• Journal of The Korean Society of Agricultural Engineers
• /
• v.64 no.3
• /
• pp.9-24
• /
• 2022

Currently, a vast amount of hydrologic data is accumulated in real-time through automatic water level measuring instruments in agricultural reservoirs. At the same time, false and missing data points are also increasing. The applicability and reliability of quality control of hydrological data must be secured for efficient agricultural water management through calculation of water supply and disaster management. Considering the characteristics of irregularities in hydrological data caused by irrigation water usage and rainfall pattern, the Korea Rural Community Corporation is currently applying the Hampel filter as a water level data quality management method. This method uses window size as a key parameter, and if window size is large, distortion of data may occur and if window size is small, many outliers are not removed which reduces the reliability of the corrected data. Thus, selection of the optimal window size for individual reservoir is required. To ensure reliability, we compared and analyzed the RMSE (Root Mean Square Error) and NSE (Nash-Sutcliffe model efficiency coefficient) of the corrected data and the daily water level of the RIMS (Rural Infrastructure Management System) data, and the automatic outlier detection standards used by the Ministry of Environment. To select the optimal window size, we used the classification performance evaluation index of the error matrix and the rainfall data of the irrigation period, showing the optimal values at 3 h. The efficient reservoir automatic calibration technique can reduce manpower and time required for manual calibration, and is expected to improve the reliability of water level data and the value of water resources.

• Journal of Conservation Science
• /
• v.38 no.2
• /
• pp.117-123
• /
• 2022

In this study, investigated the possibility of quantitatively and qualitatively analyzing Korean ancient glasses via Raman Spectroscopy. We subjected four categories of Korean traditional glasses, namely, lead-BaO, lead, potash, and soda glasses (3, 3, 10, and 10 pieces, respectively), to this analytical technique. The results showed significant differences between the stretching and bending Raman vibration regions corresponding to these different Korean ancient glass types. Specifically, the stretching vibration regions corresponding to lead-BaO and lead glasses showed peaks at 1040 and 1000 cm^-1, respectively; the stretching vibration region of normal glass appears at 1100 cm^-1. The bending vibration regions corresponding to potash and soda glass showed Raman peaks at 490 and 560 cm^-1, respectively. Furthermore, the Raman spectra of the lead and lead-BaO glasses showed red shifts, which depended on the amount of PbO present. Thus, our findings highlighted the possibility of quantitatively determining the amount of PbO, a major component of lead glasses, via Raman Spectroscopy.

• Journal of the Korea Society of Computer and Information
• /
• v.27 no.12
• /
• pp.29-40
• /
• 2022

In this paper, we studied a system that detects and analyzes the pathological features of diabetic retinopathy using Mask R-CNN and a Random Forest classifier. Those are one of the deep learning techniques and automatically diagnoses diabetic retinopathy. Diabetic retinopathy can be diagnosed through fundus images taken with special equipment. Brightness, color tone, and contrast may vary depending on the device. Research and development of an automatic diagnosis system using artificial intelligence to help ophthalmologists make medical judgments possible. This system detects pathological features such as microvascular perfusion and retinal hemorrhage using the Mask R-CNN technique. It also diagnoses normal and abnormal conditions of the eye by using a Random Forest classifier after pre-processing. In order to improve the detection performance of the Mask R-CNN algorithm, image augmentation was performed and learning procedure was conducted. Dice similarity coefficients and mean accuracy were used as evaluation indicators to measure detection accuracy. The Faster R-CNN method was used as a control group, and the detection performance of the Mask R-CNN method through this study showed an average of 90% accuracy through Dice coefficients. In the case of mean accuracy it showed 91% accuracy. When diabetic retinopathy was diagnosed by learning a Random Forest classifier based on the detected pathological symptoms, the accuracy was 99%.

