• Journal of Drive and Control
• /
• v.17 no.4
• /
• pp.133-140
• /
• 2020

Traction performance of a tractor varies depending on soil conditions. Sinkage and slip of the driving wheel for tractor frequently occur in a reclaimed land. The objective of this study was to develop a tractor suitable for a reclaimed land. Traction performance was evaluated according to soil conditions of reclaimed land and paddy field. Field experiments were conducted at two test sites (Fields A: paddy field; and Field B: reclaimed land). The tractor load measurement system was composed of an axle rotation speed sensor, a torque meter, a six-component load cell, GPS, and a DAQ (Data Acquisition System). Soil properties including soil texture, water content, cone index, and electrical conductivity (EC) were measured. Referring to previous researches, the tractor traveling speed was set to B3 (7.05 km/h), which was frequently used in ridge plow tillage. Soil moisture contents were 33.2% and 48.6% in fields A and B, respectively. Cone index was 2.1 times higher in field A than in field B. When working in the reclaimed land, slip ratios were about 10.5% and 33.1% for fields A and B, respectively. The engine load was used almost 100% of all tractors under the two field conditions. Traction powers were 31.9 kW and 24.2 kW for fields A and B, respectively. Tractive efficiencies were 83.3% and 54.4% for fields A and B, respectively. As soil moisture increased by 16.4%, the tractive efficiency was lowered by about 28.9%. Traction performance of tractor was significantly different according to soil conditions of fields A and B. Therefore, it is necessary to improve the traction performance of tractor for smooth operations in all soil conditions including a reclaimed land by reflecting data of this study.

• Economic and Environmental Geology
• /
• v.54 no.4
• /
• pp.475-482
• /
• 2021

This study proposed a strategy with literature review on effective monitoring of dispersion of the particulate matters (PM) emitted from domestic open pit lime mines. The mines generally produced a large amount of PM through the mine processes such as crushing and transportation of raw or crushed ores. The PM emission from mine facilities or transportation can be assessed using empirical equations which was prepared through the experimental tests to produce PM from ores. For effective monitoring of mine PM dispersion, this study showed a preliminary application of the monitoring network with multiple low-cost sensors around a main PM emission source for each mine site. Therefore, two domestic limestone mine sites were selected for this study, and install the monitoring network with low-cost PM sensors and LTE (Long-term evolution) data communication. Then, preliminary resultant PM data plotted according to monitoring duration showed typical PM dispersion patterns. The quantification of the PM dispersion patterns should be roughly prepared by a PM size-dependent dispersion modeling.

• KIPS Transactions on Software and Data Engineering
• /
• v.11 no.3
• /
• pp.141-148
• /
• 2022

Recently, reinforcement learning combined with deep neural network technology has achieved remarkable success in various fields such as board games such as Go and chess, computer games such as Atari and StartCraft, and robot object manipulation tasks. However, such deep reinforcement learning describes states, actions, and policies in vector representation. Therefore, the existing deep reinforcement learning has some limitations in generality and interpretability of the learned policy, and it is difficult to effectively incorporate domain knowledge into policy learning. On the other hand, dNL-RRL, a new relational reinforcement learning framework proposed to solve these problems, uses a kind of vector representation for sensor input data and lower-level motion control as in the existing deep reinforcement learning. However, for states, actions, and learned policies, It uses a relational representation with logic predicates and rules. In this paper, we present dNL-RRL-based policy learning for transportation mobile robots in a manufacturing environment. In particular, this study proposes a effective method to utilize the prior domain knowledge of human experts to improve the efficiency of relational reinforcement learning. Through various experiments, we demonstrate the performance improvement of the relational reinforcement learning by using domain knowledge as proposed in this paper.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.25 no.2
• /
• pp.1-17
• /
• 2022

This study analyzed the PM_2.5 pattern by using data measured for one year from June 2020 to May 2021 by 21 low-cost sensors installed near the Changwon National Industrial Complex in Changwon, Gyeongsangnam-do. For the PM_2.5 pattern, the land use types around the measuring points and meteorological factors such as air temperature and wind speed were considered. The PM_2.5 concentration was high from November to March in winter, and from 1 to 9 in the morning and early in the morning by time zone. The concentration of PM_2.5 was higher as it got closer to the industrial area, but the concentration was lower in the residential area and public facility area. In terms of meteorological factors, the higher the air temperature and wind speed, the lower the concentration of PM_2.5. As a result of this study, it was possible to identify the PM_2.5 patter near Changwon National Industrial Complex. This result will be useful data that can be used in urban and environmental planning to improve air quality including PM_2.5 in urban area in the future.

