• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.49 no.2
• /
• pp.94-101
• /
• 2012

This paper proposes an improved image steganalysis scheme to raise the detection rate of stego images out of cover images. To improve the detection rate of stego image in the steganalysis, tiny variation caused by data hiding should be amplified. For this, we extract feature vectors of cover image and stego image by two steps. First, we separate image into upper 4 bit subimage and lower 4 bit subimage. As a result, stego noise is expanded more than two times. We decompose separated subimages into twelve subbands by applying 3-level Haar wavelet transform and calculate co-occurrence probabilities of two different subbands in the same scale. Since co-occurrence probability of the two wavelet subbands is affected by data hiding, it can be used as a feature to differentiate cover images and stego images. The extracted feature vectors are used as the input to the multilayer perceptron(MLP) classifier to distinguish between cover and stego images. We test the performance of the proposed scheme over various embedding rates by the LSB, S-tool, COX's SS, and F5 embedding method. The proposed scheme outperforms the previous schemes in detection rate to existence of hidden message as well as exactness of discrimination.

• Journal of Korea Society of Industrial Information Systems
• /
• v.20 no.3
• /
• pp.61-69
• /
• 2015

This study presents a probabilistic knowledge discovery method to interpret heart rate variability (HRV) based on time and frequency domain indexes, extracted using discrete wavelet transform. The knowledge induction algorithm was composed of two phases: rule generation and rule estimation. Firstly, a rule generation converts numerical attributes to intervals using ROC curve analysis and constructs a reduced ruleset by comparing consistency degree between attribute-value pairs with different decision values. Then, we estimated three measures such as rule support, confidence, and coverage to a probabilistic interpretation for each rule. To show the effectiveness of proposed model, we evaluated the statistical discriminant power of five rules (3 for atrial fibrillation, 1 for normal sinus rhythm, and 1 for both atrial fibrillation and normal sinus rhythm) generated using a data (n=58) collected from 1 channel wireless holter electrocardiogram (ECG), i.e., HeartCall$^{(R)}$, U-Heart Inc. The experimental result showed the performance of approximately 0.93 (93%) in terms of accuracy, sensitivity, specificity, and AUC measures, respectively.

• Journal of the Korean Society of Clothing and Textiles
• /
• v.26 no.2
• /
• pp.355-363
• /
• 2002

The purpose of this study was to investigate how the weave type, yarn twist fabric count and fiber content of the worsted fabrics affect the subjective sensation of the hand. Thirty worsted fabrics that were mainly used for the spring and fall ladies'suits at national brands were selected. Variables were such as four different kinds of weave types, plain, twill, satin and decorative; two levels of yarn twist, normal and high; various fabric counts; two different fiber contents, pure wool and Lycra contained. Image analysis and wavelet transform techniques were used to quantify the surface fiber, For surface characteristics, MIU, MMD and SMD were measured by KES-FB system. The Questionnaires with 23 adjectives were used for the subjective hand evaluation. Panels were So specialists of fashion or fabric designers and merchandizers. By Factor Analysis, six factors that represent the subjective hand were extracted. The relationship between these factors and structural variables were analyzed. Yarn twist was significantly related to the surface characteristics and resilience. Weave structure affected surface characteristics, volume/warm-cool feeling and resilience. Fabric counts showed relations with volume/warm-cool feeling and the fiber contents with volume/warm-cool feeling, resilience and elastic properties. MIU, MMD and SMD showed no relations with the surface fibers. Subjective sensation of surface characteristics was affected by SMD and surface fibers.

• Journal of IKEEE
• /
• v.22 no.4
• /
• pp.1175-1179
• /
• 2018

In this paper, we propose recurrent CNN(Convolutional Neural Networks) for detecting seizures among patients using EEG signals. In the proposed method, data were mapped by image to preserve the spectral characteristics of the EEG signal and the position of the electrode. After the spectral preprocessing, we input it into CNN and extracted the spatial and temporal features without wavelet transform. Results from the Children's Hospital of Boston Massachusetts Institute of Technology (CHB-MIT) dataset showed a sensitivity of 90% and a false positive rate (FPR) of 0.85 per hour.

