• Proceedings of the Korean Society of Computer Information Conference
• /
• 2021.07a
• /
• pp.645-647
• /
• 2021

본 논문에서는 목조건물의 Crack만을 움직여 Data set을 증강하는 기법을 제안한다. 이 기법은 이미지 내 Crack Detection의 학습 데이터를 만들기 위해 이미지의 전체적인 값으로 Flip, Rotation, Shift, Rescale 등의 변환을 통해 Data Augmentation을 진행하는 대신 Crack이라는 하나의 Object만을 가지고 새로운 데이터를 생성한다. 이때 Object는 관심 영역 내에서만 연산되어 기존의 방법보다 더욱 많은 데이터를 얻을 수 있으며, Crack이 관심 영역 밖으로 이동하지 않기 때문에 이상치 혹은 결측치가 존재하지 않는 데이터를 얻을 수 있다. 또한 Crack이 존재하지 않는 이미지에도 임의적으로 Crack을 생성하여 새로운 데이터를 만들 수 있다. 결론적으로 본 논문에서는 Crack Detection의 학습을 위하여 기존 방법보다 우수한 성능의 Data Augmentation을 제안하였다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2014.04a
• /
• pp.721-723
• /
• 2014

본 논문은 선박내부의 센서데이터 이상감지를 위해 실시간 신뢰구간을 설정하고 신뢰구간을 초과하거나 미만이 되면 경보를 통해 관리자에게 알려주는 모니터링을 위한 신뢰구간 추정이다. 여기서, 이상 감지 예측의 정확도 향상을 위해 단순지수평활법과 이동평균법의 평균제곱오차를 비교 평가 하였다. 실험결과, 이동평균법의 평균제곱오차가 단순지수평활법 보다 적게 나와 선박 내부 모니터링을 위한 신뢰구간은 이동평균법을 적용하였다.

• Journal of IKEEE
• /
• v.24 no.2
• /
• pp.403-408
• /
• 2020

Photovoltaic (PV) has both intermittent and uncertainty in nature, so it is difficult to accurately predict. Thus anomaly detection technology is important to diagnose real time PV generation. This paper identifies a correlation between various parameters and classifies the PV data applying k-nearest neighbor and dynamic time warpping. Results for the two classifications showed that an outlier detection by a fault of some facilities, and a temporary power loss by partial shading and overall shading occurring during the short period. Based on 100kW plant data, machine learning analysis and test results verified actual outliers and candidates of outlier.

• Journal of the Korea Convergence Society
• /
• v.12 no.2
• /
• pp.1-6
• /
• 2021

In the modern society, traffic problems are occurring as vehicle ownership increases. In particular, the incidence of highway traffic accidents is low, but the fatality rate is high. Therefore, a technology for detecting an abnormality in a vehicle is being studied. Among them, there is a vehicle anomaly detection technology using deep learning. This detects vehicle abnormalities such as a stopped vehicle due to an accident or engine failure. However, if an abnormality occurs on the road, it is possible to quickly respond to the driver's location. In this study, we propose a deep learning-based vehicle anomaly detection using road CCTV data. The proposed method preprocesses the road CCTV data. The pre-processing uses the background extraction algorithm MOG2 to separate the background and the foreground. The foreground refers to a vehicle with displacement, and a vehicle with an abnormality on the road is judged as a background because there is no displacement. The image that the background is extracted detects an object using YOLOv4. It is determined that the vehicle is abnormal.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.34 no.9A
• /
• pp.719-726
• /
• 2009

CR systems performs spectrum sensing operation to detect the appearance of primary users. However, since it is not feasible to do spectrum sensing and data transmission simultaneously, they typically operate alternatively in a time domain. There have been an effort(8) to investigate the optimal spectrum sensing duration for maximum throughput for the scheme with cooperative spectrum sensing. This is based on an assumption that the communication channels between each secondary user and the fusion center are ideal and does not consider the effects of transmission error. Motivated by this, we here model the channels as binary symmetric channels and examined its effect on the maximum throughput and the associated optimal sensing duration. Analysis shows that the performance degradation due to the transmission error is smaller for the case of using the AND fusion rule than for the OR fusion rule.

