• Electronics and Telecommunications Trends
• /
• v.36 no.5
• /
• pp.82-91
• /
• 2021

This study reviews application of data-driven anomaly detection techniques to the aviation domain. Recent advances in deep learning have inspired significant anomaly detection research, and numerous methods have been proposed. However, some of these advances have not yet been explored in aviation systems. After briefly introducing aviation safety issues, data-driven anomaly detection models are introduced. Along with traditional statistical and well-established machine learning models, the state-of-the-art deep learning models for anomaly detection are reviewed. In particular, the pros and cons of hybrid techniques that incorporate an existing model and a deep model are reviewed. The characteristics and applications of deep learning models are described, and the possibility of applying deep learning methods in the aviation field is discussed.

• Journal of the Chungcheong Mathematical Society
• /
• v.36 no.4
• /
• pp.231-244
• /
• 2023

We study the modularity and holomorphic anomaly equation for Hodge-Gromov-Witten invariants of elliptic curves.

• Journal of Korean Ophthalmic Optics Society
• /
• v.5 no.1
• /
• pp.147-154
• /
• 2000

To describe the prevalence of binocular anomalies in adult Koreans. Patients included were 19 to 40 years of age, 41 males and 60 females and living in Kwang-Ju Korea. Refractive correction was estimated objectively with an autorefractometer and subjectively refined without cycloplegia. Myopia was defined as a refractive error less than -0.50 diopters hyperopia was defined as a refractive error greater than +0.50 diopters. 101 no strabismic patients who had a refractive error and a near lateral phoria(46%) and an AC/A(accommodative convergence/accommodation) anomaly(50.4%). The prevalence of a near vergence anomaly(52.5%) was higher than a near divergence anomaly(55.5%). The prevalence of a positive relative accommodation(PRA) anomaly(61.4%) was higher than a negative relative accommodation(NRA) anomaly(54.5%). According to Morgan's analysis method, patients with vergence anomaly(21.7%) were seen slightly less frequently than those with accommodative interaction anomaly(29.7%). 34.6% of patients had both vergence anomaly and accommodative interaction anomaly. These results indicate that full prescription for a refractive corrections should be considered as these can improve binocular visual function for ametropia.

• Journal of Digital Contents Society
• /
• v.19 no.2
• /
• pp.377-383
• /
• 2018

Internet of Things (IoT) is producing various data as the smart environment comes. The IoT data collection is used as important data to judge systems's status. Therefore, it is important to monitor the anomaly state of the sensor in real-time and to detect anomaly data. However, it is necessary to convert the IoT data into a normalized data structure for anomaly detection because of the variety of data structures and protocols. Thus, we can expect a good quality effect such as accurate analysis data quality and service quality. In this paper, we propose an anomaly detection system based on big data from collected sensor data. The proposed system is applied to ensure anomaly detection and keep data quality. In addition, we applied the machine learning model of support vector machine using anomaly detection based on time-series data. As a result, machine learning using preprocessed data was able to accurately detect and predict anomaly.

• Journal of Navigation and Port Research
• /
• v.35 no.9
• /
• pp.701-706
• /
• 2011

Radio waves including GPS signals, various TV communications, and radio broadcasting can be disturbed by a strong solar storm, which may occur due to solar flares and produce an ionospheric delay anomaly in the ionosphere according to the change of total electron content. Electron density irregularities can cause deep signal fading, frequently known as ionospheric scintillation, which can result in the positioning error using GPS signal. This paper proposes a detection algorithm for the ionosphere delay anomaly during a solar storm by using multi-reference stations. Different TEC grid which has irregular electron density was applied above one reference station. Then the ionospheric delay in zenith direction applied different TEC will show comparatively large ionospheric zenith delay due to the electron irregularity. The ionospheric slant delay applied an elevation angle at reference station was analyzed to detect the ionospheric delay anomaly that can result in positioning error. A simulation test was implemented and a proposed detection algorithm using data logged by four reference stations was applied to detect the ionospheric delay anomaly compared to a criterion.

