• International Journal of Advanced Culture Technology
• /
• v.10 no.4
• /
• pp.536-546
• /
• 2022

A society will lose a lot of something in this field when the forest fire broke out. If a forest fire can be detected in advance, damage caused by the spread of forest fires can be prevented early. So, we studied how to detect forest fires using CCTV currently installed. In this paper, we present a deep learning-based model through efficient image data construction for monitoring forest fire smoke, which is unstructured data, based on the deep learning model YOLOv5. Through this study, we conducted a study to accurately detect forest fire smoke, one of the amorphous objects of various forms, in YOLOv5. In this paper, we introduce a method of self-learning by producing insufficient data on its own to increase accuracy for unstructured object recognition. The method presented in this paper constructs a dataset with a fixed labelling position for images containing objects that can be extracted from the original image, through the original image and a model that learned from it. In addition, by training the deep learning model, the performance(mAP) was improved, and the errors occurred by detecting objects other than the learning object were reduced, compared to the model in which only the original image was learned.

• Journal of the Korean Society of Manufacturing Process Engineers
• /
• v.21 no.3
• /
• pp.100-109
• /
• 2022

In this study, calibration technology that increases the alignment accuracy in large flexible flat panels was studied. For precise of calibration, a systematization of the calibration algorithm was established, and a calibration correction technique was studied to revise calibration errors. A coordinate systems of camera and UVW stage was established to get the global position of the mark, and equations for translational and rotational calibration were systematically derived based on geometrical analysis. Correction process for the calibration data was carried, and alignment experiments were performed sequentially in cases of the presence or absence of calibration-correction. Alignment results of both calibration correction and non-calibration correction showed accuracy performance less than 1㎛. On the other hand, the standard deviation in calibration-correction is smaller than non-calibration correction. Therefore, calibration correction showed improvement of the alignment repeatability.

• Physical Therapy Korea
• /
• v.29 no.3
• /
• pp.194-199
• /
• 2022

Background: Older adults use different ankle muscle activation patterns during difficult static balance conditions. It has been suggested that this is related to a decline in proprioception with age, resulting in reduced postural balance. However, the association between proprioception and ankle muscle activity during quiet standing has not been directly assessed. Objects: This study aimed to investigate the effects of age and sensory condition on ankle muscle activity and the association between ankle proprioception and ankle muscle activity. Methods: We recruited 10 young women and 9 older women. Ankle proprioception was evaluated using joint position sense (JPS) and force sense (FS) divided by dorsiflexion and plantarflexion. The electromyographic activity of the tibialis anterior (TA) and gastrocnemius (GCM) muscles was collected during quiet standing. Results: Older women activated GCM muscle more than young during quiet standing and when performing difficult tasks. Older women had more errors in JPS dorsiflexion and FS plantarflexion than did young. The GCM muscle activity is related to JPS dorsiflexion and FS plantarflexion. Conclusion: Lower proprioception of the GCM with age leads to increased muscle activity, resulting in reduced postural balance. There was no difference in TA proprioception or muscle activity among older women with frequent physical activity.

• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• v.2
• /
• pp.9-14
• /
• 2006

Galileo is the European Global Navigation Satellite System, under civilian control, and consists on a constellation of medium Earth orbit satellites and its associated ground infrastructure. Galileo will provide to their users highly accurate global positioning services and their associated integrity information. The elements in charge of the computation of Galileo navigation and integrity information are the OSPF (Orbit Synchronization Processing Facility) and IPF (Integrity Processing Facility), within the Galileo Ground Mission Segment (GMS). Navigation algorithms play a key role in the provision of the Galileo Mission, since they are responsible for computing the essential information the users need to calculate their position: the satellite ephemeris and clock offsets. Such information is generated in the Galileo Ground Mission Segment and broadcast by the satellites within the navigation signal, together with the expected a-priori accuracy (SISA: Signal-In-Space Accuracy), which is the parameter that in fault-free conditions makes the overbounding the predicted ephemeris and clock model errors for the Worst User Location. In parallel, the integrity algorithms of the GMS are responsible of providing a real-time monitoring of the satellite status with timely alarm messages in case of failures. The accuracy of the integrity monitoring system is characterized by the SISMA (Signal In Space Monitoring Accuracy), which is also broadcast to the users through the integrity message.

• International Journal of Korean Welding Society
• /
• v.2 no.1
• /
• pp.45-51
• /
• 2002

In the multi-pass welding of pressure vessels or ships, the mechanical touch sensor system is generally used together with a manipulator to measure the gap and depth of the narrow gap to perform seam tracking. Unfortunately, such mechanical touch sensors may commit measuring errors caused by the deterioration of the measuring device. An automation system of narrow gap multi-pass welding using a laser vision system which can track the seam line of narrow gap and which can control welding power has been developed. The joint profile of the narrow gap, with 250mm depth and 28mm width, can be captured by laser vision camera. The image is then processed for defining tracking positions of the torch during welding. Then, the real-time correction of lateral and vertical position of the torch can be done by the laser vision system. The adaptive control of welding conditions like welding currents and welding speeds, can also be performed by the laser vision system, which cannot be done by conventional mechanical touch systems. The developed automation system will be adopted to reduce the idle time of welders, which happens frequently in conventional long welding processes, and to improve the reliability of the weld quality as well.

