Clustering ECG complexes using Hermite functions and self-organizing maps

By M. Lagerholm, C. Peterson, G. Braccini, L. Edenbrandt, L. Sörnmo. IEEE Transactions on Biomedical Engineering, 2000

595 citations recorded by the source corpus.

Subfields: Cardiology and Cardiovascular Medicine, Control and Systems Engineering

View Paper: https://www.semanticscholar.org/paper/dca4c3b778ca76f6c4167e4e50cd7e86dd51dc41

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Cardiology and Cardiovascular Medicine

In Control and Systems Engineering

Citations in the corpus

Heartbeat Classification Using Morphological and Dynamic Features of ECG Signals (2012, methodology): “These works explored the characterization of heartbeats using a variety of features, including Hermite coefficients [6], [9], [13], high-order statistics features [9], [17], wavelet features [11], [14], waveform shape features [8], [10], [12], [15]– [17], etc.”
Heartbeat Classification Using Feature Selection Driven by Database Generalization Criteria (2011, methodology): “Several classifiers were adopted in the reviewed papers, from simple linear discriminant functions based on the Gaussian assumption of the data [4], [8] to more elaborated ones, as artificial neural networks (ANN’s), self-organizing maps (SOM), and learning vector quantization (LVQ) among others [2]”
ECG-based heartbeat classification for arrhythmia detection: A survey (2016, background): “[138] 16 HBF, SOM clustering Acc = 98% Dokur and Olmez [98] 10 Fourier, Wavelet + FSDP MLP, RCE, Acc = 96% Novel hybrid NN Osowski and Linh [88] 6 HOSC fuzzy NN Acc = 96% Tsipouras et al.”
Support vector machine-based expert system for reliable heartbeat recognition (2004, methodology): “[5] have presented the most complete recognition system among all beat types existed in the MIT BIH AD and demonstrated the most integrated recognition procedure.”
Automated Atrial Fibrillation Detection using a Hybrid CNN-LSTM Network on Imbalanced ECG Datasets (2021, background): “As of now, a considerable number of studies has been carried out regarding the automated classification of heart arrhythmias by using wavelets [33], filter banks [34], support vector machines (SVM) [35], and other ML techniques [36,37].”
Block-Based Neural Networks for Personalized ECG Signal Classification (2007, methodology): “The functions are the Hermite polynomials [9], [17].”
A Patient-Adapting Heartbeat Classifier Using ECG Morphology and Heartbeat Interval Features (2006, methodology): “Hu et al. [11] achieved a 62.2% accuracy in separating VEBs from non-VEBs, and we [13] achieved a 97.4% accuracy for the same task.”
LSTM-Based ECG Classification for Continuous Monitoring on Personal Wearable Devices (2018, methodology): “Many previous ECG classification algorithms are mainly focused on signal processing techniques including extraction of morphological features [7], frequency domain analysis [8], Hermite function decomposition [9], wavelet transform [10], [11], support vector machines [12] and hidden Markov models [1”
Optimization of ECG Classification by Means of Feature Selection (2011, background): “…the ECG like amplitudes and peak widths [9], [32], features based on different transforms, e.g., wavelet transform (WT) [15], [33], [34], principal component analysis [26], [35] and Hermite functions [23], [29], [31], as well as statistical features, e.g., variances [14], [36], have been proposed.”
Automatic classification of heartbeats using ECG morphology and heartbeat interval features (2004, methodology): “The AAMI standards are adopted in this study and our results have been compared to those of [11] and [ 12 ].”
The principles of software QRS detection (2002, background): “, ECG signal enhancement [15, 17, 23, 28, 90, 99] or pattern classification [8, 26, 31, 40, 62, 63, 70, 71, 72, 108, 113, 119].”