• 전자공학회논문지S
• /
• 제35S권5호
• /
• pp.48-58
• /
• 1998

In this paper, we proposed a new algorithm using characteristics of th ereconstructed phase trajectory by topological mapping developed for a real-tiem detection of the QRS complexes of ECG signals. Using fill-factor algorithm and mutual information algorithm which are in genral used to find out the chaotic characteristics of sampled signals, we inferred the proper mapping parameter, time delay, in ECG signals and investigated QRS detection rates with varying time delay in QRS complex detection. And we compared experimental time dealy with the theoretical one. As a result, it shows that the experimental time dealy which is proper in topological mapping from ECG signals is 20ms and theoretical time delays of fill-factor algorithm and mutual information algorithm are 20.+-.0.76ms and 28.+-.3.51ms, respectively. From these results, we could easily infer that the fill-factor algorithm in topological mapping from one-dimensional sampled ECG signals to two-dimensional vectors, is a useful algorithm for the detemination of the proper ECG signals to two-dimensional vectors, is a useful algorithm for the detemination of the proper time delay. Also with the proposed algorithm which is very simple and robust to low-frequency noise as like baseline wandering, we could detect QRS complex in real-time by simplifying preprocessing stages. For the evaluation, we implemented the proposed algorithm in C-language and applied the MIT/BIH arrhythmia database of 48 patients. The proposed algorithm provides a good performance, a 99.58% detection rate.

• Asia-Pacific Journal of Atmospheric Sciences
• /
• 제54권4호
• /
• pp.527-544
• /
• 2018

This paper presents a nighttime sea fog detection algorithm incorporating unsupervised learning technique. The algorithm is based on data sets that combine brightness temperatures from the $3.7{\mu}m$ and $10.8{\mu}m$ channels of the meteorological imager (MI) onboard the Communication, Ocean and Meteorological Satellite (COMS), with sea surface temperature from the Operational Sea Surface Temperature and Sea Ice Analysis (OSTIA). Previous algorithms generally employed threshold values including the brightness temperature difference between the near infrared and infrared. The threshold values were previously determined from climatological analysis or model simulation. Although this method using predetermined thresholds is very simple and effective in detecting low cloud, it has difficulty in distinguishing fog from stratus because they share similar characteristics of particle size and altitude. In order to improve this, the unsupervised learning approach, which allows a more effective interpretation from the insufficient information, has been utilized. The unsupervised learning method employed in this paper is the expectation-maximization (EM) algorithm that is widely used in incomplete data problems. It identifies distinguishing features of the data by organizing and optimizing the data. This allows for the application of optimal threshold values for fog detection by considering the characteristics of a specific domain. The algorithm has been evaluated using the Cloud-Aerosol Lidar with Orthogonal Polarization (CALIOP) vertical profile products, which showed promising results within a local domain with probability of detection (POD) of 0.753 and critical success index (CSI) of 0.477, respectively.

• 전기전자학회논문지
• /
• 제13권2호
• /
• pp.140-149
• /
• 2009

최근 인터넷을 통한 각종 침해사고 및 트래픽 폭주와 같은 현상이 급격하게 증가함에 따라 네트워크의 비정상적 상황을 조기에 탐지하기 위한 보다 능동적이고 진보적인 기술이 요구되고 있다. 본 논문에서는 캠퍼스 네트워크와 같이 트래픽이 주기적인 특성을 띠는 환경에서 Fisher 선형 분류법(FLD)을 사용하여 트래픽을 두 개의 그룹으로 분류하고, 네트워크에 유입되는 트래픽이 어떤 그룹에 속하는지를 판별하는 기법을 제안한다. 이를 위해 WISE-Mon이라 불리는 트래픽 분석 시스템을 개발하여 캠퍼스 네트워크의 트래픽을 수집하고 이를 모니터링해서 분석을 수행한다. 생성된 트래픽의 training set을 이용하여 비정상 트래픽의 범위를 판단하기 위한 chi-square distribution을 유도하고, FLD를 적용하여 유입되는 트래픽을 두 그룹으로 분리하기 위한 초평면 (hyperplane)을 만든다. 또한 네트워크 내의 트래픽 패턴이 시간이 지남에 따라 계속적으로 변하는 상황을 반영하기 위하여 self-learning 알고리즘을 적용한다. 캠퍼스 네트워크의 트래픽을 적용한 수학적 결과를 통하여 제안하는 기법의 정확성과 신뢰도를 보여준다.

• 해양환경안전학회지
• /
• 제25권4호
• /
• pp.476-481
• /
• 2019

화재의 초기 검출은 인명과 재화의 손실을 최소화하기 위한 중요한 요소이다. 불꽃과 연기를 신속하면서 동시에 검출해야 하며 이를 위해 영상 기반의 화재 검출에 관한 연구가 다양하게 진행되고 있다. 기존의 화재 검출은 불꽃과 연기의 특징을 추출하기 위해 여러 알고리즘을 거쳐서 화재의 검출 유무를 판단하므로 연산량이 많이 소모되었으나, 딥러닝 알고리즘인 합성곱 신경망을 이용하면 별도의 과정이 생략되므로 신속하게 검출할 수 있다. 본 논문에서는 선박 기관실에서 화재 영상을 녹화한 데이터로 실험을 수행하였다. 불꽃과 연기의 특징을 외각 상자로 추출한 후 합성곱 신경망 중 하나인 욜로(YOLO)를 이용하여 학습하고 결과를 테스트하였다. 실험 결과를 검출률, 오검출률, 정확도로 평가하였으며 불꽃은 0.994, 0.011, 0.998, 연기는 0.978, 0.021, 0.978을 나타내었고, 연산시간은 0.009s를 소모됨을 확인하였다.

