• Journal of Advanced Research in Ocean Engineering
• /
• 제2권4호
• /
• pp.202-208
• /
• 2016

In this paper, we propose novel seabed sediment classification algorithm using feature obtained by continuous wavelet transform (CWT). Contrast to previous researches using direct reflection coefficient of seabed which is function of frequency and is highly influenced by sediment types, we develop an algorithm using both direct reflection signal and backscattering signal. In order to obtain feature vector, we employ CWT of the signal and obtain histograms extracted from local binary patterns of the scalogram. The proposed algorithm also adopts principal component analysis (PCA) to reduce dimension of the feature vector so that it requires low computational cost to classify seabed sediment. For training and classification, we adopts K-means clustering algorithm which can be done with low computational cost and does not require prior information of the sediment. To verify the proposed algorithm, we obtain field data measured at near Jeju island and show that the proposed classification algorithm has reliable discrimination performance by comparing the classification results with actual physical properties of the sediments.

• 한국감성과학회:학술대회논문집
• /
• 한국감성과학회 2011년도 춘계학술대회
• /
• pp.33-34
• /
• 2011

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제17권9호
• /
• pp.2361-2376
• /
• 2023

The electrocardiogram (ECG) signal is commonly used to screen and diagnose cardiovascular diseases. In recent years, deep neural networks have been regarded as an effective way for automatic ECG disease diagnosis. The convolutional neural network is widely used for ECG signal extraction because it can obtain different levels of information. However, most previous studies adopt single scale convolution filters to extract ECG signal features, ignoring the complementarity between ECG signal features of different scales. In the paper, we propose a dual-scale network with convolution filters of different sizes for 12-lead ECG classification. Our model can extract and fuse ECG signal features of different scales. In addition, different spatial and time periods of the feature map obtained from the 12-lead ECG may have different contributions to ECG classification. Therefore, we add a spatial-temporal attention to each scale sub-network to emphasize the representative local spatial and temporal features. Our approach is evaluated on PTB-XL dataset and achieves 0.9307, 0.8152, and 89.11 on macro-averaged ROC-AUC score, a maximum F1 score, and mean accuracy, respectively. The experiment results have proven that our approach outperforms the baselines.

• 말소리와 음성과학
• /
• 제4권3호
• /
• pp.103-110
• /
• 2012

In this paper, a target signal detection method using multiple signal classification (MUSIC) algorithm is proposed. The MUSIC algorithm is a subspace-based direction of arrival (DOA) estimation method. Using the inverse of the eigenvalue-weighted eigen spectra, the algorithm detects the DOAs of multiple sources. To apply the algorithm in target signal detection for GSC-based beamforming, we utilize its spectral response for the DOA of the target source in noisy conditions. The performance of the proposed target signal detection method is compared with those of the normalized cross-correlation (NCC), the fixed beamforming, and the power ratio method. Experimental results show that the proposed algorithm significantly outperforms the conventional ones in receiver operating characteristics (ROC) curves.

• 동력기계공학회지
• /
• 제14권2호
• /
• 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.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2000년도 제15차 학술회의논문집
• /
• pp.115-115
• /
• 2000

A gait pattern classification method using electromyography(EMG) signal is presented. The gait pattern with four stages such as stance, heel-off, swing and heel-strike is analyzed and classified using feature parameters such as zero-crossing, integral absolute value and variance of the EMG signal. The EMG signal from Tibialis Anterior and Gastrocnemius muscles was obtained using the surface electrodes, and low-pass filtered at 10kHz. The filtered analog signal was sampled at every 0.5msec and converted to digital signal with 12-bit resolution. The obtained data is analyzed and classified in terms of feature parameters. Analysis results are given to show that the gait patterns classified by the proposed method are feasible.

• 한국정보통신학회논문지
• /
• 제16권9호
• /
• pp.1870-1877
• /
• 2012

천이신호는 지속시간이 짧으면서 길이의 변화가 크고, 시변성 및 비정재성 특성을 갖는다. 이러한 천이신호의 식별에는 분석 프레임 단위로 참조신호에 대한 기준패턴을 만들어 입력신호와의 유사도를 비교하는 방법이 효과적일 수 있다. 본 연구에서는 참조신호의 기준패턴으로 프레임 기반의 특징벡터들에 대해 확률통계 모형인 정규혼합모델을 적용하는 방법을 제안하고, 다양한 수중 천이신호에 대한 식별 실험을 통해 제안한 방법의 타당성을 검증하였다.

• 전기학회논문지
• /
• 제67권8호
• /
• pp.1089-1098
• /
• 2018

In this paper, we propose an autonomous feeding robot and its obstacle classification system using ultrasonic sensors to secure the driving safety of the robot and efficient feeding operation. The developed feeding robot is verified by operation experiments in a cattle shed. In the proposed classification algorithm, not only the maximum amplitude of the ultrasonic echo signal but also two gradients of the signal and the variation of amplitude are considered as the feature parameters for object classification. The experimental results show the efficiency of the proposed classification method based on the Support Vector Machine, which is able to classify objects or obstacles such as a human, a cow, a fence and a wall.

• 비파괴검사학회지
• /
• 제15권4호
• /
• pp.531-539
• /
• 1996

본 연구에서는 초음파 신호형상인식법을 이용하여 용접부의 인공 결함을 분류하기 위한 연구를 실시하였다. 이를 위해 신호처리 및 특징 변수를 추출할 때에 많은 사용자 정의 변수를 가지는 신호 형상 인식 패키지를 개발하였으며 디지탈 신호처리, 특징 변수 추출, 특징 변수의 선택, 분류기 선정 등의 과정을 일괄적으로 처리하였다. 특히, 선형 분류기, 경험적 Bayesian 분류기 등의 통계적 분류기와 신경회로망 분류기를 함께 사용하여 비교, 검토하였다. 이에 관한 적용 연구로 노치와 구멍으로 이루어진 인공 결함을 분류하였다. 그 결과 인공결함 분류에서 높은 인식률을 얻었으며, 특히 적절히 학습 시켰을 경우 신경회로망 분류기가 통계적 분류기에 비하여 인식률 면에서 유리하였다.

• 한국정밀공학회:학술대회논문집
• /
• 한국정밀공학회 1995년도 추계학술대회 논문집
• /
• pp.393-396
• /
• 1995

In this syudy, the researches classifying the artificial and natural flaws in welding parts are performed using the smart pattern recognition technology. For this purpose the smart signal pattern recognition package including the user defined function was developed and the total procedure including the digital signal processing,feature extraction , feature selection and classifier selection is treated by bulk. Specially it is composed with and discussed using the statistical classifier such as the linear disciminant function classifier, the empirical Bayesian classifier. Also, the smart pattern recognition technology is applied to classification problem of natural flaw(i.e multiple classification problem-crack,lack of penetration,lack of fusion,porosity,and slag inclusion, the planar and volumetric flaw classification problem). According to this results, if appropriately learned the neural network classifier is better than ststistical classifier in the classification problem of natural flaw. And it is possible to acquire the recognition rate of 80% above through it is different a little according to domain extracting the feature and the classifier.