• Korean Journal of Remote Sensing
• /
• v.37 no.3
• /
• pp.493-502
• /
• 2021

Recently, because of changes in temperature and rising water temperatures due to increased pollution sources, many algae have been produced in the water system. Therefore, there has been a lot of research using satellite images for the generation and monitoring of green algae. However, in prior studies, it is difficult to consider the optical properties of the local water system by using only a single index, and by using medium and low-resolution satellite images to conduct large-scale algae detection, there is a problem of accuracy in narrow, broad rivers. Therefore, in this work, we utilize high-resolution images of Sentinel-2 satellites to perform green algae detection on a single index (NDVI, SEI, FGAI) and development index (NDVI & SEI, FGAI & SEI) that mixes single indices. In this study, POD, FAR, and PC values were utilized to evaluate the accuracy of green algae detection algorithms, and the FGAI & SEI index showed the highest accuracy with 98.29% overall accuracy PC.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.25 no.5
• /
• pp.1131-1141
• /
• 2015

In this paper, we proposed a new approach of machine learning based method for detecting game-bots from normal players in MMORPG by inspecting the player's action log data especially in-game money increasing/decreasing event log data. DBSCAN (Density Based Spatial Clustering of Applications with Noise), an one of density based clustering algorithms, is used to extract the attributes of spatial characteristics of each players such as a number of clusters, a ratio of core points, member points and noise points. Most of all, even game-bot developers know principles of this detection system, they cannot avoid the system because moving a wide area to hunt the monster is very inefficient and unproductive. As the result, game-bots show definite differences from normal players in spatial characteristics such as very low ratio, less than 5%, of noise points while normal player's ratio of noise points is high. In experiments on real action log data of MMORPG, our game-bot detection system shows a good performance with high game-bot detection accuracy.

• Environmental Engineering Research
• /
• v.11 no.2
• /
• pp.99-105
• /
• 2006

A digital ultrasonic image construction system was developed for the nondestructive detection of cracks in water distribution pipes. The system consists of PC based ultrasonic testing system and a scanning device. The PC based ultrasonic system has an ultrasonic pulse/receive board for the generation and reception of ultrasonic signals, an analogue to digital conversion board for the digitization of the received ultrasonic signals, and transducers for the ultrasonic sensors. Using this system, the digitized ultrasonic signals were properly constructed in accordance with the position information obtained by scanning device that moves an ultrasonic transducer along the outer surface of pipes. In the construction of the ultrasonic signals, signal processing concepts, such as spatial average and array concept, were considered to enhance the resolution of ultrasonic images of pipe wall. Using the developed system, crack detection experiments were performed in both laboratory and field, which shows promise for crack detection in the water distribution system.

• ETRI Journal
• /
• v.40 no.5
• /
• pp.570-581
• /
• 2018

This work analyzes the performance of implementable detectors for the multiple-input multiple-output (MIMO) orthogonal frequency division multiplexing (OFDM) technique under specific and realistic operation system conditions, including antenna correlation and array configuration. A time-domain channel model was used to evaluate the system performance under realistic communication channel and system scenarios, including different channel correlation, modulation order, and antenna array configurations. Several MIMO-OFDM detectors were analyzed for the purpose of achieving high performance combined with high capacity systems and manageable computational complexity. Numerical Monte Carlo simulations demonstrate the channel selectivity effect, while the impact of the number of antennas, adoption of linear against heuristic-based detection schemes, and the spatial correlation effect under linear and planar antenna arrays are analyzed in the MIMO-OFDM context.

• ETRI Journal
• /
• v.46 no.2
• /
• pp.184-193
• /
• 2024

This paper presents the performance evaluation of an amplify-and-forward (AF) relay-assisted multiuser multiple input-multiple output (MU-MIMO) downlink transmission system for correlated fading channels. The overall system performance was improved by incorporating a double-quadrature spatial modulation (DQSM) scheme. The bit error rate (BER) performance and detection complexity of the AF-MU-MIMO-DQSM system were analyzed and compared with those of a conventional AF-MU-MIMO system under the same conditions and parameters. The results showed that the correlated fading channel severely affected the performance of systems with higher spectral efficiency (SE). Considering an SE of 12 bpcu/user, the AF-MU-MIMO-DQSM system yielded a gain of up to 3 dB in BER performance compared with that of its conventional counterpart for the analyzed cases. In terms of detection complexity, the AF-MU-MIMO-DQSM system showed a reduction of up to 56 % compared with that of the conventional system for the optimal maximum likelihood detection criterion.