• Korean Journal of Remote Sensing
• /
• v.38 no.5_3
• /
• pp.967-977
• /
• 2022

The occurrence and intensity of wildfires are increasing with climate change. Emissions from forest fire smoke are recognized as one of the major causes affecting air quality and the greenhouse effect. The use of satellite product and machine learning is essential for detection of forest fire smoke. Until now, research on forest fire smoke detection has had difficulties due to difficulties in cloud identification and vague standards of boundaries. The purpose of this study is to detect forest fire smoke using Level 1 and Level 2 data of Geostationary Environment Monitoring Spectrometer (GEMS), a Korean environmental satellite sensor, and machine learning. In March 2022, the forest fire in Gangwon-do was selected as a case. Smoke pixel classification modeling was performed by producing wildfire smoke label images and inputting GEMS Level 1 and Level 2 data to the random forest model. In the trained model, the importance of input variables is Aerosol Optical Depth (AOD), 380 nm and 340 nm radiance difference, Ultra-Violet Aerosol Index (UVAI), Visible Aerosol Index (VisAI), Single Scattering Albedo (SSA), formaldehyde (HCHO), nitrogen dioxide (NO₂), 380 nm radiance, and 340 nm radiance were shown in that order. In addition, in the estimation of the forest fire smoke probability (0 ≤ p ≤ 1) for 2,704 pixels, Mean Bias Error (MBE) is -0.002, Mean Absolute Error (MAE) is 0.026, Root Mean Square Error (RMSE) is 0.087, and Correlation Coefficient (CC) showed an accuracy of 0.981.

• Korean Journal of Remote Sensing
• /
• v.38 no.3
• /
• pp.311-326
• /
• 2022

The Compact Advanced Satellite 500-4 (CAS500-4) is under development to efficiently manage and monitor forests in Korea and is scheduled to launch in 2025. The National Institute of Forest Science is developing 36 types of forestry applications to utilize the CAS500-4 efficiently. The products derived using the remote sensing method require validation with ground reference data, and the quality monitoring results for the products must be continuously reported. Due to it being the first time developing the national forestry satellite, there is no official calibration and validation site for forestry products in Korea. Accordingly, the author designed a calibration and validation site for the forestry products following international standards. In addition, to install calibration and validation sites nationwide, the authors selected appropriate sensors and evaluated the applicability of the sensors. As a result, the difference between the ground observation data and the Sentinel-2 image was observed to be within ±5%, confirming that the sensor could be used for nationwide expansion.

• KIPS Transactions on Computer and Communication Systems
• /
• v.11 no.2
• /
• pp.67-72
• /
• 2022

Recently, various intelligent application services using artificial intelligence are being actively developed. In particular, research on artificial intelligence-based real-time prediction services is being actively conducted in the manufacturing industry, and the demand for artificial intelligence services that can detect and predict fire and odors is very high. However, most of the existing detection and prediction systems do not predict the occurrence of fires and odors, but rather provide detection services after occurrence. This is because AI-based prediction service technology is not applied in existing systems. In addition, fire prediction, odor detection and odor level prediction services are services with ultra-low delay characteristics. Therefore, in order to provide ultra-low-latency prediction service, edge computing technology is combined with artificial intelligence models, so that faster inference results can be applied to the field faster than the cloud is being developed. Therefore, in this paper, we propose an LSTM algorithm-based learning model that can be used for fire prediction and odor detection/prediction, which are most required in the manufacturing industry. In addition, the proposed learning model is designed to be implemented in edge devices, and it is proposed to receive real-time sensor data from the IoT terminal and apply this data to the inference model to predict fire and odor conditions in real time. The proposed model evaluated the prediction accuracy of the learning model through three performance indicators, and the evaluation result showed an average performance of over 90%.

