Independent Component Analysis and Decision Trees for ECG Holter Recording De-Noising

Kužílek, Jakub; Kremen, Václav; Souček, Filip; Lhotská, Lenka

doi:10.1371/journal.pone.0098450

Cited by 32 publications

(16 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A large number of methods to deal with noise and/or artefacts from ECG signals have been developed, such as adaptive Filters [2,3], Independent Component Analysis (ICA) [4], Empirical Mode Decomposition (EMD) [5], adaptive Fourier decomposition [6], Savitzky-Golay filter [7], threshold method for high frequency noise detection [8], Kalman filters [9], Bayesian filter framework [10], wavelet technique [11], clustering of morphological features [12], and Neural Networks [13]. Very recent attempts include arrhythmia heart classification using different Deep Learning (DL) models [14] and QRS characteristics identification using Support Vector Machines (SVM) [15].…”

Section: Introductionmentioning

confidence: 99%

Deep Learning Models for Denoising ECG Signals

Arsene

Hankins

Yin

2019

2019 27th European Signal Processing Conference (EUSIPCO)

View full text Add to dashboard Cite

Effective and powerful methods for denoising real electrocardiogram (ECG) signals are important for wearable sensors and devices. Deep Learning (DL) models have been used extensively in image processing and other domains with great success but only very recently have been used in processing ECG signals. This paper presents several DL models namely Convolutional Neural Networks (CNNs), Long Short-Term Memory (LSTM), Restricted Boltzmann Machine (RBM) together with the more conventional filtering methods (low pass filtering, high pass filtering, Notch filtering) and the standard wavelet-based technique for denoising EEG signals. These methods are trained, tested and evaluated on different synthetic and real ECG datasets taken from the MIT PhysioNet database and for different simulation conditions (i.e. various lengths of the ECG signals, single or multiple records). The resultsshow the CNN model is a performant model that can be used for off-line denoising ECG applications where it is satisfactory to train on a clean part of an ECG signal from an ECG record, and then to test on the same ECG signal, which would have some high level of noise added to it. However, for real-time applications or near-real time applications, this task becomes more cumbersome, as the clean part of an ECG signal is very probable to be very limited in size. Therefore the solution put forth in this work is to train a CNN model on 1 second ECG noisy artificial multiple heartbeat data (i.e. ECG at effort), which was generated in a first instance based on few sequences of real signal heartbeat ECG data (i.e. ECG at rest).Afterwards it would be possible to use the trained CNN model in real life situations to denoise the ECG signal. This corresponds also to reality, where usually the human is put at rest and the ECG is recorded and then the same human is asked to do some physical exercises and the ECG is recorded at effort. The quality of results is assessed visually but also by using the Root Mean Squared (RMS) and the Signal to Noise Ratio (SNR) measures. All CNN models used an NVIDIA TITAN V Graphical Processing Unit (GPU) with 12 GB RAM, which reduces drastically the computational times. Finally, as an element of novelty, the paper presents also a Design of Experiment (DoE) study which intends to determine the optimal structure of a CNN model, which type of study has not been seen in the literature before.

show abstract

Section: Introductionmentioning

confidence: 99%

Deep Learning Models for Denoising ECG Signals

Arsene

Hankins

Yin

2019

2019 27th European Signal Processing Conference (EUSIPCO)

View full text Add to dashboard Cite

show abstract

“…In order to overcome this limitation, a wavelet adaptive filter is proposed in [16]. Recently, various techniques have been proposed based on wavelet transforms [17]- [20], interpolation algorithms [21], sparse signal decomposition [22], principal component analysis [23], independent component analysis [24], and empirical mode decomposition (EMD) [25] method. EMD is computationally very demanding in comparison to the other techniques [7].…”

Section: Introductionmentioning

confidence: 99%

Detection and Classification of Baseline-Wander Noise in ECG Signals Using Discrete Wavelet Transform and Decision Tree Classifier

Haider¹,

Alhussein²

2019

ELEKTRON ELEKTROTECH

View full text Add to dashboard Cite

An electrocardiogram (ECG) signal is usually contaminated with various noises, such as baseline-wander, power-line interference, and electromyogram (EMG) noise.Denoising must be performed to extract meaningful information from ECG signals for clinical detection of heart diseases. This work is focused on baseline-wander noise as it shares the same frequency spectrum as the ST segment of ECG signals. Hence, it is important to estimate the baseline-wander prior to its removal from ECG signals. This paper presents a method for classifying each segment of the ECG signal's baseline-wander as minimal, moderate or large. We use the C4.5 decision tree algorithm to model the classifier using the WEKA data-mining tool. We test the proposed method on ECG signals obtained from the MIT-BIH arrhythmia database (48 ECG recordings, each slightly longer than 30 min). We use 36 ECG recordings for training the classifier with the remaining 12 ECG recordings as the test data for classification. We partition each recording into 5 second, non-overlapping segments, which result in 361 segments for each record. The classification results show that the model classifier achieves an average sensitivity of 97.36 %, specificity of 99.50 %, and overall accuracy of 98.89 % in classifying the baseline-wander noise in ECG signals. The proposed method effectively addresses the question of identifying the minimal baselinewander segments. Moreover, the proposed framework may help in devising an algorithm for the selective filtering of moderate and large baseline-wander segments to achieve the best tradeoff between accuracy and computational cost.

show abstract

“…Moreover, the suitability of the random subspace ensemble method for fMRI classification has been investigated [23]. It has previously been shown that decision trees were successfully used for variable selection and classification in fMRI brain activities [24][25][26][27].…”

Section: Introductionmentioning

confidence: 99%

Optimized Naive‐Bayes and Decision Tree Approaches for fMRI Smoking Cessation Classification

Tahmassebi¹,

Gandomi

Schulte

et al. 2018

Complexity

View full text Add to dashboard Cite

This paper aims at developing new theory-driven biomarkers by implementing and evaluating novel techniques from restingstate scans that can be used in relapse prediction for nicotine-dependent patients and future treatment efficacy. Two classes of patients were studied. One class took the drug N-acetylcysteine and the other class took a placebo. Then, the patients underwent a double-blind smoking cessation treatment and the resting-state fMRI scans of their brains before and after treatment were recorded. The scientific research goal of this study was to interpret the fMRI connectivity maps based on machine learning algorithms to predict the patient who will relapse and the one who will not. In this regard, the feature matrix was extracted from the image slices of brain employing voxel selection schemes and data reduction algorithms. Then, the feature matrix was fed into the machine learning classifiers including optimized CART decision tree and Naive-Bayes classifier with standard and optimized implementation employing 10-fold cross-validation. Out of all the data reduction techniques and the machine learning algorithms employed, the best accuracy was obtained using the singular value decomposition along with the optimized Naive-Bayes classifier. This gave an accuracy of 93% with sensitivity-specificity of 99% which suggests that the relapse in nicotine-dependent patients can be predicted based on the resting-state fMRI images. The use of these approaches may result in clinical applications in the future.

show abstract

Independent Component Analysis and Decision Trees for ECG Holter Recording De-Noising

Cited by 32 publications

References 29 publications

Deep Learning Models for Denoising ECG Signals

Deep Learning Models for Denoising ECG Signals

Detection and Classification of Baseline-Wander Noise in ECG Signals Using Discrete Wavelet Transform and Decision Tree Classifier

Optimized Naive‐Bayes and Decision Tree Approaches for fMRI Smoking Cessation Classification

Contact Info

Product

Resources

About