An Antinoise-Folding Algorithm for the Recovery of Biomedical Signals From Noisy Measurements

Muduli, Priya Ranjan; Mandal, Atindra Kanti

doi:10.1109/tim.2017.2734018

Cited by 10 publications

(3 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, this method contains few limitations working in real-time applications. Priya Ranjan Muduli et al [4] in 2017 derived a novel algorithm for the extraction of biomedical signals from noisy calculations by sparse recovery analysis, and the authors [5] in 2015 did research on the study of S2 heart sounds, which engages with calculating the time period and the energy of normalized cardiac sounds, however they could not distinguish heart sounds. The authors [6] in 2018 and the authors [7] in 2013 did research work on heart sound analysis using the wavelet transform algorithm.…”

Section: Literature Reviewmentioning

confidence: 99%

Conv-Random Forest-Based IoT: A Deep Learning Model Based on CNN and Random Forest for Classification and Analysis of Valvular Heart Diseases

Sinha Roy,

Roy,

Mandal

2023

IEEE Open J. Instrum. Meas.

View full text Add to dashboard Cite

Cardiovascular diseases are growing rapidly in this world. Around 70 % of the world's population is suffering from the same. The entire research work is grouped into classification and analysis of heart sound. We defined a new Squeeze network based deep learning model -Convolutional Random Forest for real time valvular heart sound classification and analysis using industrial raspberry pi 4B. The proposed electronic stethoscope is internet enabled using ESP32, and raspberry pi. The said IOT based model is also low cost, portable, and can be reachable to distant remote places where doctors are not available. As far as the classification part is concerned, the multiclass classification is done for seven types of valvular heart sound. The random forest classifier scored a good accuracy among other ensemble methods in small training set data. The CNN-based Squeeze Net model achieved a decent accuracy of 98.65 % after its hyper parameters were optimized for heart sound analysis. The proposed IOT based model overcomes the drawbacks faced individually in both squeeze network and random forest. CNN-based Squeeze net model and Random Forest classifier combined together improved the performance of classification accuracy. The squeeze net model plays a pivotal part in feature extraction of heart sound, and a Random forest classifier acts as a classifier in the class prediction layer for predicting class labels. Experimental results on several datasets like the Kaggle dataset, Physio net challenge, and Pascal Challenge showed that the Conv-RF model works the best. The proposed IOT based Conv-RF model is also applied on selected subjects with different age groups and genders having history of heart diseases. The Conv-Random Forest method scored an accuracy of 99.37+ 0.05% on the different test datasets with a sensitivity of 99.5 + 0.12% and specificity of 98.9 + 0.03%. The proposed model is also examined with the current state of art models in terms of accuracy.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

Conv-Random Forest-Based IoT: A Deep Learning Model Based on CNN and Random Forest for Classification and Analysis of Valvular Heart Diseases

Sinha Roy,

Roy,

Mandal

2023

IEEE Open J. Instrum. Meas.

View full text Add to dashboard Cite

show abstract

“…Denoising of signals has grown considerably in recent years as it has become an area of interest (Chen et al 2018;Ignjatović et al 2018;Muduli et al 2017). In the biomedical field, ECG signal processing has been extensively studied by the scientific community, particularly its denoising for reliable diagnosis (Vargas 2018;Hesar and Mohebbi 2017;Pham et al 2018).…”

Section: Introductionmentioning

confidence: 99%

ECG signal denoising by fractional wavelet transform thresholding

2020

View full text Add to dashboard Cite

Introduction The analysis of electrocardiogram (ECG) signals allows experts to diagnose several cardiac disorders. However, the accuracy of such diagnosis depends heavily on the signal quality. In this paper, an efficient method based on fractional wavelet decomposition coupled with thresholding techniques is proposed for noise removal. Methods The usual low-pass and high-pass filters of the wavelet transform are replaced by fractional-order ones. Thus, fractional wavelets are proposed, simulated, and compared to other wavelets for ECG denoising. The denoising process was made operational by the means of an appropriate choice of the wavelet transform coefficient thresholding and the wavelet decomposition level of the signal. Results Considering the relative error metrics, the best wavelet function for efficient denoising is the fractional one. In our study, we have used eight real ECG signals from the Physionet MITBIH. In order to prove the effectiveness of our method, we investigated the filtering of two types of noises, namely Gaussian white noise and power-line interference (PLI) noise. The proposed method removed the Gaussian white noise completely and had better performance on the PLI noise. Considering classical metrics of assessment, results show the advantage of the proposed method compared to other types of wavelets. Conclusion The proposed method is the most suitable one for removing PLI and Gaussian white noise from ECG signals with superior performance than other wavelets. Also, it can be applied for high-frequency denoising even without a priori frequency knowledge.

show abstract

“…Y. Ma et al proposed a blind sub-Nyquist cooperative wideband spectrum sensing scheme to reduce energy consumption in wideband signal processing without loss of performance [29]. However, this algorithm requires high sparsity in signal and high signal-to-noise ratio, and the noise folding caused by compressed sampling [30] brings 3dB loss in recovery signal-to-noise ratio when doubling the compression ratio.…”

Section: Introductionmentioning

confidence: 99%

Wideband Spectrum Sensing Based on Bidirectional Decision of Normalized Spectrum for Cognitive Radio Networks

Wang

et al. 2019

IEEE Access

View full text Add to dashboard Cite

Cognitive radio (CR) is considered to be an effective approach to eliminate the dilemma of spectrum shortage. To meet the ever-increasing demands of instant and accurate spectrum sensing in CR with wideband and multi-frequency-slots, a novel wideband spectrum sensing algorithm based on bidirectional decision of normalized spectrum (BDNP) is proposed in this paper. The proposed algorithm takes the normalized power spectrum within the frequency slot as the detection statistics, and finds out all of the occupied frequency slots in the range of the target bandwidth by searching forward and backward in sequence. The asymptotic normality and independence of Fourier transform is proved firstly, and based on which the false alarm probability of single decision is derived. Additionally, the closed-form expression of decision threshold is obtained by using Neyman-Pearson criterion. Theoretical analysis and simulation results show that the BDNP algorithm can accurately identify occupied frequency slots, which provides the base of avoiding interference to the primary users. Furthermore, comparing with the spectrum sensing algorithm based on conventional spectral estimation (CSE), BDNP algorithm can effectively overcome noise uncertainty in spectrum sensing.

show abstract

An Antinoise-Folding Algorithm for the Recovery of Biomedical Signals From Noisy Measurements

Cited by 10 publications

References 24 publications

Conv-Random Forest-Based IoT: A Deep Learning Model Based on CNN and Random Forest for Classification and Analysis of Valvular Heart Diseases

Conv-Random Forest-Based IoT: A Deep Learning Model Based on CNN and Random Forest for Classification and Analysis of Valvular Heart Diseases

ECG signal denoising by fractional wavelet transform thresholding

Wideband Spectrum Sensing Based on Bidirectional Decision of Normalized Spectrum for Cognitive Radio Networks

Contact Info

Product

Resources

About