• Journal of the Korean Geotechnical Society
• /
• v.37 no.5
• /
• pp.47-63
• /
• 2021

Recently, the demand for three-dimensional (3D) underground maps from the perspective of digital twins and the demand for linkage utilization are increasing. However, the vastness of national geotechnical survey data and the uncertainty in applying geostatistical techniques pose challenges in modeling underground regional geotechnical characteristics. In this study, an optimal learning model based on multi-layer perceptron (MLP) was constructed for 3D subsurface lithological and geotechnical classification in Seoul, South Korea. First, the geotechnical layer and 3D spatial coordinates of each borehole dataset in the Seoul area were constructed as a geotechnical database according to a standardized format, and data pre-processing such as correction and normalization of missing values for machine learning was performed. An optimal fitting model was designed through hyperparameter optimization of the MLP model and model performance evaluation, such as precision and accuracy tests. Then, a 3D grid network locally assigning geotechnical layer classification was constructed by applying an MLP-based bet-fitting model for each unit lattice. The constructed 3D geotechnical layer map was evaluated by comparing the results of a geostatistical interpolation technique and the topsoil properties of the geological map.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.29 no.1D
• /
• pp.135-143
• /
• 2009

Integrating the Global Positioning System (GPS) and Inertial Navigation System (INS) sensor technologies using the precise GPS Carrier phase measurements is a methodology that has been widely applied in those application fields requiring accurate and reliable positioning and attitude determination; ranging from 'kinematic geodesy', to mobile mapping and imaging, to precise navigation. However, such integrated system may not fulfil the demanding performance requirements when the baseline length between reference and mobil user GPS receiver is grater than a few tens of kilometers. This is because their positioning/attitude determination is still very dependent on the errors of the GPS observations, so-called "baseline dependent errors". This limitation can be remedied by the integration of GPS and INS sensors, using multiple reference stations. Hence, in order to derive the GPS distance dependent errors, this research proposes measurement processing algorithms for multiple reference stations, such as a reference station ambiguity resolution procedure using linear combination techniques, a error estimation based on Kalman filter and a error interpolation. In addition, all the algorithms are evaluated by processing real observations and results are summarized in this paper.

• The Journal of the Convergence on Culture Technology
• /
• v.10 no.4
• /
• pp.687-692
• /
• 2024

The energy crisis is emerging as a serious problem around the world. In the case of Korea, there is great interest in energy efficiency research related to industrial complexes, which use more than 53% of total energy and account for more than 45% of greenhouse gas emissions in Korea. One of the studies is a study on saving energy through sharing facilities between factories using the same utility in an industrial complex called a virtual energy network plant and through transactions between energy producing and demand factories. In such energy-saving research, data collection is very important because there are various uses for data, such as analysis and prediction. However, existing systems had several shortcomings in reliably collecting time series data. In this study, we propose an intelligent IIoT platform to improve it. The intelligent IIoT platform includes a preprocessing system to identify abnormal data and process it in a timely manner, classifies abnormal and missing data, and presents interpolation techniques to maintain stable time series data. Additionally, time series data collection is streamlined through database optimization. This paper contributes to increasing data usability in the industrial environment through stable data collection and rapid problem response, and contributes to reducing the burden of data collection and optimizing monitoring load by introducing a variety of chatbot notification systems.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.14 no.3
• /
• pp.78-95
• /
• 2011

This study has developed various DEMs with different spatial resolutions using many different interpolation methods with the aid of a 1:5,000 digital map. In addition, this study has evaluated the vertical accuracy of various DEMs constructed by check point data obtained from the network RTK GPS survey. The obtained results suggest that a DEM developed from the TIN-based Terrain method performs well in evaluating height restriction of buildings in a flying safety area considering general RMSE values, land-type RMSE values and profile evaluation results, etc. And, it has been found that three meters is the right spatial resolution for a DEM in evaluating height restriction of buildings in a flying safety area. Meanwhile, elevation values obtained by the DEM are not point estimation values but interval estimation values. This can be used to check whether the height of buildings in the vicinity of an airfield violates height limitation values of the area. To check whether the height of buildings measured in interval estimation values violates height limitation values of the area, this study has adopted three steps: 1) high probability of violation, 2) low probability of violation, 3) inconclusiveness about the violation. The obtained results will provide an important basis for developing a GIS related to the evaluation of height restriction of buildings in the vicinity of an airfield. Furthermore, although results are limited to the study area, the vertical accuracy values of the DEM constructed from a two-dimensional digital map may provide useful information to researchers who try to use DEMs.

