• Atmosphere
• /
• v.29 no.3
• /
• pp.257-267
• /
• 2019

This study is to assess the applicability of the Extreme Forecast Index (EFI) algorithm of the ECMWF seasonal forecast system to the Global Seasonal Forecasting System version 5 (GloSea5), operational seasonal forecast system of the Korea Meteorological Administration (KMA). The EFI is based on the difference between Cumulative Distribution Function (CDF) curves of the model's climate data and the current ensemble forecast distribution, which is essential to diagnose the predictability in the extreme cases. To investigate its applicability, the experiment was conducted during the heat-wave cases (the year of 1994 and 2003) and compared GloSea5 hindcast data based EFI with anomaly data of ERA-Interim. The data also used to determine quantitative estimates of Probability Of Detection (POD), False Alarm Ratio (FAR), and spatial pattern correlation. The results showed that the area of ERA-Interim indicating above 4-degree temperature corresponded to the area of EFI 0.8 and above. POD showed high ratio (0.7 and 0.9, respectively), when ERA-Interim anomaly data were the highest (on Jul. 11, 1994 (> $5^{\circ}C$) and Aug. 8, 2003 (> $7^{\circ}C$), respectively). The spatial pattern showed a high correlation in the range of 0.5~0.9. However, the correlation decreased as the lead time increased. Furthermore, the case of Korea heat wave in 2018 was conducted using GloSea5 forecast data to validate EFI showed successful prediction for two to three weeks lead time. As a result, the EFI forecasts can be used to predict the probability that an extreme weather event of interest might occur. Overall, we expected these results to be available for extreme weather forecasting.

• The Sea:JOURNAL OF THE KOREAN SOCIETY OF OCEANOGRAPHY
• /
• v.26 no.4
• /
• pp.307-326
• /
• 2021

Real-time sea level observations from tide gauges include missing and erroneous values. Classification as abnormal values can be done for the latter by the quality control procedure. Although the 3𝜎 (three standard deviations) rule has been applied in general to eliminate them, it is difficult to apply it to the sea-level data where extreme values can exist due to weather events, etc., or where erroneous values can exist even within the 3𝜎 range. An artificial intelligence model set designed in this study consists of non-annotated recurrent neural networks and ensemble techniques that do not require pre-labeling of the abnormal values. The developed model can identify an erroneous value less than 20 minutes of tide gauge recording an abnormal sea level. The validated model well separates normal and abnormal values during normal times and weather events. It was also confirmed that abnormal values can be detected even in the period of years when the sea level data have not been used for training. The artificial neural network algorithm utilized in this study is not limited to the coastal sea level, and hence it can be extended to the detection model of erroneous values in various oceanic and atmospheric data.

• Proceedings of the KSRS Conference
• /
• 2005.10a
• /
• pp.237-240
• /
• 2005

Calibration and Validation are major element of any space borne Earth Observation Mission. These activities are the major objective of the commissioning phases but routine activities shall be maintained during the whole mission in order to maintain the quality of the product delivered to the users or at least to fully characterise the evolution with time of the product quality. With the launch of ERS-l in 1991, the European Space Agency decided to put in place a group dedicated to these activities, along with the daily monitoring of the product quality for anomaly detection and algorithm evolution. These four elements are all strongly linked together. Today this group is fully responsible for the monitoring of two ESA missions, ERS-2 and Envisat, for a total of 12 instruments of various types, preparing itself for the Earth Explorer series of five. other satellites (Cryosat, Goce, SMOS, ADM-Aeolus, Swarm) and at various levels in past and future Third Party Missions such as Landsat, J-ERS, ALOS and KOMPSAT. The Joint proposal by the European Union and the European Space Agency for a 'Global Monitoring for Environment and Security' project (GMES), triggers a review of the scope of these activities in a much wider framework than the handling of single missions with specific tools, methods and activities. Because of the global objective of this proposal, it is necessary to put in place Multi-Mission Calibration and Validation systems and procedures. GMES Calibration and Validation activities will rely on multi source data access, interoperability, long-term data preservation, and definition standards to facilitate the above objectives. The scope of this presentation is to give an overview of the current Calibration and Validation activities at ESA, and the planned evolution in the context of GMES.

• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• 2015.07a
• /
• pp.310-311
• /
• 2015

Ships' tracking data are being monitored and collected by vessel traffic service center in real time. In this paper, we intend to contribute to vessel traffic service operators' decision making through extracting ships' tracking patterns and models based on these data. Support Vector Machine algorithm was used for vessel track modeling to handle and process the data sets and k-fold cross validation was used to select the proper parameters. Proposed data processing methods could support vessel traffic service operators' decision making on case of anomaly detection, calculation ships' dead reckoning positions and etc.

• Journal of Internet Computing and Services
• /
• v.22 no.3
• /
• pp.17-26
• /
• 2021

Recently, COVID-19 has spread and time to stay at home has been increasing in accordance with quarantine guidelines of the government such as recommendations to refrain from going out. As a result, the number of single-person households staying at home is also increasingsingle-person households are less likely to be notified to the outside world in times of emergency than multi-person households. This study collects various situations occurring in the home with lidar, image, and voice sensors and analyzes the data according to the sensors through their respective algorithms. Using this method, we analyzed abnormal patterns such as emergency situations and conducted research to detect abnormal signs in humans. Artificial intelligence algorithms that detect abnormalities in people by each sensor were studied and the accuracy of anomaly detection was measured according to the sensor. Furthermore, this work proposes a fusion method that complements the pros and cons between sensors by experimenting with the detectability of sensors for various situations.

• Journal of the Korean Society of Industry Convergence
• /
• v.26 no.1
• /
• pp.113-119
• /
• 2023

In this paper, we propose an optimization of a pose estimation deep learning model for recognition of abnormal behavior in unmanned stores using radio frequencies. The radio frequency use millimeter wave in the 30 GHz to 300 GHz band. Due to the short wavelength and strong straightness, it is a frequency with less grayness and less interference due to radio absorption on the object. A millimeter wave radar is used to solve the problem of personal information infringement that may occur in conventional CCTV image-based pose estimation. Deep learning-based pose estimation models generally use convolution neural networks. The convolution neural network is a combination of convolution layers and pooling layers of different types, and there are many cases of convolution filter size, number, and convolution operations, and more cases of combining components. Therefore, it is difficult to find the structure and components of the optimal posture estimation model for input data. Compared with conventional millimeter wave-based posture estimation studies, it is possible to explore the structure and components of the optimal posture estimation model for input data using genetic algorithms, and the performance of optimizing the proposed posture estimation model is excellent. Data are collected for actual unmanned stores, and point cloud data and three-dimensional keypoint information of Kinect Azure are collected using millimeter wave radar for collapse and property damage occurring in unmanned stores. As a result of the experiment, it was confirmed that the error was moored compared to the conventional posture estimation model.

• Atmosphere
• /
• v.33 no.1
• /
• pp.49-59
• /
• 2023

Blocking refers to a class of weather phenomena appearing in the mid and high latitudes, whose characteristics are blocked airflow of persistence. Frequently found over the Pacific and Atlantic regions of the Northern Hemisphere, blocking affects severe weather in the surrounding areas with different mechanisms depending on the type of blocking patterns. Along with lots of studies about persistent weather extremes focusing on the specific types of blocking, a new categorization using Rossby wave breaking has emerged. This study aims to apply this concept to the classification of blockings over the Pacific and examine how different wave breakings specify the associated cold weather in the Korean peninsula. At the same time, we investigate a strongly developing ridge around the Pacific by designing a new detection algorithm, where a reversal method is modified to distinguish ridge-type blocking patterns. As result, Kamchatka blocking (KB) and strong ridge over the Central Pacific are observed the most frequently during 20 years (2001~2020) of the studied period, and anomalous low pressures with cold air over the Korean Peninsula are accompanied by blocking events. When it considers the Rossby wave breaking, cyclonic wave-breaking is dominant in KB, which generates low-pressure anomalies over the Korean Peninsula. However, KB with anticyclone wave breaking appears with the high-pressure anomalies over the Korean Peninsula and it generates the warm temperature anomaly. Lastly, the low-pressure anomalies are also generated by the strong ridge over the Central Pacific, which persists for approximately three days and give a significant impact on cold surge on the Korean Peninsula.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2011.11a
• /
• pp.941-944
• /
• 2011

