• Proceedings of the KIEE Conference
• /
• 2007.04a
• /
• pp.73-76
• /
• 2007

Photodynamic diagnosis(PDD) is a method to diagnose the possibility of cancer, both by the principle that if a photosensitizer is injected into an organic tissue, it is accumulated in the tissue of a malignant tumor selectively after a specific period, and by a comparison of the intensity of the fluorescence of normal tissue with abnormal tissue after investigating the excitation light of a tissue with accumulated photosensitizer. Since the selection of the wavelength band of excitation light has an interrelation with fluorescence generation according to the selection of a photosencitizer, it plays an important role in POD. This study aims at designing and evaluating light source devices that can stably generate light with various kinds of wavelengths In order to make possible PDD using a photosensitizer and diagnosis using auto-fluorescence. The light source device was a Xenon lamp and filter wheel, composed of an optical output control through Iris and filters with several wavelength bands It also makes the inducement of auto-fluorescence possible because it is designed to generate a wavelength band of 380-400. The transmission part of the light source was, developed to enhance the efficiency of light transmission. To evaluate this light source device, the characteristics of the light output and wavelength band were verified. To validate the capability of this device as PDD the detection of auto-fluorescence using mouse was performed.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2022.11a
• /
• pp.905-907
• /
• 2022

악성코드를 분석하는 기존 기법인 정적분석은 빠르고 효율적으로 악성코드를 탐지할 수 있지만 난독화된 파일에 취약한 반면,, 동적분석은 난독화된 파일에 적합하지만 느리고 비용이 많이 든다는 단점을 가진다. 본 연구에서는 두 분석 기법의 단점을 해결하기 위해 딥러닝 모델을 활용한 난독화에 강한 정적분석 모델을 제안하였다. 본 연구에서 제안한 방법은 원본 코드 및 난독화된 파일을 grayscale 이미지로 변환하여 데이터셋을 구축하고 AutoEncoder 를 사전학습시켜 encoder 가 원본 파일과 난독화된 파일로부터 원본 파일의 특징을 추출할 수 있도록 한 이후, encoder 의 output 을 fully connected layer 의 입력으로 넣고 전이학습시켜 악성코드를 탐지하도록 하였다. 본 연구에서는 제안한 방법론은 난독화된 파일에서 악성코드를 탐지하는 성능을 F1 score 기준 14.17% 포인트 향상시켰고, 난독화된 파일과 원본 파일을 전체를 합친 데이터셋에서도 악성코드 탐지 성능을 F1 score 기준 7.22% 포인트 향상시켰다.

• Journal of Digital Convergence
• /
• v.14 no.11
• /
• pp.249-255
• /
• 2016

Since the elderly voices include a lot of noise caused by physiological changes in respiration, phonation, and resonance, the performance of the convergence health-care equipments such as speech recognition, synthesis, analysis program done by elderly voice is deteriorated. Therefore it is necessary to develop researches to operate health-care instruments with elderly voices. In this study, a voice activity detection using a symmetric higher-order differential energy function (SHODEO) was developed and was compared with auto-correlation function(ACF) and the average magnitude difference function(AMDF). It was confirmed to have a better performance than other methods in the voice interval detection. The voice activity detection will be applied to a voice interface for the elderly to improve the accessibility of the smart devices.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.26 no.6
• /
• pp.1513-1526
• /
• 2016

Since finance companies started e-banking services, those services have been diversified and use of them has continued to increase. Finance companies are implementing financial security policy for safe e-banking services, but e-Banking incidents are continuing to increase and becoming more intelligent. Along with the rise of internet banks and boosting Fintech industry, financial supervisory institutes are not only promoting user convenience through improving e-banking regulations such as enforcing Non-face-to-face real name verification policy and abrogating mandatory use of public key certificate or OTP(One time Password) for e-banking transactions, but also recommending the prevention of illegal money transfer incidents through upgrading FDS(Fraud Detection System). In this study, we assessed a blacklist based auto detection method suitable for overall situations for finance company, a real-time based suspicious transaction detection method linking with blacklist statistics model by each security level, and an alternative FDS model responding to typical transaction patterns of which information were collected from previous e-Banking incidents.

