• Journal of Animal Science and Technology
• /
• v.63 no.4
• /
• pp.790-798
• /
• 2021

The objective of this study was evaluation of pig behavior changes related to temperature, relative humidity, volatile organic compounds (VOCs), and illuminance. A total of 24 growing pigs ([Yorkshire × Landrace] × Duroc) were used in the experiment. A sensor was installed at a height of 0.5 m in the center of the pig house. In experiment 1, temperature was changed every four days to 18℃ (T1), 22℃ (T2), 26℃ (T3), and then 30℃ (T4). In experiment 2, relative humidity was adjusted to 45% (low humidity [LH]), 60% (middle humidity [MH]), and then 75% (high humidity [HH]) for four days. In experiment 3, after cleaning the pig house just before experiment, only minimal ventilation was provided. VOCs and pig behaviors were observed for 7 days without cleaning the pig house. In experiment 4, three light bulbs of 40 W (470 lumens / 45 lx; low illuminance [LI]), 75 W (1,055 lumens / 103 lx; middle illuminance [MI]), and 100 W (1,521 lumens / 146 lx; high illuminance [HI]) were used for four days each. Pig behavior analysis was performed for following criteria : Feed intake, Standing, Lying, Sitting, Drink water, Rooting, Posture transition (lying-standing), Posture transition (standing-lying), Wallowing, and Biting. In experiment 1, feed intake time was lower (p < 0.05) for the T3 than other treatment groups. Standing time was highest (p < 0.05) for the T1 and lowest (p < 0.05) for the T3. Lying time was shorter (p < 0.05) in T1 and T2 compared to T3 and T4. Drinking frequency was higher (p < 0.05) for the T4 than other treatment groups. In experiment 2, the frequency of rooting and wallowing increased (p < 0.05) with increasing humidity. LH showed the lowest (p < 0.05) rooting frequency and HH showed the highest (p < 0.05) rooting frequency. In experiment 3, VOCs concentration did not (p > 0.05) change pig behavior. In experiment 4, lying time was the longest (p < 0.05) at LI and shortest (p < 0.05) at HI. Therefore, pig behavior is heavily influenced by the environment, especially temperature and humidity. However, correlation between pig behavior to VOCs and illuminance seems to be needed more research.

• Journal of the Korea Society for Simulation
• /
• v.30 no.2
• /
• pp.11-22
• /
• 2021

Sonobuoy is widely used as a very important sensor in combat management system using P-3 patrol aircraft due to its advantages of rapid searching into wide exploration range. It is necessary to verify the performance of developed sonobuoy system using various maritime test data in order to be successfully applied in combat management system. But it is difficult to acquire various real maritime data because it needs much time and effort. Therefore we have developed in this paper a synthetic signal generator and a simulator that they can verify the performance of sonobuoy system and evaluate its operational effectiveness without conducting maritime test. We have synthesized target signals based on the characteristics of underwater sound sources, and then developed the synthesized signal generator which consider to sound propagation etc. like as underwater environment. And in the simulator development we use a HMI technique to enhance the convenience of operator, and design to verify the performance of sonobuoy system. The developed signal generator and simulator can be used as useful tools to evaluate the operational effectiveness such as optimal deployment of sonobuoy in combat management system using P-3 patrol aircraft.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.21 no.3
• /
• pp.123-128
• /
• 2021

For accurate speed and current control in industrial applications, SRM (Switched Reluctance Motor) is very important to synchronize the stator phase excitation and rotor position in the drive due to its nature. In general, position sensors such as encoder and resolver are used to generate rotational force by exciting the stator winding according to the rotor position and to control the motor by using speed and position information. However, for these sensors, 1) the cost of the sensors is quite large in terms of price, so the proportion of the motor system to the total system cost is high. 2) In terms of mechanical, position sensors such as encoders and resolvers are attached to the stator to increase the size and weight. In conclusion, in order to drive the SRM, control based on the rotor position information should be basically performed, and it is important to design the SRM driving system according to the environment in consideration of the application field. Therefore, in this paper, we intend to study the driving and control characteristics of SRM through variable switching duty control by designing a low-cost analog driving device, deviating from the general control system using the conventional encoder and resolver.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.22 no.2
• /
• pp.104-112
• /
• 2021

For extrusion processes in the process industry, the need to build smart factories is increasing. However, in most extrusion production sites, the production method is continuous, and because the properties of the data are undeed, it is difficult to process the data. In order to solve this problem, we present a methodology utilizing a near field communication (NFC) sensor rather than water-based data entry. To this end, a wireless network environment was built, and a data management method was designed. A non-contact NFC method was studied for the production performance-data input method, and an analysis method was implemented using the pivot function of the Excel program. As a result, data input using NFC was automated, obtaining a quantitative effect from reducing the operator's data processing time. In addition, using the input data, we present a case where a bottleneck is improved due to quality problems.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.14 no.1
• /
• pp.22-28
• /
• 2021

Multivariate processes, such as chemical and mechanical process, power plants are operated in a state where several facilities are complexly connected, the fault of a particular system can also have fatal consequences for the entire process. In addition, since process data is measured in an unstable environment, outlier is likely to be include in the data. Therefore, monitoring technology is essential, which can remove outlier from measured data and detect failures in advance. In this paper, data obtained from dynamic and multivariate process models was used to detect fault in various type of processes. The dynamic process is a simulation of a process with autoregressive property, and the multivariate process is a model that describes a situation when a specific sensor fault. Mahalanobis distance was used to remove outlier contained in the data generated by dynamic process model and multivariate process model, and fault detection was performed using ICA. For comparison, we compared performance with and a conventional single ICA method. The proposed fault detection method improves performance by 0.84%p for bias data and 6.82%p for drift data in the dynamic process. In the case of the multivariate process, the performance was improves by 3.78%p, therefore, the proposed method showed better fault detection performance.