• Journal of the Korean Society for Nondestructive Testing
• /
• v.24 no.2
• /
• pp.142-150
• /
• 2004

A preliminary study of the behavior of ultrasonic guided wave mode in a pipe using a comb transducer for maintenance inspection of power plant facilities has been verified experimentally. The mode identification has been carried out in a pipe using the time-frequency analysis methods such as the wavelet transform(WT) and the short time Fourier transform (STFT), compared with theoretically calculated group velocity dispersion curves for longitudinal and flexural modes. The results are in good agreement with analytical predictions and show the effectiveness of using the time-frequency analysis method to identify the individual modes. It was found out that the longitudinal mode(0,1) is less affected by mode conversion compared with the other modes. Therefore, L(0,1) is selected as an optimal mode for the evaluation of the surface defect in a pipe.

• Journal of Power System Engineering
• /
• v.14 no.2
• /
• pp.40-47
• /
• 2010

This paper proposes a fault detection system to detect the strip rupture in six-high stand Cold Rolling Mills based on transient current signal of an electrical motor. For this work, signal smoothing technique is used to highlight precise feature between normal and fault condition. Subtracting the smoothed signal from the original signal gives the residuals that contains the information related to the normal or faulty condition. Using residual signal, discrete wavelet transform is performed and acquire the signal presenting fault feature well. Also, feature extraction and classification are executed by using PCA, KPCA and SVM. The actual data is acquired from POSCO for validating the proposed method.

• Journal of Korea Multimedia Society
• /
• v.15 no.7
• /
• pp.847-858
• /
• 2012

In this paper, we propose a mobile watermarking based on the distortion analysis of display-capture image in a smart phone. We compose a random sequence by utilizing the property of frequency band in the wavelet domain. Then we calculate the CCS (Coefficients Comparative Sum) using the block wavelet coefficients of selected subbands after the wavelet transformation and the random sequence and repeatedly embed a watermark using an insertion threshold for the watermark robustness. For correcting a distortion caused by the display-capture process, we adopt a frame at the outside of watermarked image, then we can equate a watermark synchronization by detecting the frame. And we can improve frame detection ratio by using an iteratively adaptive threshold. A proposed scheme embedded information of 206 bits into standard digital images and it shows an average about 41.42 dB in PSNR. In watermark extract experiments, a proposed scheme accurately recognizes the frame more than 97% in total captured images. Also in BER (Bit Error Ratio) of captured images, it shows about 3.73%, then it was improved more than 70%, compared with the Pramila's method.

• Journal of the Korean Geographical Society
• /
• v.51 no.4
• /
• pp.509-523
• /
• 2016

The soil prediction can provide quantitative soil information for sustainable mountainous ecosystem management. Visible near infrared spectroscopy, one of soil prediction methods, has been applied to predict several soil properties with effective costs, rapid and nondesctructive analysis, and satisfactory accuracy. Spectral preprocessing is a essential procedure to correct noisy spectra for visible near infrared spectroscopy. However, there are no attempts to evaluate various spectral preprocessing methods. We tested 5 different pretreatments, namely continuum removal, Savitzky-Golay filter, discrete wavelet transform, 1st derivative, and 2nd derivative to predict soil carbon(C) and nitrogen(N). Partial least squares regression was used for the prediction method. The total of 153 soil samples was split into 122 samples for calibration and 31 samples for validation. In the all range, absorption was increased with increasing C contents. Specifically, the visible region (650nm and 700nm) showed high values of the correlation coefficient with soil C and N contents. For spectral preprocessing methods, continuum removal had the highest prediction accuracy(Root Mean Square Error) for C(9.53mg/g) and N(0.79mg/g). Therefore, continuum removal was selected as the best preprocessing method. Additionally, there were no distinct differences between Savitzky-Golay filter and discrete wavelet transform for visual assessment and the methods showed similar validation results. According to the results, we also recommended Savitzky-Golay filter that is a simple pre-treatment with continuum removal.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2011.05a
• /
• pp.128-128
• /
• 2011

