• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.44 no.4
• /
• pp.169-176
• /
• 2021

Maritime monitoring requirements have been beyond human operators capabilities due to the broadness of the coverage area and the variety of monitoring activities, e.g. illegal migration, or security threats by foreign warships. Abnormal vessel movement can be defined as an unreasonable movement deviation from the usual trajectory, speed, or other traffic parameters. Detection of the abnormal vessel movement requires the operators not only to pay short-term attention but also to have long-term trajectory trace ability. Recent advances in deep learning have shown the potential of deep learning techniques to discover hidden and more complex relations that often lie in low dimensional latent spaces. In this paper, we propose a deep autoencoder-based clustering model for automatic detection of vessel movement anomaly to assist monitoring operators to take actions on the vessel for more investigation. We first generate gridded trajectory images by mapping the raw vessel trajectories into two dimensional matrix. Based on the gridded image input, we test the proposed model along with the other deep autoencoder-based models for the abnormal trajectory data generated through rotation and speed variation from normal trajectories. We show that the proposed model improves detection accuracy for the generated abnormal trajectories compared to the other models.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2023.05a
• /
• pp.175-175
• /
• 2023

Detection and monitoring of wildfires are essential for limiting their harmful effects on ecosystems, human lives, and property. In this research, we propose a novel method running in the Google Earth Engine platform for identifying and characterizing burnt regions using a hybrid of Sentinel-1 (C-band synthetic aperture radar) and Sentinel-2 (multispectral photography) images. The 2022 Uljin wildfire, the severest event in South Korean history, is the primary area of our investigation. Given its documented success in remote sensing and land cover categorization applications, we select the Random Forest (RF) method as our primary classifier. Next, we evaluate the performance of our model using multiple accuracy measures, including overall accuracy (OA), Kappa coefficient, and area under the curve (AUC). The proposed method shows the accuracy and resilience of wildfire identification compared to traditional methods that depend on survey data. These results have significant implications for the development of efficient and dependable wildfire monitoring systems and add to our knowledge of how machine learning and remote sensing-based approaches may be combined to improve environmental monitoring and management applications.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.19 no.1
• /
• pp.233-240
• /
• 2024

In this study, we introduce a system for real-time monitoring of field conditions within an industrial complex using a 5G network UAV (: Unmanned Aerial Vehicle). When a monitoring event occurs in a sensor mounted on a UAV (detection of fire, harmful gas, or industrial disaster type human accident), key information from the sensor is transmitted to the UAS (: Unmanned Aerial System) application server. As a result of this information transmission and processing, managers or operators of the Industrial Complex Corporation were able to secure legal basis data for fatal accidents, fires, and detection of harmful gases at sites within the Industrial Complex Corporation through trigger processing for each accident risk situation.

• Proceedings of the Korea Committee for Ocean Resources and Engineering Conference
• /
• 2004.05a
• /
• pp.111-116
• /
• 2004

We surveyed the coastal structure damages due to the typhoon 'Mae-mi' which heavily struck Korean peninsula in September 12, 2003. The survey revealed the typhoon induced high tides and strong winds were the main causes especially in Busan areas. Though some experimental real time coastal monitoring stations captured the typhoon movements at the critical time, more systematic and complete systems should be implemented to save human lives and properties from huge typhoon disasters.

• CDE review
• /
• v.11 no.2
• /
• pp.15-22
• /
• 2005

Presented in the paper is an approach to developing an intelligent mold shop as a means to overcome the difficulties faced by mold-makers due to skill shortages and increased global competition. A machine shop where as much as of the human skills are replaced by a set of intelligent systems is called an intelligent machine shop, and an intelligent mold-making machine shop is called an intelligent mold shop(MS). By analyzing the contents of operator's skill. three intelligent S/W stations have been designed: Technical Data Processing(TDP) Station, Loading Schedule Station, and Real-time Monitoring Station. A detailed architecture of the TDP station is described, and measures of effectiveness of IMS are elaborated.

• 제어로봇시스템학회:학술대회논문집
• /
• 2003.10a
• /
• pp.803-807
• /
• 2003

Tele-operation and remote monitoring techniques are essential and important technologies for performing the inspection and repair tasks effectively in nuclear power plants. This paper presents the application of a mobile robot for the remote monitoring and inspection of the Calandria faces, where human access is limited because of the high-level radioactive environments during full power operation. The mobile robot was designed with reconfigurable crawler type of wheels attached on the front and rear side in order to pass through the ditch. The extendable mast, mounted on the mobile robot, can be extended up to 8 m vertically. This robot was also equipped a visible CCD/thermal infrared inspection head module and a stereo camera module for the enhancement of visual inspection.

• Proceedings of the Korean Radioactive Waste Society Conference
• /
• 2004.06a
• /
• pp.430-432
• /
• 2004

Tele-operation and remote monitoring techniques are essential and important technologies for the inspection and maintenance of the radioactive waste. A mobile robot has been developed for the application of remote monitoring and inspection of nuclear facilities, where human access is limited because of the high-level radioactive environments, The mobile robot was designed with reconfigurable crawler type of wheels attached on the front and rear side in order to pass through the ditch, The extendable mast, mounted on the mobile robot, car be extended up to 8 m vertically. The robust controller for radiation is designed in focus on electric components to prevent abnormal operation in a highly radioactivated area during reactor operation, This robot system will enhance the reliability of nuclear power facilities, and cope with the unexpected radiation accident.

• Korean Journal of Child Studies
• /
• v.25 no.2
• /
• pp.133-154
• /
• 2004

This study examined the relations between maternal parenting, mother-adolescent conflict, and adolescent individuation with a sample of 271 high school students (156 boys and 115 girls) living in Seoul. Data were analyzed by correlations and regressions. Maternal monitoring, reasoning and affection were positively related to connectedness and separateness, two subscales of adolescent individuation, and maternal over-expectation, intrusiveness, physical abuse and neglect were negatively related to connectedness and separateness. Mother-adolescent conflict was negatively related to connectedness and separateness. Maternal monitoring, reasoning and affection were negatively related to mother-adolescent conflict, and maternal over-expectation, intrusiveness, and physical abuse and neglect were positively related to mother-adolescent conflict. Mother-adolescent conflict played a mediating role between maternal parenting and adolescent individuation.

• Bioinformatics and Biosystems
• /
• v.1 no.1
• /
• pp.17-27
• /
• 2006

Recent progress in the development of non-invasive imaging technologies continues to strengthen the role of molecular imaging biological research. These tools have been validated recently in variety of research models, and have been shown to provide continuous quantitative monitoring of the location(s), magnitude, and time-variation of gene delivery and/or expression. This article reviews the use of radionuclide, magnetic resonance, and optical imaging technologies as they have been used in imaging gene delivery and gene expression for molecular imaging applications. The studies published to date demonstrate that noninvasive imaging tools will help to accelerate pre-clinical model validation as well as allow for clinical monitoring of human diseases.

• Proceedings of the PSK Conference
• /
• 2003.04a
• /
• pp.288.3-289
• /
• 2003

Sphingolipid species are important second messengers due to their role in the mitogenesis, differentiation and apoptosis. We developed a new column liquid chromatography-triple quadrupole tandem mass spectrometry (LC-MS/MS) in combination with multiple reaction monitoring (MRM) method for the rapid, simultaneous and quantitative determination of unambiguous detecting sphingolipids in cell culture of human cancer cells (HL-60). (omitted)