• Geomechanics and Engineering
• /
• v.32 no.1
• /
• pp.111-123
• /
• 2023

The slope of an open cut tunnel is located above the exit of the Leijia tunnel on the Changgan high-speed railway. During the excavation of the open cut tunnel foundation pit, the slope slipped twice, a large landslide of 92500 m³ formed. The landslide body and unstable slope body not only caused the foundation pit of the open cut tunnel to be buried and the anchor piles to be damaged but also directly threatened the operational safety of the later high-speed railway. Therefore, to study the stability change in the slope of the open cut tunnel under heavy rain and excavation conditions, a 3D numerical calculation model of the slope is carried out by Midas GTS software, the deformation mechanism is analyzed, anti-sliding measures are proposed, and the effectiveness of the anti-sliding measures is analyzed according to the field monitoring results. The results show that when rainfall occurs, rainwater collects in the open cut tunnel area, resulting in a transient saturation zone on the slope on the right side of the open cut tunnel, which reduces the shear strength of the slope soil; the excavation at the slope toe reduces the anti-sliding capacity of the slope toe. Under the combined action of excavation and rainfall, when the soil above the top of the anchor pile is excavated, two potential sliding surfaces are bounded by the top of the excavation area, and the shear outlet is located at the top of the anchor pile. After the excavation of the open cut tunnel, the potential sliding surface is mainly concentrated at the lower part of the downhill area, and the shear outlet moves down to the bottom of the open cut tunnel. Based on the deformation characteristics and the failure mechanism of the landslides, comprehensive control measures, including interim emergency mitigation measures and long-term mitigation measures, are proposed. The field monitoring results further verify the accuracy of the anti-sliding mechanism analysis and the effectiveness of anti-sliding measures.

• Journal of the Korean earth science society
• /
• v.44 no.1
• /
• pp.1-12
• /
• 2023

Oceanic wind waves have been recognized as one of the important indicators of global warming and climate change. It is necessary to study the spatial and temporal variability of significant wave height (SWH) and wave direction in the Yellow Sea and a part of the East China Sea, which is directly affected by the East Asian monsoon and climate change. In this study, the spatial and temporal variability including seasonal and interannual variability of SWH and wave direction in the Yellow Sea and East China Sea were analyzed using European Center for Medium-Range Weather Forecasts (ECMWF) Reanalysis 5 (ERA5) data. Prior to analyzing the variability of SWH and wave direction using the model reanalysis, the accuracy was verified through comparison with SWH and wave direction measurements from Ieodo Ocean Science Station (I-ORS). The mean SWH ranged from 0.3 to 1.6 m, and was higher in the south than in the north and higher in the center of the Yellow Sea than in the coast. The standard deviation of the SWH also showed a pattern similar to the mean. In the Yellow Sea, SWH and wave direction showed clear seasonal variability. SWH was generally highest in winter and lowest in late spring or early summer. Due to the influence of the monsoon, the wave direction propagated mainly to the south in winter and to the north in summer. The seasonal variability of SWH showed predominant interannual variability with strong variability of annual amplitudes due to the influence of typhoons in summer.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.29 no.2D
• /
• pp.199-207
• /
• 2009

We tried to show the course of UTIS vitalization, promoting to introduce as part of the advanced traveler information system through analysis using traffic information gap model of service and structural equation modeling being used by drivers. The summary of the research is as follows. 1. We could find out the service matters needed to improve and what should be prior that make drivers' use increase through establishing the gap model of service. 2. We could establish the structural equation modeling through using traffic information use satisfaction rate, entire traffic information satisfaction rate as the observation variables. You can say it is the fruit of this research that it was confirmed the entire satisfaction rate of traffic information influenced extension, convenience, accuracy, economical efficiency in order. We could also arrange the base to determine the order of services for vitalization of UTIS in the future through grasping the priority of each service functions classified by factors. 3. It is confirmed that many drivers want multimedia function, driving support function and various functions for the personal convenience in situations except driving, which enable the drivers to enjoy leisures and interests rather than economical functions during driving due to the recent social and economic changes.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.30 no.5D
• /
• pp.533-540
• /
• 2010

Dam is very important facility in water supply and flood control. Therefore study needs to analyze reservoir capacity accurately to manage Dam efficiently. This study compared time series reservoir capacity using multi-dimensional spatial information to Chungju Dam reservoir and major conclusions are as follows. First, LiDAR and multi beam echo sounder survey were carried out in land zone and water zone of Dam reservoir area. And calibration process was performed to enhance the accuracy of survey data and it could be constructed that multi dimensional spatial information which was clearly satisfied with the standard of tolerance error by validation with ground control points. Reservoir capacity by water level was calculated using triangle irregular network from detailed topographic data that was constructed by linked with airborne LiDAR and multi beam echo sounder data, and curve equation of reservoir capacity was developed through regression analysis in 2008. In the comparison of the reservoir capacity of 2008 with those of 1986 and 1996, the higher water level goes, total reservoir capacity of 2008 showed decrease because of the increase of sediment in reservoir. Also, erosion and sediment area could be analyzed through calculating the reservoir capacity by the range of water level. Especially the range of water level as 130.0~135.0 which is the upper part of average water level, showed the highest erosion characteristics during 1986~2008 and 1996~2008 and it is considered that the erosion of reservoir slant by heavy rainfall is major reason.