• Journal of the Korea institute for structural maintenance and inspection
• /
• v.26 no.6
• /
• pp.175-181
• /
• 2022

The condition of infrastructure deteriorates as the service life increases. Since most infrastructure in South Korea were intensively built during the period of economic growth, the proportion of outdated infrastructure is rapidly increasing now. Aging of such infrastructure can lead to safety accidents and even human casualties. To prevent these issues in advance, periodic and accurate inspection is essential. For this reason, the need for research to detect various types of damage using computer vision and deep learning is increasingly required in the field of remotely controlled or autonomous inspection. To this end, this study proposed a neural network structure that can detect concrete damage by classifying it into three types. In particular, the proposed neural network can detect them more accurately through a hierarchical learning technique. This neural network was trained with 2,026 damage images and tested with 508 damage images. As a result, we completed an algorithm with average mean intersection over union of 67.04% and F1 score of 52.65%. It is expected that the proposed damage detection algorithm could apply to accurate facility condition diagnosis in the near future.

• Journal of Conservation Science
• /
• v.38 no.3
• /
• pp.217-233
• /
• 2022

The remains found in Geumcheok-ri, Gyeongju are located in close proximity to the Ancient Tombs in Geumcheok-ri, Gyeongju (Historic Site) which were built between the late 5th and early 6th centuries, and these tombs are known to belong to the powerful rulers of that area. Using metallurgical techniques, this study was conducted on the iron objects obtained from the excavated remains in Geumcheok-ri, Gyeongju which are presumed to have a close relation to the nearby ruins that played an important role in the growth of Silla. To identify differences in manufacturing techniques based on the purpose of the iron objects, eight objects were selected after classifying them by use and the microstructure and non-metallic inclusions were investigated. The analyses results confirmed that the manufacturing process involved forging iron with a high or low carbon content to produce a particular shape, and that the carburization process was applied to iron post forging a shape to increase its strength when necessary. The mechanical properties were improved by selectively applying the steelmaking method and the heat treatment technique considering the functions of the parts, and the low temperature reduction was applied to the smelting process. Furthermore, in comparison with the iron objects excavated from the remains located in the center of Gyeongju and its outskirts, it is confirmed that there is similarity in the smelting and manufacturing techniques between these objects.

• Journal of Korea Water Resources Association
• /
• v.55 no.spc1
• /
• pp.1177-1185
• /
• 2022

The water and sewage system is an infrastructure that provides safe and clean water to people. In particular, since the water and sewage pipelines are buried underground, it is very difficult to detect system defects. For this reason, the diagnosis of pipelines is limited to post-defect detection, such as system diagnosis based on the images taken after taking pictures and videos with cameras and drones inside the pipelines. Therefore, real-time detection technology of pipelines is required. Recently, pipeline diagnosis technology using advanced equipment and artificial intelligence techniques is being developed, but AI-based defect detection technology requires a variety of learning data because the types and numbers of defect data affect the detection performance. Therefore, in this study, various defect scenarios are implemented using 3D printing model to improve the detection performance when detecting defects in pipelines. Afterwards, the collected images are performed to pre-processing such as classification according to the degree of risk and labeling of objects, and real-time defect detection is performed. The proposed technique can provide real-time feedback in the pipeline defect detection process, and it would be minimizing the possibility of missing diagnoses and improve the existing water and sewerage pipe diagnosis processing capability.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.22 no.1
• /
• pp.16-24
• /
• 2023

Accidents are greatly reduced through projects to improve frequent traffic accidents. These results show that safety facilities play a big role. Traffic accidents are caused by various causes and various environmental factors, and it is difficult to achieve improvement effects by installing one safety facility or facilities without standards. Therefore, this study analyzed the improvement effect of each accident type by combining the two safety facilities, and suggested a method of predicting the combination of safety facilities suitable for a specific point, including environmental factors such as road type, road type, and traffic. The prediction was carried out by selecting an XGBoost technique that creates one strong prediction model by combining prediction models that can be simple classification. Through this, safety facilities that have had positive effects through improvement projects and safety facilities to be installed at points in need of improvement were derived, and safety facilities effect analysis and prediction methods for future installation points were presented.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.28 no.3D
• /
• pp.407-415
• /
• 2008

