• Journal of Aerospace System Engineering
• /
• v.18 no.4
• /
• pp.43-52
• /
• 2024

This paper presents an anomaly detection system that uses an LSTM-Autoencoder model to identify early-stage anomalies in the blade pitch system of floating wind turbines. The sensor data used in power plant monitoring systems is primarily composed of multivariate time-series data for each component. Comprising two unidirectional LSTM networks, the system skillfully uncovers long-term dependencies hidden within sequential time-series data. The autoencoder mechanism, learning solely from normal state data, effectively classifies abnormal states. Thus, by integrating these two networks, the system can proficiently detect anomalies. To confirm the effectiveness of the proposed framework, a real multivariate time-series dataset collected from a wind turbine model was employed. The LSTM-autoencoder model showed robust performance, achieving high classification accuracy.

• Journal of the Korea Convergence Society
• /
• v.8 no.10
• /
• pp.249-255
• /
• 2017

The domestic tourism industry mostly relies on quantitative surveys for customer satisfaction. However, customer participation of the questionnaires is extremely low and the improvement of the dissatisfactory factors is not being performed promptly. In this paper, we propose a new topic map system and prove its empirical effectiveness to improve the accuracy of customer feedback information and the efficiency of the analysis process. The topic map system is a system for analyzing large amounts of customer feedback data in real time. It uses text mining and ontology techniques by integrating data collected over a certain period from real-time SNS and quantitative data obtained from existing survey systems. The effect after improving the analyzed factors of dissatisfaction is also a new and innovative evaluation system for monitoring customer satisfaction in real time. The classification based on this integrated data is a classification system that is specific to the product or the customer. According to this classification, it is possible to measure the effect of the recognition and improvement of the complaint factor in real time on the topic map system. This provides a sophisticated prioritization of the improvement factors and enables customer satisfaction quality control as a PDCA feedback system. In addition, the survey period and costs are greatly shortened, and responses can be more precise to the existing survey method. As a practical application, this system is applied to the largest H travel agency in Korea to prove the accuracy and efficiency of the proposed system.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.25 no.3
• /
• pp.279-286
• /
• 2015

The rapid increase of the current marine accidents is mainly due to the human execution errors. In an effort to address this, various kinds of researches such as construction of the digital vessels and vessel information monitoring systems have been conducted. But for safe navigation of vessels, it lack on systems study which can efficiently store, utilize and manage the mass data accepted by the vessel. In this paper, we propose a VWS(Virtual World System) that is based on the architecture of intelligent systems RVC(Reactive Layer-Virtual World-Considerative Layer) model of intelligent autonomous navigation system. VWS is responsible to store all the necessary information for safe navigation of the vessel and the information services to the sub-system of intelligent autonomous navigation system. VWS uses topology database to express the specific problem area, and utilizes a scheduling to reflect the characteristics of the real-time processing environment. Also, Virtual World defines API for the system to reflect the characteristics of the distributed processing environment. As a case study, the VWS is applied to a intelligent ship autonomous navigation system, and simulation is done to prove the effectiveness of the proposed system.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.8 no.5
• /
• pp.159-166
• /
• 2008

Recently, according to the rapid development of location positioning technology and wireless communications technology and increasement of usage of moving object data, many researches and developments on the real-time locating systems which provides real time service of moving object data stream are under proceeding. However, MO (Moving Object) DBMS used based system in the in these systems is the inefficient management of moving object data streams, and the existing DSMS (Data Stream Management System) has problems that spatio-temporal data are not handled efficiently. Therefore, in this thesis, we designed and implemented spatio-temporal DSMS for efficient real-time management of moving object data stream. This thesis implemented spatio-temporal DSMS based STREAM (STanford stREam dAta Manager) of Stanford University is supporting real-time management of moving object data stream and spatio-temproal query processing and filtering for reduce the input loading. Specifically, spatio-temporal operators of the spatio-temporal DSMS support standard interface of SQL form which extended "Simple Feature Specification for SQL" standard specifications presented by OGC for compatibility. Finally, implemented spatio-temporal DSMS in this thesis, proved the effectiveness of the system that as applied real-time monitoring areas that require real-time locating of object data stream DSMS.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.17 no.5
• /
• pp.1-9
• /
• 2016

Railroad bridges account for 25% of the entire high-speed rail network. Railway bridges are subject to gradual structural degradation or fatigue accumulation due to consistent and repeating excitation by fast moving trains. Wireless sensing technology has opened up a new avenue for bridge health monitoring owing to its low-cost, high fidelity, and multiple sensing capability. On the other hand, measuring the transient response during train passage is quite challenging that the current wireless sensor system cannot be applied due to the intrinsic time delay of the sensor network. Therefore, this paper presents a framework for monitoring such transient responses with wireless sensing systems using 1) real-time excessive vibration monitoring through ultra-low-power MEMS accelerometers, and 2) post-event time synchronization scheme. The ultra-low power accelerometer continuously monitors the vibration and trigger network when excessive vibrations are detected. The entire network of wireless smart sensors starts sensing through triggering and the post-event time synchronization is conducted to compensate for the time error on the measured responses. The results of this study highlight the potential of detecting the impact load and triggering the entire network, as well as the effectiveness of the post-event time synchronized scheme for compensating for the time error. A numerical and experimental study was carried out to validate the proposed sensing hardware and time synchronization method.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.18 no.9
• /
• pp.146-156
• /
• 2017

In this study, the causal relationship between the main factors influencing the import of agricultural products and the changes in agricultural imports was investigated. In addition, we compared the magnitude of the impact of each factor on the changes in agricultural imports. It was found that the import liberalization rate, which represents the FTA factors and reflects the per capita GDP, the conditions of supply and demand of agricultural products in exporting countries and the changes in exchange rates, affects the changes of the agricultural products imports. However, the factors affecting the change of the imports by agricultural product category and the magnitude of the influence by each factor were different. This shows that various factors, other than the FTA factors, are compounding the changes in the agricultural imports. In the future, the market openings due to the implementation of the FTA will be further enlarged and the economic territory of the FTA will be further expanded, due to the implementation of additional FTAs, and the changes in the imports of agricultural products will cause damage to the domestic agricultural sector.