• Journal of the Korea Society of Computer and Information
• /
• v.29 no.3
• /
• pp.127-136
• /
• 2024

This study explores the correlation between system anomalies and large-scale logs within the Spark cluster environment. While research on anomaly detection using logs is growing, there remains a limitation in adequately leveraging logs from various components of the cluster and considering the relationship between anomalies and the system. Therefore, this paper analyzes the distribution of normal and abnormal logs and explores the potential for anomaly detection based on the occurrence of log templates. By employing Hadoop and Spark, normal and abnormal log data are generated, and through t-SNE and K-means clustering, templates of abnormal logs in anomalous situations are identified to comprehend anomalies. Ultimately, unique log templates occurring only during abnormal situations are identified, thereby presenting the potential for anomaly detection.

• Journal of Internet Computing and Services
• /
• v.23 no.5
• /
• pp.135-143
• /
• 2022

As the world has implemented social distancing and telecommuting due to the spread of COVID-19, real-time streaming sessions based on routing protocols have increased dependence on the Internet due to the activation of video and voice-related content services and cloud computing. BGP is the most widely used routing protocol, and although many studies continue to improve security, there is a lack of visual analysis to determine the real-time nature of analysis and the mis-detection of algorithms. In this paper, we analyze BGP data, which are powdered as normal and abnormal, on a real-world basis, using an anomaly detection algorithm that combines statistical and post-processing statistical techniques with Rule-based techniques. In addition, we present an interactive spatio-temporal analysis plan as an intuitive visualization plan and analysis result of the algorithm with a map and Sankey Chart-based visualization technique.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.2 no.4
• /
• pp.53-58
• /
• 2009

In recently years, the research and application for sensor has increased in each field. In this paper, the system which can perceive and detect using 3-axis accelerometer sensor and serial communication is proposed. Also, the user has GUI environment for monitor in real-time. In order to reduce unstable data and error defect of electronic rechargeable liquid tilt sensor used digital 3-axis accelerometer sensor which has AD convertor. Therefore, this system provide exact data and a problem of objects for user more easier.

• The Journal of Society for e-Business Studies
• /
• v.23 no.2
• /
• pp.111-121
• /
• 2018

Many problems in rotating machinery such as aircraft engines, wind turbines and motors are caused by bearing defects. The abnormalities of the bearing can be detected by analyzing signal data such as vibration or noise, proper pre-processing through a few signal processing techniques is required to analyze their frequencies. In this paper, we introduce the condition monitoring method for diagnosing the failure of the rotating machines by analyzing the vibration signal of the bearing. From the collected signal data, the normal states are trained, and then normal or abnormal state data are classified based on the trained normal state. For preprocessing, a Hamming window is applied to eliminate leakage generated in this process, and the cepstrum analysis is performed to obtain the original signal of the signal data, called the formant. From the vibration data of the IMS bearing dataset, we have extracted 6 statistic indicators using the cepstral coefficients and showed that the application of the Mahalanobis distance classifier can monitor the bearing status and detect the failure in advance.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2015.04a
• /
• pp.81-83
• /
• 2015

최근 주변 사물과 IT기술을 접목하여 사람들의 불필요한 시간을 줄여주는 제품들이 각광받고 있고 이러한 제품들을 구현하기 위한 다양한 임베디드 디바이스 또한 많은 개발과 발전을 하였다. 본 프로젝트는 아두이노와 스마트 디바이스의 통신을 통해 아이의 위기와 이상을 감지하여 물리적 먼 거리에서도 보호자가 위기 상황을 감지할 수 있도록 통보하는 디바이스를 개발하였다. 아두이노와 사운드 센서를 기본 디바이스로 아이의 울음을 감지하고, wifi 쉴드를 통해 데이터를 저장하며 스마트 디바이스는 이를 감지하여 부모에게 필요한 정보를 전달하여 보호가 필요한 아이의 위급 상황에 빠른 대처가 가능하게 하였다.