This study presents the methodology to link with aerial photos for advancing the accuracy of topographic survey data that is used to calculate water volume in urban stream. First, GIS spatial interpolation technique as Inverse Distance Weight (IDW) and Kriging was applied to construct the terrain morphology to the sand-bar and grass area using cross-sectional survey data, and also validation point data was used to estimate the accuracy of created topographic data. As the result of comparison, IDW ($d^{-2}_{ij}$, 2nd square number) in Sand-bar area and Kriging Spherical model in grass area showed more efficient results in the construction of topographic data of river boundary. But the differences among interpolation methods are very slight. Image classification method, Minimum Distance Method (MDM) was applied to extract sand-bar and grass area that are located to river boundary efficiently and the elevation value of extracted layers was allocated to the water level point value. Water volume with topographic data from aerial photos shows the advanced accuracy of 13% (in sand-bar) and 12% (in grass) compared to the water volume of original terrain data. Therefore, terrain analysis method in river linking with aerial photos is efficient to the monitoring about sand-bar and grass area that are located in the downstream of Dam in flooding season, and also it can be applied to calculate water volume efficiently.

• Ecology and Resilient Infrastructure
• /
• v.10 no.4
• /
• pp.107-115
• /
• 2023

High turbidity in source water can have adverse effects on water treatment plant operations and aquatic ecosystems, necessitating turbidity management. Consequently, research aimed at predicting river turbidity continues. This study developed a multi-class classification model for prediction of turbidity using LightGBM (Light Gradient Boosting Machine), a representative ensemble machine learning algorithm. The model utilized data that was classified into four classes ranging from 1 to 4 based on turbidity, from low to high. The number of input data points used for analysis varied among classes, with 945, 763, 95, and 25 data points for classes 1 to 4, respectively. The developed model exhibited precisions of 0.85, 0.71, 0.26, and 0.30, as well as recalls of 0.82, 0.76, 0.19, and 0.60 for classes 1 to 4, respectively. The model tended to perform less effectively in the minority classes due to the limited data available for these classes. To address data imbalance, the SMOTE (Synthetic Minority Over-sampling Technique) algorithm was applied, resulting in improved model performance. For classes 1 to 4, the Precision and Recall of the improved model were 0.88, 0.71, 0.26, 0.25 and 0.79, 0.76, 0.38, 0.60, respectively. This demonstrated that alleviating data imbalance led to a significant enhancement in Recall of the model. Furthermore, to analyze the impact of differences in input data composition addressing the input data imbalance, input data was constructed with various ratios for each class, and the model performances were compared. The results indicate that an appropriate composition ratio for model input data improves the performance of the machine learning model.

• Journal of Internet Computing and Services
• /
• v.24 no.5
• /
• pp.17-27
• /
• 2023

Today, as AI (Artificial Intelligence) technology develops and its practicality increases, it is widely used in various application fields in real life. At this time, the AI model is basically learned based on various statistical properties of the learning data and then distributed to the system, but unexpected changes in the data in a rapidly changing data situation cause a decrease in the model's performance. In particular, as it becomes important to find drift signals of deployed models in order to respond to new and unknown attacks that are constantly created in the security field, the need for lifecycle management of the entire model is gradually emerging. In general, it can be detected through performance changes in the model's accuracy and error rate (loss), but there are limitations in the usage environment in that an actual label for the model prediction result is required, and the detection of the point where the actual drift occurs is uncertain. there is. This is because the model's error rate is greatly influenced by various external environmental factors, model selection and parameter settings, and new input data, so it is necessary to precisely determine when actual drift in the data occurs based only on the corresponding value. There are limits to this. Therefore, this paper proposes a method to detect when actual drift occurs through an Anomaly analysis technique based on XAI (eXplainable Artificial Intelligence). As a result of testing a classification model that detects DGA (Domain Generation Algorithm), anomaly scores were extracted through the SHAP(Shapley Additive exPlanations) Value of the data after distribution, and as a result, it was confirmed that efficient drift point detection was possible.