Sangho Lee

Sangho Lee

Auto-generated profile, based on publicly available information

Sangho Lee

Geo-Resources Convergence Knowledge Division, Korea Institute of Geoscience and Mineral Resources, Daejeon, Republic of Korea

Research Focus & Metrics

Academic Career Length

10Years (2017-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
21 November 2017 in Minerals
Verified
Journal Article
Open access
PDF file
Jieun BaekJieun Baek
Jieun Baek
Yosoon ChoiYosoon Choi
Yosoon Choi
CLChaeyoung Lee
Chaeyoung Lee
Jangwon SuhJangwon Suh
Jangwon Suh
SLSangho Lee
Sangho Lee
A Bluetooth beacon-based underground navigation system (BBUNS) was developed to identify the optimal haul road in an underground mine, track the locations of dump trucks, and display this information on mobile devices. A three-dimensional (3-D) geographic information system (GIS) database of the haul roads in an underground mine was constructed, and the travel time for each section was calculated. A GIS database was also constructed for 50 Bluetooth beacons that were installed along the haul roads. An Android-based BBUNS application was developed to visualize the current location of each dump truck and the optimal haul road to the destination on mobile devices, using the Bluetooth beacon system that was installed in the underground mine. Whenever the BBUNS recognized all of the Bluetooth beacons installed in the underground mine, it could provide the dump truck drivers with information on the current location and the two-dimensional (2-D) and 3-D haul road properties. The operating time of each dump truck and the time spent on each unit task could be analyzed using recorded data on the times when Bluetooth beacon signals were recognized by the BBUNS. The underground mine navigation system that was developed in this study can contribute to the improvement of haul operation efficiency and productivity.

Verified
Journal Article
Open access
PDF file
SASeongin Ahn
Seongin Ahn
DRDong-Woo Ryu
Dong-Woo Ryu
SLSangho Lee
Sangho Lee
With the development of machine learning technology, research cases for spatial estimation through machine learning approach (MLA) in addition to the traditional geostatistical techniques are increasing. MLA has the advantage that spatial estimation is possible without stationary hypotheses of data, but it is possible for the prediction results to ignore spatial autocorrelation. In recent studies, it was considered by using a distance matrix instead of raw coordinates. Although, the performance of spatial estimation could be improved through this approach, the computational complexity of MLA increased rapidly as the number of sample points increased. In this study, we developed a method to reduce the computational complexity of MLA while considering spatial autocorrelation. Principal component analysis is applied to it for extracting spatial features and reducing dimension of inputs. To verify the proposed approach, indicator Kriging was used as a benchmark model, and each performance of MLA was compared when using raw coordinates, distance vector, and spatial features extracted from distance vector as inputs. The proposed approach improved the performance compared to previous MLA and showed similar performance compared with Kriging. We confirmed that extracted features have characteristics of rigid classification in spatial estimation; on this basis, we conclude that the model could improve performance.

12 June 2019 in IEEE Geoscience and Remote Sensing Letters
Verified
Journal Article
Closed access
JKJae-Mo Kang
Jae-Mo Kang
IKILMIN KIM
ILMIN KIM
SLSangho Lee
Sangho Lee
DRDong-Woo Ryu
Dong-Woo Ryu
JKJihoe Kwon
Jihoe Kwon
Ground vibration monitoring with microelectromechanical systems (MEMS) sensors is very effective and promising for alerting geological disasters. In this letter, explicitly considering and effectively addressing several specific issues related to practical MEMS sensors, we develop a novel ground vibration monitoring scheme for MEMS sensed data based on a deep convolutional neural network (CNN). Experiments are then conducted on the synthetic and real data sets. Experimental results on both data sets demonstrate that the proposed scheme significantly outperforms the other comparable schemes. For the synthetic data set, the proposed scheme achieves a very high overall accuracy of 98.82%. Also, for the real data set, the proposed scheme achieves a high overall accuracy of 81.64%, which is about 7% higher than that reported in the literature.

18 October 2017 in Minerals
Verified
Journal Article
Open access
PDF file
Jangwon SuhJangwon Suh
Jangwon Suh
SLSangho Lee
Sangho Lee
Yosoon ChoiYosoon Choi
Yosoon Choi
Conventional mine site investigation has difficulties in fostering location awareness and understanding the subsurface environment; moreover, it produces a large amount of hardcopy data. To overcome these limitations, the UMineAR mobile tablet application was developed. It enables users to rapidly identify underground mine objects (drifts, entrances, boreholes, hazards) and intuitively visualize them in 3D using a mobile augmented reality (AR) technique. To design UMineAR, South Korean georeferenced standard-mine geographic information system (GIS) databases were employed. A web database system was designed to access via a tablet groundwater-level data measured every hour by sensors installed in boreholes. UMineAR consists of search, AR, map, and database modules. The search module provides data retrieval and visualization options/functions. The AR module provides 3D interactive visualization of mine GIS data and camera imagery on the tablet screen. The map module shows the locations of corresponding borehole data on a 2D map. The database module provides mine GIS database management functions. A case study showed that the proposed application is suitable for onsite visualization of high-volume mine GIS data based on geolocations; no specialized equipment or skills are required to understand the underground mine environment. UMineAR can be used to support abandoned-mine hazard site investigations.

30 March 2021 in IEEE Geoscience and Remote Sensing Letters
Verified
Journal Article
Closed access
SYSangseok Yun
Sangseok Yun
JKJae-Mo Kang
Jae-Mo Kang
JHJeongseok Ha
Jeongseok Ha
SLSangho Lee
Sangho Lee
DRDong-Woo Ryu
Dong-Woo Ryu
IKILMIN KIM
ILMIN KIM
This letter studies deep learning-based efficient ground vibration monitoring systems. In this work, artificial intelligence (AI) techniques are adopted to effectively deal with practical issues of data collection and classification. Specifically, we develop a novel energy-efficient data collection scheme by adopting deep Q-network-based reinforcement learning. Also, we propose an enhanced joint recurrent neural network (RNN) and convolutional neural network (CNN) approach for ground vibration classification. The performance of the proposed scheme is evaluated using real-world ground vibration data. The experimental results show that the proposed classification scheme outperforms the best existing scheme with CNN by more than 13% in terms of classification accuracy. It is also shown that the proposed energy management scheme can improve the accuracy of the proposed ground vibration monitoring system by 7.6% over the comparable scheme using equal power allocation.

1 October 2019 in Journal of the Korean Society of Mineral and Energy Resources Engineers
Verified
Journal Article
Open access
SLSangho Lee
Sangho Lee