• Journal of Navigation and Port Research
• /
• v.34 no.7
• /
• pp.511-516
• /
• 2010

GPS anomaly has increased according to the degradation of satellite performance, and many GPS users could be exposed to any kinds of error-included signals without any previous notice when unscheduled error occurred. RSIM (Reference Station Integrity Monitors) is a typical monitoring method to broadcast PRC (Pseudo Range Correction) for users. However, there were some cases that the receiver detected the anomalous satellite's signal even though it was unhealthy set, consequently it occurred a large range error. Then it is important to monitor the integrity of GPS signal and it is needed to devise the correction method of pseudorange by eliminating error-occurred PRN for notification to GPS users when it is monitored that the anomaly occurred. This paper proposes the basic concept of how to correct the pseudorange. The paper also shows the analysis results of PRN10 GPS anomaly occurred on day 39 in 2007 with corrected results by eliminating anomaly satellite (PRN10). The proposed correction method shows decreased pseudorange error range compared to the case when the anomaly satellite were used.

• Journal of the Korea Society of Computer and Information
• /
• v.8 no.1
• /
• pp.103-113
• /
• 2003

Program Behavior Intrusion Detection Technique analyses system calls that called by daemon program or root authority, constructs profiles. and detectes anomaly intrusions effectively. Anomaly detections using system calls are detected only anomaly processes. But this has a Problem that doesn't detect affected various Part by anomaly processes. To improve this problem, the relation among system calls of processes is represented by bayesian probability values. Application behavior profiling by Bayesian Network supports anomaly intrusion informations . This paper overcomes the Problems of various intrusion detection models we Propose effective intrusion detection technique using Bayesian Networks. we have profiled concisely normal behaviors using behavior context. And this method be able to detect new intrusions or modificated intrusions we had simulation by proposed normal behavior profiling technique using UNM data.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.15 no.1
• /
• pp.69-75
• /
• 2022

Due to the increase in the demand for anomaly detection according to the ageing of power generation facilities, the need for developing an anomaly detection method that can provide high-reliability turbine blade anomaly detection performance has been continuously raised. Additionally, the false detection results caused by a human error accelerates the increase of the need. In this paper, we propose an anomaly detection technique for turbine blades in power plants using deep neural networks. Experimental results prove that the proposed technique achieves stable anomaly detection performance while minimizing human factor intervention.

• Smart Structures and Systems
• /
• v.28 no.6
• /
• pp.811-825
• /
• 2021

High-voltage isolating switches play a paramount role in ensuring the safety of power supply systems. However, their exposure to outdoor environmental conditions may cause serious physical defects, which may result in great risk to power supply systems and society. Image processing-based methods have been used for anomaly detection. However, their accuracy is affected by numerous uncertainties due to manually extracted features, which makes the anomaly detection of isolating switches still challenging. In this paper, a vision-based anomaly detection method for isolating switches, which uses the rotational angle of the switch system for more accurate and direct anomaly detection with the help of deep learning (DL) and image processing methods (Single Shot Multibox Detector (SSD), improved frame differencing method, and Hough transform), is proposed. The SSD is a deep learning method for object classification and localization. In addition, an improved frame differencing method is introduced for better feature extraction and a hough transform method is adopted for rotational angle calculation. A number of experiments are conducted for anomaly detection of single and multiple switches using video frames. The results of the experiments demonstrate that the SSD outperforms the You-Only-Look-Once network. The effectiveness and robustness of the proposed method have been proven under various conditions, such as different illumination and camera locations using 96 videos from the experiments.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.10a
• /
• pp.19-21
• /
• 2022

Anomaly detection using self-supervised learning typically generates synthetic data to learn to classify normal and abnormal, and uses real abnormal data as test data to measure anomaly detection performance. In a study using this method to generate synthetic data similar to normal data, anomaly detection was carried out by generating synthetic data by cutting and pasting a specific patch from the original image. In this way, the degree of similarity to normal data depends on the number and size of patches, which affects anomaly detection performance. In this paper, synthetic data were generated by varying patch sizes and numbers, and then similarity and analysis with normal data were conducted using a pre-trained model, and anomaly detection performance was measured by learning the model.