• 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.149-152
• /
• 2005

A new methodology to detect forest fire burnt scars at near real time using MODIS (Moderate-resolution Imaging Spectroradiometer) data is presented here with a goal of introducing a new and improved capability to detect forest fire burnt scars in Thailand. This new technology is expected to increase the efficiency and effectiveness of the forest fire tackling resources distribution and management of the country. Using MODIS data in burnt scars detection has two major advantages - high availability of data and high resolution per performance ratio. Results prove the near real time algorithm suitable and working well in order to monitor the forest fire dynamic movement. The algorithm is based on the threshold separated linear equation of burnt and un-burnt. A ground truth experiment confirms the burnt and un-burnt? areas characteristics (temperature and NDVI). A threshold line on a scatter plot of Band I and Band 2 is determined to separate the burnt from un-burnt pixels. The different threshold values of NDVI and temperature use to identify pixels' anomaly, abnormal low NDVI and high temperature. The overlay (superimpose) method is used to verify burnt pixels. Since forest fire is a dynamic phenomenon, MODIS burnt scars information is suiting well to fill in the missing temporal information of LANDSAT for the forest fire control managing strategy in Thailand. This study was conducted in the Huai-Kha-Kaeng (HKK) Wildlife Sanctuary, Thailand

• 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 Biomedical Engineering Research
• /
• v.28 no.1
• /
• pp.84-94
• /
• 2007

In order to collect information on local distribution of conductivity and permittivity underneath a scan probe, we developed a multi-frequency trans-admittance scanner (TAS). Applying a sinusoidal voltage with variable frequency on a chosen distal part of a human body, we measure exit currents from 320 grounded electrodes placed on a chosen surface of the subject. The electrodes are packaged inside a small and light scan probe. The system includes one voltage source and 17 digital ammeters. Front-end of each ammeter is a current-to-voltage converter with virtual grounding of a chosen electrode. The rest of the ammeter is a voltmeter performing digital phase-sensitive demodulation. Using resistor loads, we calibrate the system including the scan probe to compensate frequency-dependent variability of current measurements and also inter-channel variability among multiple. We found that SNR of each ammeter is about 85dB and the minimal measurable current is 5nA. Using saline phantoms with objects made from TX-151, we verified the performance of the lesion estimation algorithm. The error rate of the depth estimation was about 19.7%. For the size estimate, the error rate was about 15.3%. The results suggest improvement in lesion estimation algorithm based on multi-frequency trans-admittance data.

• The Journal of the Korea Contents Association
• /
• v.7 no.3
• /
• pp.93-100
• /
• 2007

Internet had spread in all fields with the fast speed during the last 10 years. Lately, wireless network is also spreading rapidly. Also, number of times that succeed attack attempt and invasion for wireless network is increasing rapidly TMS system was developed to overcome these threat on wireless network. Existing TMS system supplies active confrontation mechanism on these threats. However, existent TMS has limitation that new form of attack do not filtered efficiently. Therefor this paper proposes a new method that it automatically compute the threat from the imput packets with vector space model and detect anomaly detection of wireless network. Proposed mechanism in this research analyzes similarity degree between packets, and detect something wrong symptom of wireless network and then classify these threats automatically.

• Korean Journal of Soil Science and Fertilizer
• /
• v.49 no.5
• /
• pp.469-479
• /
• 2016

Kimchi cabbage is one of the most important vegetables in Korea and a target crop for market stabilization as well. In particular Kimchi cabbages in a highland area are very sensitive to the fluctuations in supply and demand. Yield variability due to growth conditions dictates the market fluctuations of Kimchi cabbage price. This study was carried out to understand the distribution of the highland Kimchi cabbage growth status in Anbandeok. Anbandeok area in Gangneung, Gangwon-do, Korea is one of the main producing districts of highland Kimchi cabbage. The highland Kimchi cabbage status map of each growth factor was obtained from unmanned aerial vehicle (UAV) imagery and field survey data. Six status maps include UAVRGB image map, normalized difference vegetation index (NDVI) distribution/anomaly map, Crop distribution map, Planting/Harvest distribution map, Growth parameter map and Growth disorder map. As a result, the highland Kimchi cabbage status maps from May 31 to Sep. 6 in 2016 were presented to show spatial variability in the field. The benefits of the highland Kimchi cabbage status map can be summarized as follows: crop growth monitoring, reference for field observations and survey, the relative comparison of the growth condition in field scale, evaluation of growth in comparison of average year, change detection of annual crops or planting areas, abandoned fields monitoring, prediction of harvest season etc.

