• Journal of the Korean Institute of Telematics and Electronics S
• /
• v.35S no.5
• /
• 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
• /
• v.54 no.4
• /
• 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.

• Journal of IKEEE
• /
• v.13 no.2
• /
• pp.140-149
• /
• 2009

Traffic anomaly detection is one of important technology that should be considered in network security and administration. In this paper, we propose an abnormal traffic detection mechanism that includes traffic monitoring and traffic analysis. We develop analytical passive monitoring system called WISE-Mon which can inspect traffic behavior. We establish a criterion by analyzing the characteristics of a traffic training set. To detect abnormal traffic, we derive a hyperplane by using Fisher linear discriminant and chi-square distribution as well as the analyzed characteristics of traffic. Our mechanism can support reliable results for traffic anomaly detection and is compatible to real-time detection. In addition, since the trend of traffic can be changed as time passes, the hyperplane has to be updated periodically to reflect the changes. Accordingly, we consider the self-learning algorithm which reflects the trend of the traffic and so enables to increase the pliability of detection probability. Numerical results are presented to validate the accuracy of proposed mechanism. It shows that the proposed mechanism is reliable and relevant for traffic anomaly detection.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.25 no.4
• /
• pp.476-481
• /
• 2019

Early detection of fire is an important measure for minimizing the loss of life and property damage. However, fire and smoke need to be simultaneously detected. In this context, numerous studies have been conducted on image-based fire detection. Conventional fire detection methods are compute-intensive and comprise several algorithms for extracting the flame and smoke characteristics. Hence, deep learning algorithms and convolution neural networks can be alternatively employed for fire detection. In this study, recorded image data of fire in a ship engine room were analyzed. The flame and smoke characteristics were extracted from the outer box, and the YOLO (You Only Look Once) convolutional neural network algorithm was subsequently employed for learning and testing. Experimental results were evaluated with respect to three attributes, namely detection rate, error rate, and accuracy. The respective values of detection rate, error rate, and accuracy are found to be 0.994, 0.011, and 0.998 for the flame, 0.978, 0.021, and 0.978 for the smoke, and the calculation time is found to be 0.009 s.

• Korean Journal of Remote Sensing
• /
• v.35 no.1
• /
• 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).

• Journal of the Korea Society of Computer and Information
• /
• v.28 no.2
• /
• pp.9-17
• /
• 2023

In this paper, we propose a one-class vibration anomaly detection system for bearing defect diagnosis. In order to reduce the economic and time loss caused by bearing failure, an accurate defect diagnosis system is essential, and deep learning-based defect diagnosis systems are widely studied to solve the problem. However, it is difficult to obtain abnormal data in the actual data collection environment for deep learning learning, which causes data bias. Therefore, a one-class classification method using only normal data is used. As a general method, the characteristics of vibration data are extracted by learning the compression and restoration process through AutoEncoder. Anomaly detection is performed by learning a one-class classifier with the extracted features. However, this method cannot efficiently extract the characteristics of the vibration data because it does not consider the frequency characteristics of the vibration data. To solve this problem, we propose an AutoEncoder model that considers the frequency characteristics of vibration data. As for classification performance, accuracy 0.910, precision 1.0, recall 0.820, and f1-score 0.901 were obtained. The network design considering the vibration characteristics confirmed better performance than existing methods.

• IEIE Transactions on Smart Processing and Computing
• /
• v.6 no.2
• /
• 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.

• Proceedings of the Korean Society of Machine Tool Engineers Conference
• /
• 2004.04a
• /
• 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.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2003.06a
• /
• 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.

• Proceedings of the KIEE Conference
• /
• 2007.07a
• /
• 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.