• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제15권5호
• /
• pp.1610-1629
• /
• 2021

Failures frequently occurred in manufacturing machines due to complex and changeable manufacturing environments, increasing the downtime and maintenance costs. This manuscript develops a novel deep learning-based method named Multi-Domain Convolutional Neural Network (MDCNN) to deal with this challenging task with vibration signals. The proposed MDCNN consists of time-domain, frequency-domain, and statistical-domain feature channels. The Time-domain channel is to model the hidden patterns of signals in the time domain. The frequency-domain channel uses Discrete Wavelet Transformation (DWT) to obtain the rich feature representations of signals in the frequency domain. The statistic-domain channel contains six statistical variables, which is to reflect the signals' macro statistical-domain features, respectively. Firstly, in the proposed MDCNN, time-domain and frequency-domain channels are processed by CNN individually with various filters. Secondly, the CNN extracted features from time, and frequency domains are merged as time-frequency features. Lastly, time-frequency domain features are fused with six statistical variables as the comprehensive features for identifying the fault. Thereby, the proposed method could make full use of those three domain-features for fault diagnosis while keeping high distinguishability due to CNN's utilization. The authors designed massive experiments with 10-folder cross-validation technology to validate the proposed method's effectiveness on the CWRU bearing data set. The experimental results are calculated by ten-time averaged accuracy. They have confirmed that the proposed MDCNN could intelligently, accurately, and timely detect the fault under the complex manufacturing environments, whose accuracy is nearly 100%.

• 한국콘텐츠학회논문지
• /
• 제11권3호
• /
• pp.271-280
• /
• 2011

심박 변이도 (HRV) 분석은 심근허혈 (MI)를 평가하기 위한 편리한 도구이다. HRV에 대한 분석법은 시간 영역과 주파수 영역 분석으로 나눠질 수 있다. 본 논문은 단기간의 HRV 분석에 있어서 웨이블릿 변환을 주파수 영역 분석과 시간 영역 분석 비교하기 위하여 사용하였다. ST-T와 정상 에피소드는 각각 European ST-T 데이터베이스와 MIT-BIH Normal Sinus Rhythm 데이터베이스에서 각각 수집되었다. 한 에피소드는 32개 연속하는 RR 간격으로 나눠질 수 있다. 18개 HRV 특징은 시간과 주파수 영역 분석을 통하여 추출된다. 가종 퍼지소속함수 신경망 (NEWFM)은 추출된 18개의 특징을 이용하여 심근허혈을 진단하였다. 결과는 보여주는 평균 정확도로부터 시간영역과 주파수영역의 특징은 각각 75.29%와 80.93%이다.

• 한국멀티미디어학회논문지
• /
• 제22권12호
• /
• pp.1457-1465
• /
• 2019

3D convolution is to stack multiple consecutive frames to form a cube, and then apply the 3D convolution kernel in the cube. In this structure, each feature map of the convolutional layer is connected to multiple adjacent sequential frames in the previous layer, thus capturing the motion information. However, due to the changes of pedestrian posture, motion and position, the convolution at the same place is inappropriate, and when the 3D convolution kernel is convoluted in the time domain, only time domain features of three consecutive frames can be extracted, which is not a good enough to get action information. This paper proposes an action recognition method based on feature fusion of 3D convolutional neural network. Based on the VGG16 network model, sending a pre-acquired optical flow image for learning, then get the time domain features, and then the feature of the time domain is extracted from the features extracted by the 3D convolutional neural network. Finally, the behavior classification is done by the SVM classifier.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2009년도 정보 및 제어 심포지움 논문집
• /
• pp.37-39
• /
• 2009

In the research of speech recognition, locating the beginning and end of a speech utterance in a background of noise is of great importance. Since the background noise presenting to record will introduce disturbance while we just want to get the stationary parameters to represent the corresponding speech section, in particular, a major source of error in automatic recognition system of isolated words is the inaccurate detection of beginning and ending boundaries of test and reference templates, thus we must find potent method to remove the unnecessary regions of a speech signal. The conventional methods for speech endpoint detection are based on two simple time-domain measurements - short-time energy, and short-time zero-crossing rate, which couldn't guarantee the precise results if in the low signal-to-noise ratio environments. This paper proposes a novel approach that finds the Lyapunov exponent of time-domain waveform. This proposed method has no use for obtaining the frequency-domain parameters for endpoint detection process, e.g. Mel-Scale Features, which have been introduced in other paper. Comparing with the conventional methods based on short-time energy and short-time zero-crossing rate, the novel approach based on time-domain Lyapunov Exponents(LEs) is low complexity and suitable for Digital Isolated Word Recognition System.

• 대한의용생체공학회:의공학회지
• /
• 제39권2호
• /
• pp.69-79
• /
• 2018

The present study proposes an algorithm that can discriminate between normal subjects and paroxysmal atrial fibrillation (PAF) patients, which is conducted using electrocardiogram (ECG) without PAF events. For this, time-domain features and random forest classifier are used. Time-domain features are obtained from Poincare plot, Lorenz plot of ${\delta}RR$ interval, and morphology analysis. Afterward, three features are selected in total through feature selection. PAF patients and normal subjects are classified using random forest. The classification result showed that sensitivity and specificity were 81.82% and 95.24% respectively, the positive predictive value and negative predictive value were 96.43% and 76.92% respectively, and accuracy was 87.04%. The proposed algorithm had an advantage in terms of the computation requirement compared to existing algorithm, so it has suggested applicability in the more efficient prediction of PAF.