• Journal of the Korean Institute of Gas
• /
• v.24 no.6
• /
• pp.91-97
• /
• 2020

Lithium-ion batteries (LIBs) have a longer lifespan, higher energy density, and lower self-discharge rates than other batteries, therefore, they are preferred as an Energy Storage System (ESS). However, during years 2017-2019, 28 ESS fire accidents occurred in Korea, and accurate capacity estimation of LIB is essential to ensure safety and reliability during operations. In this study, data-driven modeling that predicts capacity changes according to the charging cycle of LIB was conducted, and developed models were compared their performance for the selection of the optimal machine learning model, which includes the Decision Tree, Ensemble Learning Method, Support Vector Regression, and Gaussian Process Regression (GPR). For model training, lithium battery test data provided by NASA was used, and GPR showed the best prediction performance. Based on this study, we will develop an enhanced LIB capacity prediction and remaining useful life estimation model through additional data training, and improve the performance of anomaly detection and monitoring during operations, enabling safe and stable ESS operations.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.25 no.12
• /
• pp.1739-1748
• /
• 2021

Real estate prices affect countries, businesses, and households, and many studies have been conducted on the real estate bubble in recent soaring real estate prices. However, if the real estate bubble prediction simply compares the real estate price, or if it does not reflect key psychological variables in real estate sales, it can be judged that the accuracy of the bubble prediction model is poor. The purpose of this study is to design a predictive model that can explain the real estate bubble situation by region using the autoencoder technique. Existing real estate bubble analysis studies failed to set various types of variables that affect prices, and most of them were conducted based on linear models. Thus, this study suggests the possibility of introducing techniques and variables that have not been used in existing real estate bubble studies.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.05a
• /
• pp.240-243
• /
• 2021

Recently, there have been research results of applying Big data and AI technologies to the evaluation and individual learning for education. It is information technology innovations that collect dynamic and complex data, including student personal records, physiological data, learning logs and activities, learning outcomes and outcomes from social media, MOOCs, intelligent tutoring systems, LMSs, sensors, and mobile devices. In addition, e-learning was generated a large amount of learning data in the COVID-19 environment. It is expected that learning analysis and AI technology will be applied to extract meaningful patterns and discover knowledge from this data. On the learner's perspective, it is necessary to identify student learning and emotional behavior patterns and profiles, improve evaluation and evaluation methods, predict individual student learning outcomes or dropout, and research on adaptive systems for personalized support. This study aims to contribute to research in the field of education by researching and classifying machine learning technologies used in anomaly detection and recommendation systems for educational data.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2023.01a
• /
• pp.39-42
• /
• 2023

최근 온라인 게임 산업이 급속도로 확장됨과 더불어 Gamebot과 같은 비정상적인 프로그램으로 인한 게임 서비스 피해사례가 급격하게 증가하고 있다. 특히, 대표적인 게임 장르 중 하나인 FPS(First-Person Shooter)에서 Aimbot의 사용은 정상적인 이용자들에게 재미 요소를 잃어버리게 하고 상대적 박탈감을 일으켜 게임의 수명을 줄이는 원인이 된다. 비정상 게임 이용자의 근절을 위해서 메모리 변조 및 불법 변조 프로그램 접근 차단 기법과 불법 프로그램 사용의 패턴 모니터링과 같은 기법들이 제안되었지만, 우회 프로그램 및 새로운 패턴을 이용한 비정상적인 프로그램의 개발에는 취약하다는 단점이 있다. 따라서, 본 논문에서는 정상적인 게임 이용자의 패턴만 학습함으로써 비정상 이용자 검출을 가능하게 하는 딥러닝 기반 단일 클래스 분류 기법을 제안하며, 가장 빈번하게 발생하는 치트(Cheat) 유형인 FPS 게임 내 Aimbot 사용 감지에 초점을 두었다. 제안된 비정상 게임 이용자 감지 시스템은 정상적인 사용자의 마우스 좌표를 데카르트 좌표계(Cartesian coordinates)와 극좌표계(Polar coordinates)의 형태로 패턴을 추출하는 과정과 정상적인 마우스 동작 기록으로 부터 학습된 LSTM 기반 Autoencoder의 복원 에러에 따른 검출 과정으로 구성된다. 실험에서 제안된 모델은 FPS 게임 내 마우스 동작을 기록한 공개 데이터셋인 CSGO 게임 데이터셋으로 부터 학습되었으며, 학습된 모델의 테스트 결과는 데카르트 좌표계로부터 훈련된 제안 모델이 비정상 게임 이용자를 분류하는데 적합함을 입증하였다.