• Journal of Advanced Navigation Technology
• /
• v.27 no.2
• /
• pp.190-196
• /
• 2023

Recently, following the development of LIDAR technology which can detect distance from the object, the interest for LIDAR based 3D object detection network is getting higher. Previous networks generate inaccurate localization results due to spatial information loss during voxelization and downsampling. In this study, we propose an attention-based convergence method and a camera-LIDAR convergence system to acquire high-level features and high positional accuracy. First, by introducing the attention method into the Voxel-RCNN structure, which is a grid-based 3D object detection network, the multi-scale sparse 3D convolution feature is effectively fused to improve the performance of 3D object detection. Additionally, we propose the late-fusion mechanism for fusing outcomes in 3D object detection network and 2D object detection network to delete false positive. Comparative experiments with existing algorithms are performed using the KITTI data set, which is widely used in the field of autonomous driving. The proposed method showed performance improvement in both 2D object detection on BEV and 3D object detection. In particular, the precision was improved by about 0.54% for the car moderate class compared to Voxel-RCNN.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.28 no.5A
• /
• pp.699-707
• /
• 2008

For most structural evaluation of bridge integrity, it is very important to measure the geometric profile, which is a major factor representing the global behavior of civil structures, especially bridges. In the past, because of the lack of appropriate methods to measure the deflection profile of bridges on site, the measurement of deflection has been restricted to just a few discrete points along the bridge, and the measuring points have been limited to the locations installed with displacement transducers. Thus, some methods for predicting the static deflection by using fiber optic strain sensors has been applied to simply supported bridges. In this study, a method of estimating the static deflection profile by using strains measured from suspension bridges was proposed. Based on the classical deflection theory of suspension bridges, an equation of deflection profile was derived and applied to obtain the actual deflection profile on Namhae suspension bridge. Field load tests were carried out to measure strains from FBG strain sensors attached inside the stiffening girder of the bridge. The predicted deflection profiles were compared with both precise surveying data and numerical analysis results. Thus, it is found that the equation of predicting the deflection profiles proposed in this study could be applicable to suspension bridges and the FBG strain sensors could be reliable on acquiring the strain data from bridges on site.

• The Sea:JOURNAL OF THE KOREAN SOCIETY OF OCEANOGRAPHY
• /
• v.21 no.1
• /
• pp.1-10
• /
• 2016

Currently available surface seawater partial pressure carbon dioxide ($pCO_2$) data sets in the East Sea are not enough to quantify statistically the carbon dioxide flux through the air-sea interface. To complement the scarcity of the $pCO_2$ measurements, we construct a neural network (NN) model based on satellite data to map $pCO_2$ for the areas, which were not observed. The NN model is constructed for the Ulleung Basin, where $pCO_2$ data are best available, to map and estimate the variability of $pCO_2$ based on in situ $pCO_2$ for the years from 2003 to 2012, and the sea surface temperature (SST) and chlorophyll data from the MODIS (Moderate-resolution Imaging Spectroradiometer) sensor of the Aqua satellite along with geographic information. The NN model was trained to achieve higher than 95% of a correlation between in situ and predicted $pCO_2$ values. The RMSE (root mean square error) of the NN model output was $19.2{\mu}atm$ and much less than the variability of in situ $pCO_2$. The variability of $pCO_2$ with respect to SST and chlorophyll shows a strong negative correlation with SST than chlorophyll. As SST decreases the variability of $pCO_2$ increases. When SST is lower than $15^{\circ}C$, $pCO_2$ variability is clearly affected by both SST and chlorophyll. In contrast when SST is higher than $15^{\circ}C$, the variability of $pCO_2$ is less sensitive to changes in SST and chlorophyll. The mean rate of the annual $pCO_2$ increase estimated by the NN model output in the Ulleung Basin is $0.8{\mu}atm\;yr^{-1}$ from 2003 to 2014. As NN model can successfully map $pCO_2$ data for the whole study area with a higher resolution and less RMSE compared to the previous studies, the NN model can be a potentially useful tool for the understanding of the carbon cycle in the East Sea, where accessibility is limited by the international affairs.