• Journal of the Korean earth science society
• /
• v.41 no.6
• /
• pp.575-587
• /
• 2020

Meteorological phenomena are observed by the Korea Meteorological Administration in a variety of ways (e.g., surface, upper-air, marine, ocean, and aviation). However, there are limits to the meteorological observation of the planetary boundary layer (PBL) that greatly affects human life. In particular, observations using a sonde or aircraft require significant observational costs in economic terms. Therefore, the goal of this study was to measure and analyze the meteorological factors of the vertical distribution of the see-land breeze among local meteorological phenomena using meteorological drones. To investigate the spatial distribution of the see-land breeze, a same integrated meteorological sensor was mounted on each drone at three different points (seaside, bottom of mountain, and mountainside), including the Boseong tall tower (BTT) at the Boseong Standard Weather Observatory (BSWO) in the Boseong region. Vertical profile observations for air temperature, relative humidity, wind direction, wind speed, and air pressure were conducted up to 400 m every 30 minutes from 1100 LST to 1800 LST on August 4, 2018. The spatial characteristics of meteorological phenomena for temperature, relative humidity, and atmospheric pressure were not shown at the four points. Strong winds (~8 m s-1) were observed from the midpoint (~100 m) at strong solar radiation hour, and in the afternoon the wind direction changed from the upper layer at the inland area to the west wind. It is expected that the analysis results of the lower atmospheric layer observed using the meteorological drone may help to improve the weather forecast more accurately.

• 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 Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.39 no.6
• /
• pp.541-548
• /
• 2021

Recently, multispectral cameras are being actively utilized in various application fields such as agriculture, forest management, coastal environment monitoring, and so on, particularly onboard UAV's. Resultant multispectral images are typically georeferenced primarily based on the onboard GPS (Global Positioning System) and IMU (Inertial Measurement Unit)or accurate positional information of the pixels, or could be integrated with ground control points that are directly measured on the ground. However, due to the high cost of establishing GCP's prior to the georeferencing or for inaccessible areas, it is often required to derive the positions without such reference information. This study aims to provide a means to improve the georeferencing performance of a multispectral camera images without involving such ground reference points, but instead with the simultaneously onboard high resolution RGB camera. The exterior orientation parameters of the drone camera are first estimated through the bundle adjustment, and compared with the reference values derived with the GCP's. The results showed that the incorporation of the images from a high resolution RGB camera greatly improved both the exterior orientation estimation and the georeferencing of the multispectral camera. Additionally, an evaluation performed on the direction estimation from a ground point to the sensor showed that inclusion of RGB images can reduce the angle errors more by one order.

• Journal of the Korea Computer Graphics Society
• /
• v.27 no.5
• /
• pp.63-71
• /
• 2021

Among drone autonomous flight technologies, obstacle avoidance is a very important technology that can prevent damage to drones or surrounding environments and prevent danger. Although the LiDAR sensor-based obstacle avoidance method shows relatively high accuracy and is widely used in recent studies, it has disadvantages of high unit price and limited processing capacity for visual information. Therefore, this paper proposes an obstacle avoidance algorithm for drones using camera-based PPO(Proximal Policy Optimization) reinforcement learning, which is relatively inexpensive and highly scalable using visual information. Drone, obstacles, target points, etc. are randomly located in a learning environment in the three-dimensional space, stereo images are obtained using a Unity camera, and then YOLov4Tiny object detection is performed. Next, the distance between the drone and the detected object is measured through triangulation of the stereo camera. Based on this distance, the presence or absence of obstacles is determined. Penalties are set if they are obstacles and rewards are given if they are target points. The experimennt of this method shows that a camera-based obstacle avoidance algorithm can be a sufficiently similar level of accuracy and average target point arrival time compared to a LiDAR-based obstacle avoidance algorithm, so it is highly likely to be used.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.40 no.3
• /
• pp.217-226
• /
• 2022

In the view of the application of high-precision spatial information production, UAV (Umanned Aerial Vehicle)-Photogrammetry has a problem in that it lacks specific procedures and detailed regulations for quantitative quality verification methods or certification of captured images. In addition, test tools for UAV image quality assessment use only the GSD (Ground Sample Distance), not MTF (Modulation Transfer Function), which reflects image resolution and contrast at the same time. This fact makes often the quality of UAV image inferior to that of manned aerial image. We performed MTF and GSD analysis simultaneously using a siemens star to confirm the necessity of MTF analysis in UAV image quality assessment. The analyzing results of UAV images taken with different payload and sensors show that there is a big difference in σ_MTF values, representing image resolution and the degree of contrast, but slightly different in GSD. It concluded that the MTF analysis is a more objective and reliable analysis method than just the GSD analysis method, and high-quality drone images can only be obtained when the operator make images after judging the proper selection the sensor performance, image overlaps, and payload type. However, the results of this study are derived from analyzing only images acquired by limited sensors and imaging conditions. It is therefore expected that more objective and reliable results will be obtained if continuous research is conducted by accumulating various experimental data in related fields in the future.