Papers by Keyword: ECG Signal

Abstract: As most of developed empirical mode decomposition (EMD) based R-peaks detection algorithms consume a considerable time of calculation caused by the large length of the input ECG signal, the design of a new technique that allows the acceleration of such methods becomes necessary. Accordingly, a new variant of an EMD-based strategy for R-peaks localization is presented. The new accelerated variant is constituted of three essential parts. The first step is the length reduction of the input signal by means of the truncation in the Fast Fourier Transform (FFT) domain followed by the application of the inverse FFT guaranteeing a suitable time-domain down-sampling. Consequently, the new input signal of a reduced length preserves all medical information contained initially in the original lengthy signal. The second part is dedicated to identify the QRS complex using EMD-based R-peaks detection. This latter comprises a low-pass filter, Empirical Mode Decomposition (EMD) and the Hilbert transform, Finally, the third phase is the time-domain up-sampling using the FFT, the zero padding and the Inverse Fast Fourier Transform (IFFT) to obtain a resulting processed signal which has the same length as the original signal. Next, as a post-processing step, final R-peaks refined localization is achieved. It is noticeable that the new variant ensures same results, in term of accuracy, as the standard method; however, a significant speed-up ratio of 6.95:1 is reported. Additionally, to more prove the effectiveness of the suggested strategy, it has been applied to accelerate two other efficient algorithms and satisfactory speed up ratios of, 7.20:1 and 4.23:1, respectively have been reached.

Abstract: Cardiovascular disease is the leading cause of death in the world and the number one killer in Indonesia, with a mortality rate of 17.05%. The target of this research is to increase the range of electrocardiograph (ECG) equipment using LoRa Technology. With LoRa Technology, it is expected that the data transmission process can run effectively and produce an accurate ECG signal and minimal noise. The research method is by sending a heart signal from the ECG simulator by the microcontroller via LoRa Technology which is received by the PC (Personal Computer) and the ECG signal is displayed on the PC display. The most optimal setting will be obtained from the sender-receiver distance and baudrate by measuring data loss and delay. In this study, the simulated cardiac signal from the phantom ECG is fed to an analog signal processing circuit, then the signal is converted to digital and digitally filtered on the microcontroller, then the signal is sent via the LoRa HC-12 Transceiver to a PC with baudrate, distance and barrier settings. The results obtained are that data transmission can be carried out at a distance of 175 meters without a barrier and a distance of 50 meters with a barrier. This remote ECG equipment can detect heart signals and the results can be sent to a PC using LoRa Technology. The implication is that the transmission of ECG signal data via the Lora HC-12 Transceiver media can be carried out optimally at the 9600 baudrate setting.

Abstract: The recordings of electrocardiogram (ECG), as an important biological signal which provides a valuable basis for the clinical diagnosis and treatment, are often corrupted by the wide range of artifacts. One important of them is power line interference (PLI). The overlapping interference affects the quality of ECG waveform, leading to the false detection and recognition of wave groups, and thus causing faulty treatment or diagnosis. The study deals with some of the signal processing approaches frequently used for elimination of PLI in ECG signal and compares the accuracy of methods by evaluation of the power of the remaining noise and comparing a filtered ECG signal with an original. The results are compared for three levels of interference and each tested method: Butterworth filter (BF), notch filter, moving average filter (MA), adaptive noise canceller (ANC), wavelet transform (WT) and empirical mode decomposition (EMD).

Abstract: Computer-aided diagnosis of Premature Ventricular Contraction (PVC) plays an important role in timely detection and treatment of arrhythmias. Conventional identification methods based on back propagation neural network (BPNN) get problems of overlong training time and local optimum. This paper proposes an application of improved BPNN on PVC identification and the improvements of BPNN are based on self-adaptive learning rate and momentum in training. Denoising and feature extraction of ECG signal obtained from MIT-BIH arrhythmia database are processed first. A comparison between standard BPNN and improved BPNN shows that the latter gets less training time and better accuracy.

Abstract: ECG signal contains abundant information of human heart activity. It is important basis of doctors’ diagnose. With the development of computer technology, computer aided analysis has been widely applied in the field of ECG analysis. Most of the traditional method is based on single classifier and too complex. Also, the accuracy is not high. This paper focuses on ECG heart beat classification, extracting different types of feature, training different classifiers by vector model and support vector machine (SVM), merging the result of multiple classifiers. In this paper, we used the advanced voting method (voting by weight) to fusion the result of different classifier, having compared it with the traditional voting method.It performed better than traditional method in term of accuracy

Abstract: ECG signal is affected by many factors such as noise and interference in the process of acquisition, which make it difficult for clinicians to interpret the ECG signal precisely and effectively. In order to detect whether an ECG signal is worthy to be interpreted by clinicians, an algorithm was proposed to assess the quality of ECG signal based on wavelet energy ratio and wavelet energy entropy. After wavelet decomposition, the ECG signals wavelet energy ratio and wavelet energy entropy were calculated in three different frequency bands, and we defined them as the quality indices to evaluate the quality of ECG signal. Experimental results show that we can achieve an accuracyof 95.2%.

Abstract: According to the process of the ECG signal extraction, the ECG signal is susceptible to interference which will affect the quality and effect of ECG test. In this essay, we designed an ECG signal filtering system based on ARM. It can filter the interference signal and reduce the interference of the common mode signal and power frequency, through the design circuit of the preamplifier, post amplification, filtering, notch filtering, and power amplification. Thus, ECG signal will be better collected and met the best demand.

Abstract: Aiming at the large calculation workload of adaptive algorithm in adaptive filter based on wavelet transform, affecting the filtering speed, a wavelet-based neural network adaptive filter is constructed in this paper. Since the neural network has the ability of distributed storage and fast self-evolution, use Hopfield neural network to implement adaptive filter LMS algorithm in this filter so as to improve the speed of operation. The simulation results prove that, the new filter can achieve rapid real-time denoising.

Abstract: Baseline drift is the main noise of ECG signals which affects the detection accuracy so its removal plays a significantrole in the ECG signal preprocessing. Complex calculation and non-optimal signal processing cause problems of ineffective results and low real-time effects in traditional methods. This paper designs a new filter to remove baseline drift based on the theory of mathematical morphology, which is created by the geometric parameters of the ECG signal. Experiments show that the method can effectively remove the noise of baseline drift by simple computation and is helpful to improve the detection accuracy.

Abstract: Electrocardiogram (ECG) is a kind of weak signal. It was disturbed by surrounding factors, even by patient him/herself. It was happened mostly in portable device. Filtering is an usual step in ECG signal processing. Therefore, the quality evaluation of ECG signal became necessary. In the paper, some indexes were proposed to evaluate the quality of filtered ECG signal. The definition and recommended values or limits of the indexes were discussed. The indexes covered from the aspects of signal procession and clinical diagnosis meanings. They were Signal-to Noise Ratio (SNR), Autocorrelation coefficient (AC), Transformation Ratio (StTR) and Voltage Amplitude Change (StTV) of ECG ST Segment. Median, Wavelet, and Morphology filters were selected in the experiments. From the experiment results, Wavelet performs best in controlling attenuation, but it distorted ST segment the most, both in shape and in its voltage amplitude. The shape change ratio may reach 25%, compare to 17% of median and 14% of morphology, and those filters were acceptable clinical evaluation. It was proved that the indexes can become the potential standard in quality evaluation in ECG signal filtering process.