• ETRI Journal
• /
• 제44권5호
• /
• pp.826-836
• /
• 2022

Signal decomposition is a computational technique that dissects a signal into its constituent components, providing supplementary information. In this study, the capability of two common signal decomposition techniques, including wavelet-based and empirical mode decomposition, on preterm birth classification was investigated. Ten time-domain features were extracted from the constituent components of electrohysterogram (EHG) signals, including EHG subbands and EHG intrinsic mode functions, and employed for preterm birth classification. Preterm birth classification and anticipation are crucial tasks that can help reduce preterm birth complications. The computational results show that the preterm birth classification obtained using wavelet-based decomposition is superior. This, therefore, implies that EHG subbands decomposed through wavelet-based decomposition provide more applicable information for preterm birth classification. Furthermore, an accuracy of 0.9776 and a specificity of 0.9978, the best performance on preterm birth classification among state-of-the-art signal processing techniques, were obtained using the time-domain features of EHG subbands.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2004년도 ICCAS
• /
• pp.682-685
• /
• 2004

This paper investigated a method for classifying emotional states by using pulse wave signal. It focused on finding effective features for emotional state classification. The emptional states considered here consisted of interest and neutral. Classification experiments utilized 65 and 60 samples of interest and neutral states respectively. We have investigated 19 features derived from pulse wave signals by using both time domain and frequency domain analysis methods with 2 classifiers of minimum distance (normalized Euclidean distanece) and ${\kappa}$-Nearest Neighbour. The Leave-one-out cross validation was used as an evaluation mehtod. Based on experimental results, the most efficient features were a combination of 4 features consisting of (i) the mean of the first differences of the smoothed pulse rate time series signal, (ii) the mean of absolute values of the second differences of thel normalized interbeat intervals, (iii) the root mean square successive difference, and (iv) the power in high frequency range in normalized unit, which provided 80.8% average accuracy with ${\kappa}$-Nearest Neighbour classifier.

• 한국음향학회:학술대회논문집
• /
• 한국음향학회 1994년도 FIFTH WESTERN PACIFIC REGIONAL ACOUSTICS CONFERENCE SEOUL KOREA
• /
• pp.674-679
• /
• 1994

Acoustic signal such as speech and scattered sound, are generally a nonstationary process whose frequency contents vary at any instant of time. For time-varying signal, whether a nonstationary or a deterministic transient signal, a traditional frequency domain representation does not reveal the contents of signal characteristics and may lead to erroneous results such as the loss of desired characteristics features or the mis-interpretation for a wrong conclusion. A time-frequency domain representation is needed to characterize such signatures. Pseudo Wigner-Ville distribution (PWVD) is ideally suited for portraying nonstationary signal time-frequency domain and carried out by adapting the fast Fourier transform algorithm. In this paper, the important properties of PWVD were investigated using both stationary and nonstationry signatures by numerical examples PWVD was applied to acoustic sigtnatures to demonstrate its application for time-ferquency domain analysis.

• 한국철도학회논문집
• /
• 제2권2호
• /
• pp.21-30
• /
• 1999

This study proposes the analysis and evaluation method of time series ultrasonic signal using the phase space-frequency domain. Features extracted from time series signal analyze quantitatively characteristics of weld defects. For this purpose, analysis objectives in this study are features of time domain and frequency domain. Trajectory changes in the attractor indicated a substantial difference in fractal characteristics resulting from distance shifts such as parts of head and flange even though the types of defects are identified. These differences in characteristics of weld defects enables the evaluation of unique characteristics of defects in the weld zone. In quantitative fractal feature extraction, feature values of 3.848 in the case of part of head(crack) and 4.102 in the case of part of web(side hole) and 3.711 in the case of part of flange(crack) were proposed on the basis of fractal dimension. Proposed phase space-frequency domain method in this study can integrity evaluation for defect signals of rail weld zone such as side hole and crack.

• 비파괴검사학회지
• /
• 제36권2호
• /
• pp.93-101
• /
• 2016

This paper presents the results obtained using time-series-based methods for structural damage assessment. The methods are applied to a wind turbine blade structure subjected to fatigue loads. A 9 m CX-100 (carbon experimental 100 kW) blade is harmonically excited at its first natural frequency to introduce a failure mode. Consequently, a through-thickness fatigue crack is visually identified at 8.5 million cycles. The time domain data from the piezoelectric active-sensing techniques are measured during the fatigue loadings and used to detect incipient damage. The damage-sensitive features, such as the first four moments and a normality indicator, are extracted from the time domain data. Time series autoregressive models with exogenous inputs are also implemented. These features could efficiently detect a fatigue crack and are less sensitive to operational variations than the other methods.