• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.17 no.9
• /
• 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.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.18 no.6
• /
• pp.277-283
• /
• 2023

Vital signals provide essential information regarding the health status of individuals, thereby contributing to health management and medical research. Present monitoring methods, such as ECGs (Electrocardiograms) and smartwatches, demand proximity and fixed postures, which limit their applicability. To address this, Non-contact vital signal measurement methods, such as CW (Continuous-Wave) radar, have emerged as a solution. However, unwanted signal components and a stepwise processing approach lead to errors and limitations in heart rate detection. To overcome these issues, this study introduces an integrated neural network approach that combines noise removal, demodulation, and dominant-frequency detection into a unified process. The neural network employed for signal processing in this research adopts a MLP (Multi-Layer Perceptron) architecture, which analyzes the in-phase and quadrature signals collected within a specified time window, using two distinct input layers. The training of the neural network utilizes CW radar signals and reference heart rates obtained from the ECG. In the experimental evaluation, networks trained on different datasets were compared, and their performance was assessed based on loss and frequency accuracy. The proposed methodology exhibits substantial potential for achieving precise vital signals through non-contact measurements, effectively mitigating the limitations of existing methodologies.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.31 no.8C
• /
• pp.801-805
• /
• 2006

A normalization approach to coefficient adaptation in the escalator(ESC) filter structure that conventionally employs least mean square(LMS) algorithm is introduced. Using Taylor's expansion of the local error signal, a normalized form of the ESC-LMS algorithm is derived. Compared with the computational complexity of the conventional ESC-LMS algorithm employs input power estimation for time-varying convergence coefficient using a single-pole low-pass filter, the computational complexity of the proposed method can be reduced by 50% without performance degradation.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.15 no.2
• /
• pp.74-84
• /
• 2016

After installing roundabouts, changes of travel behaviour in the vicinity of roundabouts can cause increasing traffic volumes and unbalanced flow conditions. In that cases, the efficiency of roundabouts as a whole intersections can drop due to the insufficient gap between vehicles in the circulating lanes. The purpose of this study is developing a dynamic signal metering operation method for roundabouts in which a real time Signal Metering operation algorithm is suggested and its performance is tested by using VISSIM COM Interface(Visual Basic Application). The results of the real time Signal Metering operation show that there is a substantial delay improvements when two adjoined approaches are combined together and the flows of metering approach are less than controlling approach. Especially, the total entering flow is around 1,600 vehicle/h gives the delay reduction per vehicle of 70.9~102.2(73.8~77.8%) seconds for four-lane-approach with one-lane roundabouts.

• Journal of the Institute of Convergence Signal Processing
• /
• v.12 no.4
• /
• pp.228-236
• /
• 2011

Emotion recognition plays an important role in the research area of human-computer interaction, and it allows a more natural and more human-like communication between humans and computer. Most of previous work on emotion recognition focused on extracting emotions from face, speech or EEG information separately. Therefore, a novel approach is presented in this paper, including face, speech and EEG, to recognize the human emotion. The individual matching scores obtained from face, speech, and EEG are combined using a weighted-summation operation, and the fused-score is utilized to classify the human emotion. In the experiment results, the proposed approach gives an improvement of more than 18.64% when compared to the most successful unimodal approach, and also provides better performance compared to approaches integrating two modalities each other. From these results, we confirmed that the proposed approach achieved a significant performance improvement and the proposed method was very effective.

• Proceedings of the Korean Society for Noise and Vibration Engineering Conference
• /
• 2013.04a
• /
• pp.694-695
• /
• 2013

An experimental study has been made with the use of time reversal concepts to recover the input waveform in a long range propagation of dispersive Lamb waves. Three techniques have been tested: Regular TR, 1 bit TR and Inverse filter (IF). The IF approach was found to completely recover the original input signal. Moreover, the IF technique significantly increases the contrast, i.e., the ratio of the recovered signal and the sideband signal.

• Journal of Navigation and Port Research
• /
• v.42 no.1
• /
• pp.57-66
• /
• 2018

Maritime industry is affected by outside factors significantly due to its derivative demand characteristics. However, the supply side can not react to these changes immediately and due to this uniqueness, maritime industry repeats the boom-bust cycle. Therefore the government itself needs to operate early warning system in order to monitor the market and notice the upcoming risks by setting up a system to prepare for the situations. In this research, signal approach is used to establish early warning system. Overall leading index is composed of crisis index that is based on BDI(Baltic Dry Index) and various leading indexes such as finance, economy, shipping and the others. As a result of computing overall leading index which is early warning system in maritime through signal approach, the index showed a high correlation coefficient with actual maritime risk index by difference of 4 months. Also, the result was highly accurate with overall leading index's QPS(Quadratic Probability Score) at 0.37.

• Transactions of the Korean Society of Mechanical Engineers
• /
• v.18 no.4
• /
• pp.1050-1056
• /
• 1994

When a vibration data for a rotating machine such as a pump or a compressor is concerned, the frequency fluctuation of the energy contents at an instant time may provide useful information on understanding the vibration characteristics of the rotating machinery, rather than the averaged energy distribution along the frequency axis. Especially, when a periodic signal has different spectral contents, the approach to use the averaged frequency distribution, called the normal frequency analysis, may not be appropriate to extract vibration source characteristics of the structure. This paper introduces a way to analyze the signal based on an instant time. In order to evaluate the performance of the various approach, the investigatation compares three different algorithms which are frequently implemented in the instantaneous frequency analysis. Also for the noise effect embodied in the true signal, various cases for different SN ratio have been examined. The result shows that the noise level is crucial to evalute the instantaneous frequency analysis. In order to implement the instantaneous frequency analysis, the extraction of the relevant information from the measured signal should have the high S/N ratio, i, e., 40 dB or above.

• The Journal of the Acoustical Society of Korea
• /
• v.27 no.7
• /
• pp.372-378
• /
• 2008

Voice activity detectors (VAD) are important in wireless communication and speech signal processing, In the conventional VAD methods, an expression for the likelihood ratio test (LRT) based on statistical models is derived in discrete Fourier transform (DFT) domain, Then, speech or noise is decided by comparing the value of the expression with a threshold, This paper presents a new statistical VAD method based on a signal subspace approach, The probabilistic principal component analysis (PPCA) is employed to obtain a signal subspace model that incorporates probabilistic model of noisy signal to the signal subspace method, The proposed approach provides a novel decision rule based on LRT in the signal subspace domain, Experimental results show that the proposed signal subspace model based VAD method outperforms those based on the widely used Gaussian distribution in DFT domain.

• Proceedings of the KOSOMBE Conference
• /
• v.1994 no.12
• /
• pp.134-137
• /
• 1994

In this paper, we describe an approach to ECG data coding based on a fractal theory of iterated contractive transformations defined piecewise. The main characteristic of this approach is that it relies on the assumption that signal redundancy can be efficiently captured and exploited through piecewise self-transformability on a block-wise basis. The variable range size technique is employed to reduce the reconstruction error. Large ranges are used for encoding the smooth waveform to yield high compression efficiency, and the smaller ranges are used for encoding rapidly varying parts of the signal to preserve the signal quality. The suggested algorithm was evaluated using MIT/BIH arrhythmia database. A high compression ratio is achieved with a relatively low reconstruction error.