• Korean Journal of Agricultural and Forest Meteorology
• /
• v.18 no.4
• /
• pp.208-220
• /
• 2016

Automatic Mountain Meteorology Observation System (AMOS) is an important ingredient for several climatological and forest disaster prediction studies. In this study, we select the optimal sites for AMOS in the mountain areas of Honam and Jeju in order to prevent forest disasters such as forest fires and landslides. So, this study used spatial dataset such as national forest map, forest roads, hiking trails and 30m DEM(Digital Elevation Model) as well as forest risk map(forest fire and landslide), national AWS information to extract optimal site selection of AMOS. Technical methods for optimal site selection of the AMOS was the firstly used multifractal model, IDW interpolation, spatial redundancy for 2.5km AWS buffering analysis, and 200m buffering analysis by using ArcGIS. Secondly, optimal sites selected by spatial analysis were estimated site accessibility, observatory environment of solar power and wireless communication through field survey. The threshold score for the final selection of the sites have to be higher than 70 points in the field assessment. In the result, a total of 159 polygons in national forest map were extracted by the spatial analysis and a total of 64 secondary candidate sites were selected for the ridge and the top of the area using Google Earth. Finally, a total of 26 optimal sites were selected by quantitative assessment based on field survey. Our selection criteria will serve for the establishment of the AMOS network for the best observations of weather conditions in the national forests. The effective observation network may enhance the mountain weather observations, which leads to accurate prediction of forest disasters.

• 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 the Korean Association of Geographic Information Studies
• /
• v.19 no.3
• /
• pp.61-74
• /
• 2016

The purpose of this paper is to analyze the relationship between the location of the epicenter of a medium-sized earthquake(magnitude 4.8) that occurred on January 20, 2007 in the Odaesan area with lineament features using a shaded relief map(1/25,000 scale) and satellite images from LANDSAT-8 and KOMPSAT-2. Previous studies have analyzed lineament features in tectonic settings primarily by examining two-dimensional satellite images and shaded relief maps. These methods, however, limit the application of the visual interpretation of relief features long considered as the major component of lineament extraction. To overcome some existing limitations of two-dimensional images, this study examined three-dimensional images, produced from a Digital Elevation Model and drainage network map, for lineament extraction. This approach reduces mapping errors introduced by visual interpretation. In addition, spline interpolation was conducted to produce density maps of lineament frequency, intersection, and length required to estimate the density of lineament at the epicenter of the earthquake. An algorithm was developed to compute the Value of the Relative Density(VRD) representing the relative density of lineament from the map. The VRD is the lineament density of each map grid divided by the maximum density value from the map. As such, it is a quantified value that indicates the concentration level of the lineament density across the area impacted by the earthquake. Using this algorithm, the VRD calculated at the earthquake epicenter using the lineament's frequency, intersection, and length density maps ranged from approximately 0.60(min) to 0.90(max). However, because there were differences in mapped images such as those for solar altitude and azimuth, the mean of VRD was used rather than those categorized by the images. The results show that the average frequency of VRD was approximately 0.85, which was 21% higher than the intersection and length of VRD, demonstrating the close relationship that exists between lineament and the epicenter. Therefore, it is concluded that the density map analysis described in this study, based on lineament extraction, is valid and can be used as a primary data analysis tool for earthquake research in the future.

• Korean Journal of Agricultural and Forest Meteorology
• /
• v.24 no.2
• /
• pp.63-77
• /
• 2022

Our aim was to reduce estimation errors of a wind velocity model used as an early warning system for weather risk management in the agricultural sector. The Rural Development Administration (RDA) agricultural weather observation network's wind velocity data and its corresponding estimated data from January to December 2020 were used to calculate linear regression equations (Y = aX + b). In each linear regression, the wind estimation error at 87 points and eight time slots per day (00:00, 03:00, 06:00, 09.00, 12.00, 15.00, 18.00, and 21:00) is the dependent variable (Y), while the estimated wind velocity is the independent variable (X). When the correlation coefficient exceeded 0.5, the regression equation was used as the wind velocity correction equation. In contrast, when the correlation coefficient was less than 0.5, the mean error (ME) at the corresponding points and time slots was substituted as the correction value instead of the regression equation. To enable the use of wind velocity model at a national scale, a distribution map with a grid resolution of 250 m was created. This objective was achieved b y performing a spatial interpolation with an inverse distance weighted (IDW) technique using the regression coefficients (a and b), the correlation coefficient (R), and the ME values for the 87 points and eight time slots. Interpolated grid values for 13 weather observation points in rural areas were then extracted. The wind velocity estimation errors for 13 points from January to December 2019 were corrected and compared with the system's values. After correction, the mean ME of the wind velocities reduced from 0.68 m/s to 0.45 m/s, while the mean RMSE reduced from 1.30 m/s to 1.05 m/s. In conclusion, the system's wind velocities were overestimated across all time slots; however, after the correction model was applied, the overestimation reduced in all time slots, except for 15:00. The ME and RMSE improved b y 33% and 19.2%, respectively. In our system, the warning for wind damage risk to crops is driven by the daily maximum wind speed derived from the daily mean wind speed obtained eight times per day. This approach is expected to reduce false alarms within the context of strong wind risk, by reducing the overestimation of wind velocities.