FPGA Implementation of IIR Notch and Anti-Notch Filters With an Application to Localization of Protein Hot-Spots.

In this paper, high-speed second-order infinite impulse response (IIR) notch filter (NF) and anti-notch filter (ANF) are designed and realized on hardware. The improvement in speed of operation for the NF is then achieved by using the re-timing concept. The ANF is designed to specify a stability margin and minimize the amplitude area. Next, an improved approach is proposed for the detection of protein hot-spot locations using the designed second-order IIR ANF. The analytical and experimental results reported in this paper show that the proposed approach provides better hot-spot prediction compared to the reported classical filtering techniques based on the IIR Chebyshev filter and S-transform. The proposed approach also yields consistency in prediction hot-spots compared to the results based on biological methodologies. Furthermore, the presented technique reveals some new "potential" hot-spots. The proposed filters are simulated and synthesized using the Xilinx Vivado 18.3 software platform with Zynq-7000 Series (ZedBoard Zynq Evaluation and Development Kit xc7z020clg484-1) FPGA family.

A New ECG Denoising Framework Using Generative Adversarial Network.

This paper presents a novel Electrocardiogram (ECG) denoising approach based on the generative adversarial network (GAN). Noise is often associated with the ECG signal recording process. Denoising is central to most of the ECG signal processing tasks. The current ECG denoising techniques are based on the time domain signal decomposition methods. These methods use some kind of thresholding and filtering approaches. In our proposed technique, convolutional neural network (CNN) based GAN model is effectively trained for ECG noise filtering. In contrast to existing techniques, we performed end-to-end GAN model training using the clean and noisy ECG signals. MIT-BIH Arrhythmia database is used for all the qualitative and quantitative analyses. The improved ECG denoising performance open the door for further exploration of GAN based ECG denoising approach.

Noise robust automatic heartbeat classification system using support vector machine and conditional spectral moment.

Heartbeat classification is central to the detection of the arrhythmia. For the effective heartbeat classification, the noise-robust features are very significant. In this work, we have proposed a noise-robust support vector machine (SVM) based heartbeat classifier. The proposed classifier utilizes a novel noise-robust morphological feature which is based on the conditional spectral moment (CSM) of the heartbeat. In addition to the proposed CSM feature, we have also employed the existing RR interval, the wavelets, and the higher-order statistics (HOS) based temporal and morphological feature sets. The noise-robustness test of the proposed CSM and all the studied feature sets is performed for the SVM based heartbeat classifier. Further, we have studied the significance of combining these temporal and morphological features on the final classification performance. For this purpose, the individual SVMs were trained for each of the feature set. The final classification is based on the ensemble of these individual SVMs. Various combining scheme such as sum, majority, and product rules are employed to ensemble the result of the individually trained SVMs. The experimental results show the noise-robustness of the proposed CSM feature. The proposed classifier gives improved overall performance compared to the existing heartbeat classification systems.

Variational mode decomposition based ECG denoising using non-local means and wavelet domain filtering.

This paper presents a novel electrocardiogram (ECG) denoising approach based on variational mode decomposition (VMD). This work also incorporates the efficacy of the non-local means (NLM) estimation and the discrete wavelet transform (DWT) filtering technique. Current ECG denoising methods fail to remove noise from the entire frequency range of the ECG signal. To achieve the effective ECG denoising goal, the noisy ECG signal is decomposed into narrow-band variational mode functions (VMFs) using VMD method. The idea is to filter out noise from these narrow-band VMFs. To achieve that, the center frequency information associated with each VMFs is used to exclusively divide them into lower- and higher-frequency signal groups. The higher frequency VMFs were filtered out using DWT-thresholding technique. The lower frequency VMFs are denoised through NLM estimation technique. The non-recursive nature of VMD enables the parallel processing of NLM estimation and DWT filtering. The traditional DWT-based approaches need large decomposition levels to filter low frequency noises and at the same time NLM technique suffers from the rare-patch effect in high-frequency region. On the contrary, in the proposed framework both NLM and DWT approaches complement each other to overcome their individual ill-effects. The signal reconstruction is performed using the denoised high frequency and low frequency VMFs. The simulation performed on the MIT-BIH Arrhythmia database shows that the proposed method outperforms the existing state-of-the-art ECG denoising techniques.

Significance of modified empirical mode decomposition for ECG denoising.

The primary objective of the presented work is to exploit the power of modified empirical mode decomposition (M-EMD) for the denoising of ECG signals. It is well known that the ECG signals get corrupted by a number of noises during the recording process. Especially, during wireless ECG recording and ambulatory patient monitoring, the signal gets corrupted by additive white Gaussian noise (AWGN). Over the years, several techniques have been proposed for ECG denoising. Among those, empirical mode decomposition (EMD) and nonlocal means (NLM) algorithm are noted to be quite effective. Further, the NLM-based approach is better in retaining the morphological characteristics in comparison to the EMD. Consequently, the two approaches are effectively combined in this paper so that each one complements the other. In the proposed approach, the noisy ECG signal is first preprocessed using the NLM algorithm. This is followed by decomposition of the partially denoised output through M-EMD. The decomposed components are suitably thresholded and then reconstructed to obtain the final denoised signal. This largely addresses the issue of under-averaged regions noted in the case of NLM-based denoising. Furthermore, the proposed approach is noted to be superior to the other existing techniques.