• Journal of Ocean Engineering and Technology
• /
• v.37 no.1
• /
• pp.38-48
• /
• 2023

To maintain the existing systems of ships and introduce autonomous operation technology, it is necessary to improve situational awareness through the sensor fusion of the automatic identification system (AIS) and automatic radar plotting aid (ARPA), which are installed sensors. This study proposes an algorithm for determining whether AIS and ARPA signals are sent to the same ship in real time. To minimize the number of errors caused by the time series and abnormal phenomena of heterogeneous signals, a tracking method based on the combination of the unscented Kalman filter and probabilistic data association filter is performed on ARPA radar signals, and a position prediction method is applied to AIS signals. Especially, the proposed algorithm determines whether the signal is for the same vessel by comparing motion-related components among data of heterogeneous signals to which the corresponding method is applied. Finally, a measurement test is conducted on a training ship. In this process, the proposed algorithm is validated using the AIS and ARPA signal data received by the voyage data recorder for the same ship. In addition, the proposed algorithm is verified by comparing the test results with those obtained from raw data. Therefore, it is recommended to use a sensor fusion algorithm that considers the characteristics of sensors to improve the situational awareness accuracy of existing ship systems.

• Steel and Composite Structures
• /
• v.46 no.6
• /
• pp.731-744
• /
• 2023

Vehicle load information is an important role in operating and ensuring the structural health of cable-stayed bridges. In this regard, an efficient and economic method is proposed for vehicle load detection based on the observed cable tension and vehicle position using a graph neural network (GNN). Datasets are first generated using the practical advanced analysis program (PAAP), a robust program for modeling and considering both geometric and material nonlinearities of bridge structures subjected to vehicle load with low computational costs. With the superiority of GNN, the proposed model is demonstrated to precisely capture complex nonlinear correlations between the input features and vehicle load in the output. Four popular machine learning methods including artificial neural network (ANN), decision tree (DT), random forest (RF), and support vector machines (SVM) are refereed in a comparison. A case study of a cable-stayed bridge with the typical truck is considered to evaluate the model's performance. The results demonstrate that the GNN-based model provides high accuracy and efficiency in prediction with satisfactory correlation coefficients, efficient determination values, and very small errors; and is a novel approach for vehicle load detection with the input data of the existing monitoring system.

• Journal of Positioning, Navigation, and Timing
• /
• v.12 no.4
• /
• pp.349-358
• /
• 2023

The Satellite-Based Augmentation System (SBAS) plays a significant role in the fields of aviation and navigation: it corrects signal errors of the Global Navigation Satellite System (GNSS) and provides integrity information to facilitate precise positioning. These SBAS systems have been adopted as international standards by the International Civil Aviation Organization (ICAO). In recent SBAS system design, the Minimum Operational Performance Standards (MOPS) defined by the Radio Technical Commission for Aeronautics (RTCA) must be followed. In October 2014, South Korea embarked on the development of a Korean GPS precision position correction system, referred to as Korea Augmentation Satellite System (KASS). The goal is to achieve APV-1 Standard of Service Level (SoL) service level and acquisition of CAT-1 test operating technology. The first satellite of KASS, KASS Prototype 1, was successfully launched from the Guiana Space Centre in South America on June 23, 2020. In December 2022 and June 2023, the first and second service signals of KASS were broadcasted, and full-scale KASS correction signal broadcasting is scheduled to start at the end of 2023. The aim of this study is to analyze the precision of both the GNSS system and KASS system by comparing them. KASS is also compared with Japan's Multi-functional Satellite Augmentation System (MSAS), which is available in Korea. The final objective of this work is to validate the usefulness of KASS correction navigation in the South Korean operational environment.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.19 no.2
• /
• pp.437-444
• /
• 2024

The rotational inertial navigation system can provide more accurate navigation information by mounting an IMU (Inertial Measurement Unit) on the gimbal and rotating the gimbal regularly to cancel out the errors of the IMU. However, when an attitude change occurs due to waves, the attitude error is not removed to 0 at the end of one cycle of the rotation procedure and causes a large position error. In this paper, considering this problem, we propose a method of stabilizing the external gimbal by rotating it based on the roll information of the vehicle. Based on simulation, the impact of waves is analyzed and the performance of external gimbal stabilization is verified.

• Journal of Positioning, Navigation, and Timing
• /
• v.13 no.1
• /
• pp.63-73
• /
• 2024

NeQuick G is the ionosphere model utilized by Galileo single-frequency users to estimate the ionospheric delay on each user-satellite link. The model is characterized by the effective ionization level (Az) index, determined by a modified dip latitude (MODIP) and broadcast coefficients derived from daily global space weather observations. However, globally fitted Az coefficients may not accurately represent ionosphere within local area. This study introduces a method for regional ionospheric modeling that searches for locally optimized Az coefficients. This approach involves fitting TEC output from NeQuick G to TEC data collected from GNSS stations around Korea under various ionospheric conditions including different seasons and both low and high solar activity phases. The optimized Az coefficients enable calculation of the Az index at any position within a region of interest, accounting for the spatial variability of the Az index in a polynomial function of MODIP. The results reveal reduced TEC estimation errors, particularly during high solar activity, with a maximum reduction in the RMS error by 85.95%. This indicates that the proposed method for NeQuick G can effectively model various ionospheric conditions in local areas, offering potential applications in GNSS performance analyses for local areas by generating various ionospheric scenarios.