• Korean Journal of Remote Sensing
• /
• v.39 no.6_1
• /
• pp.1185-1193
• /
• 2023

The increasing interest in soil moisture data from satellite imagery for applications in hydrology, meteorology, and agriculture has led to the development of methods to produce variable-resolution soil moisture maps. Research on accurate soil moisture estimation using satellite imagery is essential for remote sensing applications. The purpose of this study is to generate a soil moisture estimation map for a test area using KOMPSAT-3/3A and KOMPSAT-5 SAR imagery and to quantitatively compare the results with soil moisture data from the Soil Moisture Active Passive (SMAP) mission provided by NASA, with a focus on accuracy validation. In addition, the Korean Environmental Geographic Information Service (EGIS) land cover map was used to determine soil moisture, especially in agricultural and forested regions. The selected test area for this study is the western part of Jeju, South Korea, where input data were available for the soil moisture estimation algorithm based on the Water Cloud Model (WCM). Synthetic Aperture Radar (SAR) imagery from KOMPSAT-5 HV and Sentinel-1 VV were used for soil moisture estimation, while vegetation indices were calculated from the surface reflectance of KOMPSAT-3 imagery. Comparison of the derived soil moisture results with SMAP (L-3) and SMAP (L-4) data by differencing showed a mean difference of 4.13±3.60 p% and 14.24±2.10 p%, respectively, indicating a level of agreement. This research suggests the potential for producing highly accurate and precise soil moisture maps using future South Korean satellite imagery and publicly available data sources, as demonstrated in this study.

• Journal of Korea Water Resources Association
• /
• v.56 no.10
• /
• pp.641-653
• /
• 2023

As climate change and urbanization are causing unprecedented natural disasters in urban areas, it is crucial to have urban flood predictions with high fidelity and accuracy. However, conventional physically- and deep learning-based urban flood modeling methods have limitations that require a lot of computer resources or data for high-resolution flooding analysis. In this study, we propose and implement a method for improving the spatial resolution of urban flood analysis using a deep learning based super-resolution technique. The proposed approach converts low-resolution flood maps by physically based modeling into the high-resolution using a super-resolution deep learning model trained by high-resolution modeling data. When applied to two cases of retrospective flood analysis at part of City of Portland, Oregon, U.S., the results of the 4-m resolution physical simulation were successfully converted into 1-m resolution flood maps through super-resolution. High structural similarity between the super-solution image and the high-resolution original was found. The results show promising image quality loss within an acceptable limit of 22.80 dB (PSNR) and 0.73 (SSIM). The proposed super-resolution method can provide efficient model training with a limited number of flood scenarios, significantly reducing data acquisition efforts and computational costs.

• The Journal of the Convergence on Culture Technology
• /
• v.9 no.6
• /
• pp.525-530
• /
• 2023

Digital drawing subjects require the subdivision of evaluation elements and the graduality of evaluation according to the recent movement of the innovative curriculum. The purpose of this paper is to present the criteria for evaluating the drawing and to propose it as a rubric evaluation. In the text, criteria for beginner evaluation were technical skills such as the accuracy and consistency of the line, the ratio and balance of the picture, and the ability to effectively utilize various brushes and tools at the intermediate levels. In the advanced evaluation section, it is a part of a new perspective or originality centered on creativity and originality, and a unique perspective or interpretation of a given subject. In addition, as an understanding of design principles, the evaluation of completeness was derived focusing on the ability to actively utilize various functions of digital drawing software through design principles such as placement, color, and shape. The importance of introducing rubric evaluation is to allow instructors to make objective and consistent evaluations, and the key to research in rubric evaluation in these art subjects is to help learners clearly grasp their strengths and weaknesses, and learners can identify what needs to be improved and develop better drawing skills accordingly through feedback on each item.