• Korean Journal of Organic Agriculture
• /
• v.29 no.4
• /
• pp.539-559
• /
• 2021

Agricultural ecosystem biodiversity monitoring and community variation analysis of insects were conducted from 2016 to 2018 in selected conventional and organic farming fields in Goesan district, Chungcheongbuk-do, South Korea. The total number of 1,125 species in 16 orders and 207 families were identified. The numbers of species collected in the locations practicing organic farming were greater than the conventional farming both in the paddy fields (564 vs. 383 species) and the upland fields (471 vs. 365 species). Among them, Hemiptera had the most abundant of species, followed by Diptera, Hymenoptera, Coleoptera and Araneae. We calculated various index values of biodiversity (diversity index H', richness index R, evenness index J', dominance index D, and similarity index QS) based on quantitative measurements of species and individuals collected over three years of field monitoring. Variations in biodiversity index values in different agricultural systems show that the positive effect of organic farming is to produce more biodiversity than conventional farming systems. When compared to other index results reported in Korea, Japan and China, the richness index was higher and other index values were at similar levels.

• Korean Journal of Agricultural and Forest Meteorology
• /
• v.25 no.3
• /
• pp.182-196
• /
• 2023

Accurate and timely estimation of crop yields is crucial for various purposes, including global food security planning and agricultural policy development. Remote sensing techniques, particularly using vegetation indices (VIs), have show n promise in monitoring and predicting crop conditions. However, traditional VIs such as the normalized difference vegetation index (NDVI) and enhanced vegetation index (EVI) have limitations in capturing rapid changes in vegetation photosynthesis and may not accurately represent crop productivity. An alternative vegetation index, the near-infrared reflectance of vegetation (NIRv), has been proposed as a better predictor of crop yield due to its strong correlation with gross primary productivity (GPP) and its ability to untangle confounding effects in canopies. In this study, we investigated the potential of NIRv in estimating crop yield, specifically for corn and soybean crops in major crop-producing regions in 14 states of the United States. Our results demonstrated a significant correlation between the peak value of NIRv and crop yield/area for both corn and soybean. The correlation w as slightly stronger for soybean than for corn. Moreover, most of the target states exhibited a notable relationship between NIRv peak and yield, with consistent slopes across different states. Furthermore, we observed a distinct pattern in the yearly data, where most values were closely clustered together. However, the year 2012 stood out as an outlier in several states, suggesting unique crop conditions during that period. Based on the established relationships between NIRv peak and yield, we predicted crop yield data for 2022 and evaluated the accuracy of the predictions using the Root Mean Square Percentage Error (RMSPE). Our findings indicate the potential of NIRv peak in estimating crop yield at the county level, with varying accuracy across different counties.

• Korean Journal of Remote Sensing
• /
• v.39 no.5_3
• /
• pp.979-995
• /
• 2023

As wildfires are difficult to predict, real-time monitoring is crucial for a timely response. Geostationary satellite images are very useful for active fire detection because they can monitor a vast area with high temporal resolution (e.g., 2 min). Existing satellite-based active fire detection algorithms detect thermal outliers using threshold values based on the statistical analysis of brightness temperature. However, the difficulty in establishing suitable thresholds for such threshold-based methods hinders their ability to detect fires with low intensity and achieve generalized performance. In light of these challenges, machine learning has emerged as a potential-solution. Until now, relatively simple techniques such as random forest, Vanilla convolutional neural network (CNN), and U-net have been applied for active fire detection. Therefore, this study proposed an active fire detection algorithm using state-of-the-art (SOTA) deep learning techniques using data from the Advanced Himawari Imager and evaluated it over East Asia and Australia. The SOTA model was developed by applying EfficientNet and lion optimizer, and the results were compared with the model using the Vanilla CNN structure. EfficientNet outperformed CNN with F1-scores of 0.88 and 0.83 in East Asia and Australia, respectively. The performance was better after using weighted loss, equal sampling, and image augmentation techniques to fix data imbalance issues compared to before the techniques were used, resulting in F1-scores of 0.92 in East Asia and 0.84 in Australia. It is anticipated that timely responses facilitated by the SOTA deep learning-based approach for active fire detection will effectively mitigate the damage caused by wildfires.

• Journal of the Korean Recycled Construction Resources Institute
• /
• v.1 no.3
• /
• pp.211-218
• /
• 2013

Cyclic wet and dry conditions in the marine environment structures corrosion is known to be the fastest rising. For that reason, accelerated corrosion test methods for the reproduction of tidal environment has been actively conducted. However, many studies have estimated threshold value for steel corrosion or concentrated in chloride penetration analysis. In this study, cyclic wet and dry conditions to reproduce the structure of the environment in accelerated corrosion and chloride penetration test analysis was performed. Corrosion was determined by the result of reinforcement corrosion monitoring based on galvanic potential measurement and half-cell potential method. Accelerated corrosion test results for each formulation was different corrosion periods, the order OPC> FA> BS> High-strength concrete. FEM durability interpretation program DuCOM was conducted under the same conditions as in accelerated corrosion test. The experimental RCPT tests demonstrated the validity of the result.