• Korean Journal of Remote Sensing
• /
• v.39 no.5_3
• /
• pp.909-919
• /
• 2023

Benthic marine invertebrates, the invertebrates living on the bottom of the ocean, are an essential component of the marine ecosystem, but excessive reproduction of invertebrate grazers or pirate creatures can cause damage to the coastal fishery ecosystem. In this study, we compared and evaluated You Only Look Once Version 7 (YOLOv7), the most widely used deep learning model for real-time object detection, and detection tansformer (DETR), a transformer-based model, using underwater images for benthic marine invertebratesin the coasts of South Korea. YOLOv7 showed a mean average precision at 0.5 (mAP@0.5) of 0.899, and DETR showed an mAP@0.5 of 0.862, which implies that YOLOv7 is more appropriate for object detection of various sizes. This is because YOLOv7 generates the bounding boxes at multiple scales that can help detect small objects. Both models had a processing speed of more than 30 frames persecond (FPS),so it is expected that real-time object detection from the images provided by divers and underwater drones will be possible. The proposed method can be used to prevent and restore damage to coastal fisheries ecosystems, such as rescuing invertebrate grazers and creating sea forests to prevent ocean desertification.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.20 no.10
• /
• pp.2001-2006
• /
• 2016

The stereo radiation detection system detects the gamma source and acquires two dimensional left and right images for gamma source and visible objects using the detection result. And then the system measures the distance to the radiation source from the system in 3D space using stereo vision algorithm. In this paper, we implemented the fast detection algorithm for gamma source from the system in 3D space to reduce the detection time with image processing algorithms. Additionally, the system's performance is verified through experiments on gamma irradiation facilities. As a result, if the fast detection algorithm applied to the system, we can confirm that the detection system represents a 35% better performance than the conventional detection method that is full scanning to acquire the stereo image. We also have visualized a gamma source distribution through a 3D monitor using the stereo vision algorithm in order to provide the information of radiation spatial distribution to the user efficiently.

• The Journal of Korea Robotics Society
• /
• v.13 no.1
• /
• pp.45-54
• /
• 2018

This paper presents a vision-based fall detection system to automatically monitor and detect people's fall accidents, particularly those of elderly people or patients. For video analysis, the system should be able to extract both spatial and temporal features so that the model captures appearance and motion information simultaneously. Our approach is based on 3-dimensional convolutional neural networks, which can learn spatiotemporal features. In addition, we adopts a thermal camera in order to handle several issues regarding usability, day and night surveillance and privacy concerns. We design a pan-tilt camera with two actuators to extend the range of view. Performance is evaluated on our thermal dataset: TCL Fall Detection Dataset. The proposed model achieves 90.2% average clip accuracy which is better than other approaches.

• Nuclear Engineering and Technology
• /
• v.55 no.4
• /
• pp.1528-1539
• /
• 2023

Since the leakage of sodium in an SFR (sodium-cooled fast reactor) causes an explosion upon reaction with air and water, sodium leakages represent an important safety issue. In this study, a novel technique for improving the reliability of sodium leakage detection applying DDVR (dynamic data validation and reconciliation) is proposed and verified to resolve this technical issue. DDVR is an approach that aims to improve the accuracy of a target system in a dynamic state by minimizing random errors, such as from the uncertainty of instruments and the surrounding environment, and by eliminating gross errors, such as instrument failure, miscalibration, or aging, using the spatial redundancy of measurements in a physical model and the reliability information of the instruments. DDVR also makes it possible to estimate the state of unmeasured points. To validate this approach for supporting sodium leakage detection, this study applies experimental data from a sodium leakage detection experiment performed by the Korea Atomic Energy Research Institute. The validation results show that the reliability of sodium leakage detection is improved by cooperation between DDVR and hardware measurements. Based on these findings, technology integrating software and hardware approaches is suggested to improve the reliability of sodium leakage detection by presenting the expected true state of the system.

• 한국공간정보시스템학회:학술대회논문집
• /
• 2005.05a
• /
• pp.3-8
• /
• 2005

위성영상을 이용한 산불탐지기법은 단순한 화재의 유무뿐만 아니라 온도, 면적, 상태 등과 같은 다양한 정보를 얻을 수 있는 수준으로 개발되었다. 하지만 실제 적용결과에 있어서는 서로 다른 탐지결과를 보이기 때문에 어떤 탐지기법을 선택하고 기법에 사용되는 임계값들을 어떻게 결정해야 하는가라는 문제점이 발생한다. 본 연구에서는 의사결정기법을 이용하여 개별 탐지기법의 결과를 분석하여 최적해를 얻고자 하였다. 이를 위하여 국내에서 발생한 산불에 주요 탐지기법을 적용, 정확도를 평가한 후 의사결정기법을 적용하여 보다 정확한 결과를 얻는 연구를 수행하였다. 그 결과 단일 탐지기법에서 발생하는 오류(false alarm)을 일정부분 보완할 수 있었다. 하지만 충분한 실측자료가 부족하여 정확한 평가 및 검증에는 한계가 있었다.