• Korean Journal of Construction Engineering and Management
• /
• v.25 no.3
• /
• pp.37-46
• /
• 2024

Recently, 3D laser scanning technology, which can collect accurate and quick information on phenomena, has been attracting attention among smart construction technologies. 3D laser scanning technology can obtain information most similar to reality at construction sites. In this study, we would like to apply a new member identification method to an actual building and present the possibility of applying point cloud data, which can be collected using 3D laser scanning technology, to measuring progress at construction sites. In order to carry out the research, we collected location information for component identification from BIM, set a recognition margin for the collected location information, and proceeded to identify the components that make up the building from point cloud data. Research results We confirmed that the columns, beams, walls, and slabs that make up a building can be identified from point cloud data. The identification results can be used to confirm all the parts that have been completed in the actual building, and can be used in conjunction with the unit price of each part in the project BOQ for prefabricated calculations. In addition, the point cloud data obtained through research can be used as accurate data for quality control monitoring of construction sites and building maintenance management. The research results can contribute to improving the timeliness and accuracy of construction information used in future project applications.

• Journal of Intelligence and Information Systems
• /
• v.25 no.1
• /
• pp.163-177
• /
• 2019

As smartphones are getting widely used, human activity recognition (HAR) tasks for recognizing personal activities of smartphone users with multimodal data have been actively studied recently. The research area is expanding from the recognition of the simple body movement of an individual user to the recognition of low-level behavior and high-level behavior. However, HAR tasks for recognizing interaction behavior with other people, such as whether the user is accompanying or communicating with someone else, have gotten less attention so far. And previous research for recognizing interaction behavior has usually depended on audio, Bluetooth, and Wi-Fi sensors, which are vulnerable to privacy issues and require much time to collect enough data. Whereas physical sensors including accelerometer, magnetic field and gyroscope sensors are less vulnerable to privacy issues and can collect a large amount of data within a short time. In this paper, a method for detecting accompanying status based on deep learning model by only using multimodal physical sensor data, such as an accelerometer, magnetic field and gyroscope, was proposed. The accompanying status was defined as a redefinition of a part of the user interaction behavior, including whether the user is accompanying with an acquaintance at a close distance and the user is actively communicating with the acquaintance. A framework based on convolutional neural networks (CNN) and long short-term memory (LSTM) recurrent networks for classifying accompanying and conversation was proposed. First, a data preprocessing method which consists of time synchronization of multimodal data from different physical sensors, data normalization and sequence data generation was introduced. We applied the nearest interpolation to synchronize the time of collected data from different sensors. Normalization was performed for each x, y, z axis value of the sensor data, and the sequence data was generated according to the sliding window method. Then, the sequence data became the input for CNN, where feature maps representing local dependencies of the original sequence are extracted. The CNN consisted of 3 convolutional layers and did not have a pooling layer to maintain the temporal information of the sequence data. Next, LSTM recurrent networks received the feature maps, learned long-term dependencies from them and extracted features. The LSTM recurrent networks consisted of two layers, each with 128 cells. Finally, the extracted features were used for classification by softmax classifier. The loss function of the model was cross entropy function and the weights of the model were randomly initialized on a normal distribution with an average of 0 and a standard deviation of 0.1. The model was trained using adaptive moment estimation (ADAM) optimization algorithm and the mini batch size was set to 128. We applied dropout to input values of the LSTM recurrent networks to prevent overfitting. The initial learning rate was set to 0.001, and it decreased exponentially by 0.99 at the end of each epoch training. An Android smartphone application was developed and released to collect data. We collected smartphone data for a total of 18 subjects. Using the data, the model classified accompanying and conversation by 98.74% and 98.83% accuracy each. Both the F1 score and accuracy of the model were higher than the F1 score and accuracy of the majority vote classifier, support vector machine, and deep recurrent neural network. In the future research, we will focus on more rigorous multimodal sensor data synchronization methods that minimize the time stamp differences. In addition, we will further study transfer learning method that enables transfer of trained models tailored to the training data to the evaluation data that follows a different distribution. It is expected that a model capable of exhibiting robust recognition performance against changes in data that is not considered in the model learning stage will be obtained.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.19 no.1
• /
• pp.95-107
• /
• 2017

In this study, a preliminary study was undertaken for development of a tunnel incident automatic detection system based on a machine learning algorithm which is to detect a number of incidents taking place in tunnel in real time and also to be able to identify the type of incident. Two road sites where CCTVs are operating have been selected and a part of CCTV images are treated to produce sets of training data. The data sets are composed of position and time information of moving objects on CCTV screen which are extracted by initially detecting and tracking of incoming objects into CCTV screen by using a conventional image processing technique available in this study. And the data sets are matched with 6 categories of events such as lane change, stoping, etc which are also involved in the training data sets. The training data are learnt by a resilience neural network where two hidden layers are applied and 9 architectural models are set up for parametric studies, from which the architectural model, 300(first hidden layer)-150(second hidden layer) is found to be optimum in highest accuracy with respect to training data as well as testing data not used for training. From this study, it was shown that the highly variable and complex traffic and incident features could be well identified without any definition of feature regulation by using a concept of machine learning. In addition, detection capability and accuracy of the machine learning based system will be automatically enhanced as much as big data of CCTV images in tunnel becomes rich.