본 연구에서는 자동유량측정시설에 의하여 실시간으로 생산되는 자동유량측정 자료의 정상성 여부를 판단하는데 중요한 적정 측정 신뢰구간을 실시간으로 예측할 수 있는 기술을 개발하였다. 전세계적으로, 현대적인 유량측정이 시작된 이래 연속유량 산정을 위한 방법은 수위-유량관계곡선을 이용하는 방법 외에 실무적으로 활용 가능한 방법은 거의 전무한 실정이다. 수위-유량관계곡선을 이용하는 방법은 연속수위를 계측하여 이에 해당하는 연속유량을 산정하는 방법으로 수위와 유량간에 일정한 관계를 가지는 정상적인 흐름을 보이는 자연하천의 경우에 정확도가 매우 높다. 그러나 감조나 구조물 등에 의해 유량이 조절되는 경우에 유량산정의 정확도는 현저히 떨어지게 된다. 따라서 수위에서 유량을 환산하는 방법이 아닌 유량을 직접 연속으로 측정하는 방법이 꾸준히 연구되어 왔고, 이 중 가장 대표적인 방법이 자동유량측정 방법이다. 그러나 자동유량측정 방법은 유량을 연속으로 측정할 수 있다는 장점에 반해 측정된 유량의 정확도를 높이기가 매우 어렵다는 단점도 가지고 있다. 계측 자체의 기술적 한계는 주로 계측기기적인 문제로 이는 전자기, 통신 기술 등 첨단 기술의 발전과 함께 다양한 현장 시험을 통해 폭넓은 개선이 이루어지고 있다. 그러나 아직 기술적 완성도가 완전하지 못한 현실에서, 현재 설치되어 있는 자동유량측정 유량자료의 신뢰도를 높이기 위해서는 각각의 계측 시점에서 자료가 정상적으로 산정되고 있는지에 대한 검정이 필요하고, 이는 자동유량측정 자료의 정확도 확보에 매우 중요한 관건으로 작용할 수밖에 없다. 이러한 배경에서 본 연구에서는 조석성분과 유출성분을 분리하여 예측하는 방법을 새롭게 개발 적용하였다. 자료는 자료의 시간해상도 증감에 따른 실제 예측의 정확도 증감을 고려하여 가장 적절하다고 판단되는 시자료를 사용하였으며, 자료간 상관을 분석하여 주 입력 자료로 팔당댐 방류량, 한강대교 지점 수위, 전류 수위를 이용하였다. 모형의 예측 능력을 극대화하기 위하여 조석 영향을 받는 자료의 경우는 웨이블릿 변환(wavelet transform)을 이용하여 순수 유출성분과 조위성분을 분리하여 별도로 적용하였다. 그리고 예측을 위한 모형은 실시간 자료기반 모형으로 그 안정성이 인정된 서포트벡터머신(support vector machine)을 이용하였다. 이러한 과정을 통해 한강대교 지점의 순수 유출성분과 조위성분의 유량을 각각 예측한 후 두 결과를 합성하여 최종 한강 대교 지점의 유량을 산정하였다. 조석성분을 분리하여 한강대교 지점의 유량을 예측한 결과 대부분의 예측치가 95% 예측구간에 포함되었다. 그리고 조석성분을 분리하지 않은 모형과 조석성분을 분리한 모형의 예측 능력을 비교한 결과, 조석성분을 분리한 모형이 예측이 정확도가 높았다. RMSE의 경우 분리하지 않은 모형대비 23%의 예측오차가 감소하였고, NSC의 경우 0.92에서 0.95로 예측의 정확도가 증가하였다.

• The Journal of the Korea Contents Association
• /
• v.11 no.3
• /
• pp.271-280
• /
• 2011

Heart Rate Variability (HRV) analysis is a convenient tool to assess Myocardial Ischemia (MI). The analysis methods of HRV can be divided into time domain and frequency domain analysis. This paper uses wavelet transform as frequency domain analysis in contrast to time domain analysis in short term HRV analysis. ST-T and normal episodes are collected from the European ST-T database and the MIT-BIH Normal Sinus Rhythm database, respectively. An episode can be divided into several segments, each of which is formed by 32 successive RR intervals. Eighteen HRV features are extracted from each segment by the time and frequency domain analysis. To diagnose MI, the Neural Network with Weighted Fuzzy Membership functions (NEWFM) is used with the extracted 18 features. The results show that the average accuracy from time and frequency domain features is 75.29% and 80.93%, respectively.