• Korean Journal of Remote Sensing
• /
• v.39 no.2
• /
• pp.193-205
• /
• 2023

A large amount of floating debris from land-based sources during heavy rainfall has negative social, economic, and environmental impacts, but there is a lack of monitoring systems for floating debris accumulation areas and amounts. With the recent development of artificial intelligence technology, there is a need to quickly and efficiently study large areas of water systems using drone imagery and deep learning-based object detection models. In this study, we acquired various images as well as drone images and trained with You Only Look Once (YOLO)v5s and the recently developed YOLO7 and YOLOv8s to compare the performance of each model to propose an efficient detection technique for land-based floating debris. The qualitative performance evaluation of each model showed that all three models are good at detecting floating debris under normal circumstances, but the YOLOv8s model missed or duplicated objects when the image was overexposed or the water surface was highly reflective of sunlight. The quantitative performance evaluation showed that YOLOv7 had the best performance with a mean Average Precision (intersection over union, IoU 0.5) of 0.940, which was better than YOLOv5s (0.922) and YOLOv8s (0.922). As a result of generating distortion in the color and high-frequency components to compare the performance of models according to data quality, the performance degradation of the YOLOv8s model was the most obvious, and the YOLOv7 model showed the lowest performance degradation. This study confirms that the YOLOv7 model is more robust than the YOLOv5s and YOLOv8s models in detecting land-based floating debris. The deep learning-based floating debris detection technique proposed in this study can identify the spatial distribution of floating debris by category, which can contribute to the planning of future cleanup work.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.52 no.3
• /
• pp.173-180
• /
• 2015

A passive type of fence security system was developed, which was based on electric charge detection technique. The implemented fence security system was installed at outskirts of greenhouse laboratory in the University of Seoul. The purpose of this research is to minimize false alarms by analyzing environmental noise. The existing system determines the intrusion alarm by analyzing the power of amplified signal, but the alarm was seriously affected by natural strong wind and heavy rainfall. The SAU(Signal Analysis Unit) sends input signals to remote server which displays intrusion alarm and stores all the information in database. The environmental noise such as temperature, humidity and wind speed was separately gathered to analyze a correlation with input signal. The input signal was analyzed for frequency characteristic using FFT(Fast Fourier Transform) and the algorithm that differentiate between intrusion alarm and environmental noise signal is improved. The proposed algorithm is applied for the site for one month as the same as the existing algorithm and the false alarm data was gathered and analyzed. The false alarm number was decreased by 98% after new algorithm was applied to the fence. The proposed algorithm improved the reliability at the field regarding environmental noise signal.

• Journal of the Korean Society for Precision Engineering
• /
• v.32 no.6
• /
• pp.529-536
• /
• 2015

A defect could be generated in bolts for a use of oil filters for the manufacturing process and then may affect to the safety and quality in bolts. Also, fine defects may be imbedded in oil filter system. So it is very important that such defects be investigated and screened during the multiple manufacturing processes. Therefore, in order effectively to evaluate the fine defects, the FEM simulations were performed to make characterization in the crack detection of the bolts and the parameters such as number of turns of the coil, the coil size, applied frequency were calculated based on the simulation results. Simulations were carried out for the defect signal of eddy current probe. Exciter and receiver were utilized. In this paper, the FEM simulations were performed in both bobbin-type and pancake-type probe, both probes were optimized under Eddy current FEM simulations and the results of calculation were discussed.

• Korean Journal of Remote Sensing
• /
• v.38 no.5_3
• /
• pp.901-912
• /
• 2022

The frequency of disasters is increasing due to global climate change, and unusual heavy rains and rainy seasons are occurring in Korea. Periodic monitoring and rapid detection are important because these weather conditions can lead to drought and flooding, causing secondary damage. Although research using optical images is continuously being conducted to determine the waterbody, there is a limitation in that it is difficult to detect due to the influence of clouds in order to detect floods that accompany heavy rain. Therefore, there is a need for research using synthetic aperture radar (SAR) that can be observed regardless of day or night in all weather. In this study, using Sentinel-1 SAR images that can be collected in near-real time as open data, the UNet model among deep learning algorithms that have recently been used in various fields was applied. In previous studies, waterbody detection studies using SAR images and deep learning algorithms are being conducted, but only a small number of studies have been conducted in Korea. In this study, to determine the applicability of deep learning of SAR images, UNet and the existing algorithm thresholding method were compared, and five indices and Sentinel-2 normalized difference water index (NDWI) were evaluated. As a result of evaluating the accuracy with intersect of union (IoU), it was confirmed that UNet has high accuracy with 0.894 for UNet and 0.699 for threshold method. Through this study, the applicability of deep learning-based SAR images was confirmed, and if high-resolution SAR images and deep learning algorithms are applied, it is expected that periodic and accurate waterbody change detection will be possible in Korea.