• 대한원격탐사학회지
• /
• 제35권1호
• /
• pp.117-136
• /
• 2019

In this study, a hybrid-type of day fog detection algorithm (DFDA) was developed based on the optical and textural characteristics of fog top, using the Himawari-8 /Advanced Himawari Imager data. Supplementary data, such as temperatures of numerical weather prediction model and sea surface temperatures of operational sea surface temperature and sea ice analysis, were used for fog detection. And 10 minutes data from visibility meter from the Korea Meteorological Administration were used for a quantitative verification of the fog detection results. Normalized albedo of fog top was utilized to distinguish between fog and other objects such as clouds, land, and oceans. The normalized local standard deviation of the fog surface and temperature difference between fog top and air temperature were also assessed to separate the fog from low cloud. Initial threshold values (ITVs) for the fog detection elements were selected using hat-shaped threshold values through frequency distribution analysis of fog cases.And the ITVs were optimized through the iteration method in terms of maximization of POD and minimization of FAR. The visual inspection and a quantitative verification using a visibility meter showed that the DFDA successfully detected a wide range of fog. The quantitative verification in both training and verification cases, the average POD (FAR) was 0.75 (0.41) and 0.74 (0.46), respectively. However, sophistication of the threshold values of the detection elements, as well as utilization of other channel data are necessary as the fog detection levels vary for different fog cases(POD: 0.65-0.87, FAR: 0.30-0.53).

• 한국컴퓨터정보학회논문지
• /
• 제28권2호
• /
• pp.9-17
• /
• 2023

본 논문에서는 베어링의 결함 진단을 위한 단일 클래스 분류의 진동 이상 탐지 시스템을 제안한다. 베어링 고장으로 인해 발생하는 경제적 및 시간적 손실을 줄이기 위해 정확한 결함 진단시스템은 필수적이며 문제 해결을 위해 딥러닝 기반의 결함 진단 시스템들이 널리 연구되고 있다. 그러나 딥러닝 학습을 위한 실제 데이터 채집 환경에서 비정상 데이터 확보에 어려움이 있으며 이는 데이터 편향을 초래한다. 이에 정상 데이터만 활용하는 단일 클래스 분류 방법을 활용한다. 일반적인 방법으로는 AutoEncoder를 통한 압축과 복원 과정을 학습하여 진동 데이터의 특성을 추출한다. 추출된 특성으로 단일 클래스 분류기를 학습하여 이상 탐지를 실시한다. 하지만 이와 같은 방법은 진동 데이터의 주파수 특성을 고려하지 않아서 진동 데이터의 특성을 효율적 추출할 수 없다. 이러한 문제를 해결하기 위해 진동 데이터의 주파수 특성을 고려한 AutoEncoder 모델을 제안한다. 분류 성능은 accuracy 0.910, precision 1.0, recall 0.820, f1-score 0.901이 나왔다. 주파수 특성을 고려한 네트워크 설계로 기존 방법들보다 우수한 성능을 확인하였다.

• IEIE Transactions on Smart Processing and Computing
• /
• 제6권2호
• /
• pp.71-75
• /
• 2017

In this paper, a smart optical fingerprint sensor technology that is robust against faked fingerprints. A new lens and prism accurately detect fingerprint ridges and valleys that are needed to express a fingerprint's intrinsic characteristics well. The proposed technology includes light path configuration and an optical fingerprint sensor that can effectively identify faked fingerprint features. Results of simulation show the smart optical fingerprint sensor classifies the characteristics of faked fingerprints made from silicone, gelatin, paper, and rubber, and show that the proposed technology has superior detection performance with faked fingerprints, compared to the existing infrared discrimination method.

• 한국공작기계학회:학술대회논문집
• /
• 한국공작기계학회 2004년도 춘계학술대회 논문집
• /
• pp.191-196
• /
• 2004

This study proposed the analysis of mass position detection and modified stiffness due to the change of the mass and stiffness of structure by using the original and modified dynamic characteristics. The method is applied to examples of a cantilever and 3 degree of freedom by modifying the mass. The predicted detection of mass positions and magnitudes are in good agrement with these from the structural reanalysis using the modified mass.

• 한국정밀공학회:학술대회논문집
• /
• 한국정밀공학회 2003년도 춘계학술대회 논문집
• /
• pp.760-763
• /
• 2003

This study proposed the analysis of damage defection due to the change of the stiffness of structure by using the original and modified dynamic characteristics. The method is applied to examples of a cantilever and 3 degree of freedom by modifying the stiffness. The predicted damage detections are in good agreement with these from the structural reanalysis using the modified stiffness.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2007년도 제38회 하계학술대회
• /
• pp.1700-1701
• /
• 2007

DC Arc Fault Current is an electric discharge which is occurred in two opposite electrode. In this paper, DC arc detection device is designed for the display of DC arc fault current which is occurred in the local electric network with DC Power. This DC arc is one of the main causes of electric fire. Arc fault in electrical network has the characteristics of low current, high impedance and low frequency. DC Arc current detection device is designed for the display of arc fault current which has the modified arc characteristics.