the analysis stage compared to the existing system. As a result, the simulation result shows that the ADS improved the success rate of data analysis by about 6%. And the ADS predicts the current crop growth condition accurately, prevents in advance the crop diseases in various environments, and provides the optimized condition for growing crops.

• Journal of the Korean Institute of Traditional Landscape Architecture
• /
• v.36 no.4
• /
• pp.105-112
• /
• 2018

This study aims to apply 3D scanning technology to the field of landscape planning design. Through this, 3D scans were conducted on Soswaewon Garden and Seongrakwon Gardens to find directions for traditional landscape planning and designs. The results as follows. First, the actual measurement of the traditional garden through a 3D scan confirmed that a precise three-dimensional modeling of ${\pm}3-5mm$ error was constructed through the merging of coordinate values based on point data acquired at each observation point and postprocessing. Second, as a result of the 3D survey, the Soswaewon Garden obtained survey data on Jewoldang House, Gwangpunggak Pavilion, the surrounding wall, stone axis, and Aeyangdan wall, while the Seongnakwon Garden obtained survey data on the topography, rocks and waterways around the Yeongbyeokji pond area. The above data have the advantage of being able to monitor the changing appearance of the garden. Third, spatial information developed through 3D scans could be developed with a three-dimensional drawing preparation and inspection tool that included precise real-world data, and this process ensured the economic feasibility of time and manpower in the actual survey and investigation of landscaping space. In addition, modelling with a three-dimensional 1:1 scale is expected to be highly efficient in that reliable spatial data can be maintained and reprocessed to a specific size depending on the size of the design. In addition, from a long-term perspective, the deployment of 3D scan data is easy to predict and simulate changes in traditional landscaping space over time.

• Journal of the Korea Institute of Building Construction
• /
• v.21 no.6
• /
• pp.665-676
• /
• 2021

As the number of deteriorated buildings increases, the importance of safety diagnosis and maintenance of buildings has been rising. Existing visual investigations and building safety diagnosis objectivity and reliability are poor due to their reliance on the subjective judgment of the examiner. Therefore, this study presented the limitations of the previously conducted appearance investigation and proposed 3D Point Cloud data to increase the accuracy of existing detailed inspection data. In addition, this study conducted a calculation of an objective building safety grade using a Deep-Neural Network(DNN) structure. The DNN structure is generated using the existing detailed inspection data and precise safety diagnosis data, and the safety grade is calculated after applying the state evaluation data obtained using a 3D Point Cloud model. This proposed process was applied to 10 deteriorated buildings through the case study, and achieved a time reduction of about 50% compared to a conventional manual safety diagnosis based on the same building area. Subsequently, in this study, the accuracy of the safety grade calculation process was verified by comparing the safety grade result value with the existing value, and a DNN with a high accuracy of about 90% was constructed. This is expected to improve economic feasibility in the future by increasing the reliability of calculated safety ratings of old buildings, saving money and time compared to existing technologies.

• Korean Journal of Construction Engineering and Management
• /
• v.24 no.1
• /
• pp.31-39
• /
• 2023

To reduce facility management costs and safety concerns due to aging of facilities, it is important to estimate the future facilities' condition based on facility management data and utilize predictive information for management decision making. To this end, this study proposed a methodology to estimate facility elements' condition using XGBoost. To validate the proposed methodology, this study constructed sample data for road bridges and developed a model to estimate condition grades of major elements expected in the next inspection. As a result, the developed model showed satisfactory performance in estimating the condition grades of deck, girder, and abutment/pier (average F1 score 0.869). In addition, a testbed was established that provides data management function and element condition estimation function to demonstrate the practical applicability of the proposed methodology. It was confirmed that the facility management data and predictive information in this study could help managers in making facility management decisions.

• Journal of the Korean Society for Marine Environment & Energy
• /
• v.9 no.4
• /
• pp.235-242
• /
• 2006

The precise estimation of total and organic carbon contents in sediments is fundamental to understand the benthic environment. To test the precision and accuracy of CHN analyzer and the procedure to quantify total and organic carbon contents(using in-situ acidification with sulfurous acid($H_2SO_3$)) in the sediment, the reference material s such as Acetanilide($C_8H_9NO$), Sulfanilammide($C_6H_8N_2O_2S$), and BCSS-1(standard estuary sediment) were used. The results indicate that CHN analyzer to quantify carbon and nitrogen content has high precision(percent error=3.29%) and accuracy(relative standard deviation=1.26%). Additionally, we conducted the instrumental comparison of carbon values analyzed using CHN analyzer and Coulometeric Carbon Analyzer. Total carbon contents measured from two different instruments were highly correlated($R^2=0.9993$, n=84, p<0.0001) with a linear relationship and show no significant differences(paired t-test, p=0.0003). The organic carbon contents from two instruments also showed the similar results with a significant linear relationship($R^2=0.8867$, n=84, p<0.0001) and no significant differences(paired t-test, p<0.0001). Although it is possible to overestimate organic carbon contents for some sediment types having high inorganic carbon contents(such as calcareous ooze) due to procedural and analytical errors, analysis of organic carbon contents in sediments using CHN Analyzer and current procedures seems to provide the best estimates. Therefore, we recommend that this method can be applied to measure the carbon content in normal any sediment samples and are considered to be one of the best procedure far routine analysis of total and organic carbon.