• Journal of radiological science and technology
• /
• v.36 no.2
• /
• pp.141-148
• /
• 2013

The CT examination sometimes fail to localize the cerebral hemorrhage part depending on the seriousness and may embarrass the pathologist if he/she is not trained enough for emergencies. Therefore, an assisting role is necessary for examination, automatic and quick detection of the cerebral hemorrhage part, and supply of the quantitative information in emergencies. the computer based automatic detection and recognition system may be of a great service to the bleeding part detection. As a result of this research, we succeeded not only in automatic detection of the cerebral hemorrhage part by grafting threshold value handling, morphological operation, and roundness calculation onto the bleeding part but also in development of the PCA based classifier to screen any wrong choice in the detection candidate group. We think if we apply the new developed system to the cerebral hemorrhage patient in his critical condition, it will be very valuable data to the medical team for operation planning.

• The Journal of the Acoustical Society of Korea
• /
• v.42 no.6
• /
• pp.500-510
• /
• 2023

Passive sonar signals mainly contain both normal and abnormal signals. The abnormal signals mixed with normal signals are primarily detected using an AutoEncoder (AE) that learns only normal signals. However, existing AEs may perform inaccurate detection by reconstructing distorted normal signals from mixed signal. To address these limitations, we propose an abnormal signal detection model based on a Recurrent Neural Network (RNN) and vector quantization. The proposed model generates a codebook representing the learned latent vectors and detects abnormal signals more accurately through the proposed search process of code vectors. In experiments using publicly available underwater acoustic data, the AE and Variational AutoEncoder (VAE) using the proposed method showed at least a 2.4 % improvement in the detection performance and at least a 9.2 % improvement in the extraction performance for abnormal signals than the existing models.

• Journal of KSNVE
• /
• v.4 no.3
• /
• pp.337-343
• /
• 1994

A method of the leak detection from the pipe system by using accelerometer is proposed. The signal detected from accelerometer is proved experimentally to be a dispersive wave. Based on the experiments, a method using the narrow band pass filter and the unit impulse response function is analyzed. The method uses the characteristics of the unit impulse response function, that the function is available evenin the narrow band signal because, unlike the cross correlation, it is normalized by the auto spectrum. The accelerometer is quite easier to use than the hydrophone in adapting to the pipe system.

• Proceedings of the KIEE Conference
• /
• 1987.07b
• /
• pp.1418-1421
• /
• 1987

An important problem in edge detection is to select a proper threshold that transforms the gradient picture to e two level picture containing optimum edges between regions, Such a threshold is determined depending on some measures of errors in tresholding. In this paper, an error criterion on extracting edges by thresholding the block gradient image is presented. Based on the error measure, the optimum threshold is chosen for the detection of acceptable edges.

• Nuclear Engineering and Technology
• /
• v.42 no.2
• /
• pp.219-230
• /
• 2010

In nuclear power plants (NPPs), periodic sensor calibrations are required to assure that sensors are operating correctly. By checking the sensor's operating status at every fuel outage, faulty sensors may remain undetected for periods of up to 24 months. Moreover, typically, only a few faulty sensors are found to be calibrated. For the safe operation of NPP and the reduction of unnecessary calibration, on-line instrument calibration monitoring is needed. In this study, principal component-based auto-associative support vector regression (PCSVR) using response surface methodology (RSM) is proposed for the sensor signal validation of NPPs. This paper describes the design of a PCSVR-based sensor validation system for a power generation system. RSM is employed to determine the optimal values of SVR hyperparameters and is compared to the genetic algorithm (GA). The proposed PCSVR model is confirmed with the actual plant data of Kori Nuclear Power Plant Unit 3 and is compared with the Auto-Associative support vector regression (AASVR) and the auto-associative neural network (AANN) model. The auto-sensitivity of AASVR is improved by around six times by using a PCA, resulting in good detection of sensor drift. Compared to AANN, accuracy and cross-sensitivity are better while the auto-sensitivity is almost the same. Meanwhile, the proposed RSM for the optimization of the PCSVR algorithm performs even better in terms of accuracy, auto-sensitivity, and averaged maximum error, except in averaged RMS error, and this method is much more time efficient compared to the conventional GA method.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.27 no.7
• /
• pp.1088-1097
• /
• 2021

Vibration data of mechanical equipment inevitably have noise. This noise adversely af ects the maintenance of mechanical equipment. Accordingly, the performance of a learning model depends on how effectively the noise of the data is removed. In this study, the noise of the data was removed using the Denoising Auto Encoder (DAE) technique which does not include the characteristic extraction process in preprocessing time series data. In addition, the performance was compared with that of the Wavelet Transform, which is widely used for machine signal processing. The performance comparison was conducted by calculating the failure detection rate. For a more accurate comparison, a classification performance evaluation criterion, the F-1 Score, was calculated. Failure data were detected using the One-Class SVM technique. The performance comparison, revealed that the DAE technique performed better than the Wavelet Transform technique in terms of failure diagnosis and error rate.