• Informatization Policy
• /
• v.31 no.2
• /
• pp.3-38
• /
• 2024

Hallucination is a significant barrier to the utilization of large-scale language models or multimodal models. In this study, we collected 654 computer science papers with "hallucination" in the abstract from arXiv from December 2022 to January 2024 following the advent of Chat GPT and conducted frequency analysis, knowledge network analysis, and literature review to explore the latest trends in hallucination research. The results showed that research in the fields of "Computation and Language," "Artificial Intelligence," "Computer Vision and Pattern Recognition," and "Machine Learning" were active. We then analyzed the research trends in the four major fields by focusing on the main authors and dividing them into data, hallucination detection, and hallucination mitigation. The main research trends included hallucination mitigation through supervised fine-tuning (SFT) and reinforcement learning with human feedback (RLHF), inference enhancement via "chain of thought" (CoT), and growing interest in hallucination mitigation within the domain of multimodal AI. This study provides insights into the latest developments in hallucination research through a technology-oriented literature review. This study is expected to help subsequent research in both engineering and humanities and social sciences fields by understanding the latest trends in hallucination research.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.12 no.6
• /
• pp.1121-1126
• /
• 2017

Various studies such as INS(: Inertial Navigation System) are conducting to estimate the position of UAV, because the GPS information of UAV is at risk like the GPS jamming. The position estimation using DoA and RTT are used to apply many radar systems, and that process can be applied in datalink of UAV. The general monopulse feed in UAV datalink is Multi-horn, because of the wide BW(: Band Width) and frequency range. And it needs wide SNR range of tracking because of the limited transmit power of airborne unit. The estimation error of position increase at low SNR, and the DoA is valid in only 3dB beam width but high SNR causes false of mainlobe detection because of large sidelobe. In this paper, We propose the method to achieve higher accuracy of DoA estimation on low SNR and review some idea that able to detect mainlobe.

• Korean Journal of Remote Sensing
• /
• v.24 no.6
• /
• pp.571-581
• /
• 2008

The sea fog occurs frequently in the west coast of Korea in spring and summer. This study focused on the detection of sea fog using MODIS satellite images. We presented a method for sea fog detection based on the homogeneity level between low stratus and sea fog, which was that the top surface of sea fog had a homogeneous aspect while that of low stratus had a heterogenous aspect. The results showed that the both homogeneity of $11{\mu}m$ brightness temperature (BT) and brightness temperature difference (BTD, $BT_{3.7{\mu}m}-BT_{11{\mu}m}$) were available to discriminate sea fog from low stratus. The frequency of difference between BT in fog/stratus area and BT in clear area provided reasonable result. In addition, the threshold values of standard deviations of BT and BTD in the fog/stratus area were applicable to differentiate fog from low stratus.

• The Journal of Korean Institute of Electromagnetic Engineering and Science
• /
• v.27 no.6
• /
• pp.531-538
• /
• 2016

In this paper, we design and fabricate a short range FMCW radar which detects and tracks a moving target in a two-dimensional domain using dual transceiver modules. For the short range radar, we propose a scheme for alternate extraction of the two-dimensional positions using one-dimensional range information from time division transceiver modules, and successfully apply the scheme to the two-dimensional short range radar. Measured results of the targets at 10 m and 30 m are presented as performance demonstration of each transceiver module. Also the performance of the two-dimensional radar is demonstrated using a two-dimensional target map, which uses the range bin corresponding to the frequency resolution, and the effectiveness of the proposed scheme is validated.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.10 no.7
• /
• pp.1532-1535
• /
• 2009

This paper describes a K-band CW radar transceiver suitable for power saving motion sensor. The presented transceiver module is designed and contains patch antennas, dielectric resonator oscillator (DRO), IF amplifier, mixer, divider. The designed divider and antenna are measured and the transmitting frequency and the power were fairly good for using in commercial applications. The transceiver is manufactured with a dimension of 35${\times}$35${\times}$10(mm) and can be adapted in various applications.

• Journal of the Korean Society of Visualization
• /
• v.20 no.3
• /
• pp.128-135
• /
• 2022

Cavitation occurs inevitably in marine propellers rotating at high speed in the water, which is a major cause of underwater radiated noise. Cavitation-induced noise from propellers rotating at a specific frequency not only reduces the sonar detection capability, but also exposes the ship's location, and it causes very fatal consequences for the survivability of the navy vessels. Therefore cavity inception speed (CIS) is one of the important factors determining the special performance of the ship. In this study, we present a method using computer vision that can detect and quantitatively estimate tip vortex cavitation on a propeller rotating at high speed. Based on the model test results performed in a large cavitation tunnel, the effectiveness of this method was verified.