모바일 클라우드 서비스는 사용자가 모바일 단말에 자원을 가지고 있지 않더라도 인터넷을 통해 외부의 다양한 IT 자원을 제공하는 서비스로서 모바일 단말이 가지는 성능적 한계를 극복시킬 수 있다는 장점과 함께 이용자 수가 증가하고 있다. 그러나 클라우드 컴퓨팅 환경에 존재하는 개인 및 기업의 정보 유출과 같은 문제들은 모바일 클라우드 컴퓨팅 환경에도 그대로 상속되기 때문에 이러한 문제에 대응하기 위해서는 모바일 클라우드 컴퓨팅 환경에서 정보유출을 탐지할 수 있는 이상행위 탐지 알고리즘이 마련되어야 한다. 여기서 이상행위란, 모바일 클라우드 자원에 접근하는 방법에 있어 기존에 인지하고 있던 정상적인 행위에서 벗어나는 행위를 의미하며 이상행위로 판단되는 상황이 발생되는 경우, 이를 정보유출이 발생할 수 있는 상황으로 인지함으로써 적절한 대응을 할 수 있게 된다. 따라서 본 논문에서는 모바일 클라우드 자원의 정보유출을 방지하기 위한 목적으로 자원 접근에 대한 이상행위 탐지 알고리즘 개발 모델을 제시한다. 이상행위 탐지 알고리즘을 개발하고 이를 검증하기 위해서는 이상행위를 일으키는 공격 모델 및 대응 모델이 개발되어야 한다. 따라서 본 논문에서는 인증 및 권한관리의 취약점을 이용하여 위협을 일으키는 공격 모델을 개발하는 방법을 제시하고, 사용자의 접속환경 및 클라우드 자원의 정보 흐름을 분석함으로써 이상행위를 탐지하는 알고리즘을 제시한다.

• Journal of Advanced Navigation Technology
• /
• v.22 no.2
• /
• pp.49-56
• /
• 2018

As the energy generated by earthquake, tsunami, etc. propagates through the air and disturbs the electron density in the ionosphere, the perturbation can be detected by analyzing the ionospheric delay in satellite signal. The electron density in the ionosphere is affected by various factors such as solar activity, latitude, season, and local time. To distinguish from the anomaly, therefore, it is required to inspect the normal trend of the ionosphere. Also, as the perturbation magnitude diminishes by distance it is necessary to develop an appropriate algorithm to detect long-distance disturbances. In this paper, normal condition ionosphere trend is analyzed via IONEX data. We selected monitoring value that has no tendency and developed an algorithm to effectively detect the long-distance ionospheric disturbances by using the lasting characteristics of the disturbances. In the end, we concluded the $2^{nd}$ derivative of ionospheric delay would be proper monitoring value, and the false alarm with the developed algorithm turned out to be 1.4e-6 level. It was applied to 2011 Tohoku earthquake case and the ionospheric disturbance was successfully detected.

• Journal of Convergence for Information Technology
• /
• v.11 no.11
• /
• pp.57-65
• /
• 2021

We propose a novel method to detect abnormal data of specific symptoms using deep learning in air pollution measurement system. Existing methods generally detect abnomal data by classifying data showing unusual patterns different from the existing time series data. However, these approaches have limitations in detecting specific symptoms. In this paper, we use DeepLab V3+ model mainly used for foreground segmentation of images, whose structure has been changed to handle one-dimensional data. Instead of images, the model receives time-series data from multiple sensors and can detect data showing specific symptoms. In addition, we improve model's performance by reducing the complexity of noisy form time series data by using 'piecewise aggregation approximation'. Through the experimental results, it can be confirmed that anomaly data detection can be performed successfully.