Name
Title | ||
|---|---|---|
Unsupervised learning applied in MER and ECG signals through Gaussians mixtures with the Expectation-Maximization algorithm and Variational Bayesian Inference. |
Abstract | ||
|---|---|---|
Automatic identification of biosignals is one of the more studied fields in biomedical engineering. In this paper, we present an approach for the unsupervised recognition of biomedical signals: Microelectrode Recordings (MER) and Electrocardiography signals (ECG). The unsupervised learning is based in classic and bayesian estimation theory. We employ gaussian mixtures models with two estimation methods. The first is derived from the frequentist estimation theory, known as Expectation-Maximization (EM) algorithm. The second is obtained from bayesian probabilistic estimation and it is called variational inference. In this framework, both methods are used for parameters estimation of Gaussian mixtures. The mixtures models are used for unsupervised pattern classification, through the responsibility matrix. The algorithms are applied in two real databases acquired in Parkinson's disease surgeries and electrocardiograms. The results show an accuracy over 85% in MER and 90% in ECG for identification of two classes. These results are statistically equal or even better than parametric (Naive Bayes) and nonparametric classifiers (K-nearest neighbor). |
Year | DOI | Venue |
|---|---|---|
2013 | 10.1109/EMBC.2013.6610503 | EMBC |
Keywords | Field | DocType |
gaussian mixture model,electrocardiography,mer identification accuracy,expectation-maximisation algorithm,naive bayes classifier,gaussian processes,expectation-maximization algorithm,diseases,parkinson disease electrocardiogram database,unsupervised biomedical signal recognition,neurophysiology,bayesian estimation theory,biomedical electrodes,ecg signal,classic estimation theory,matrix algebra,biomedical engineering,medical signal processing,unsupervised pattern classification,k-nearest neighbor classifier,frequentist estimation theory,electrocardiography signal,parkinson disease surgery database,estimation theory,bayes methods,bayesian probabilistic estimation,signal classification,gaussian mixture parameters estimation,automatic biosignal identification,microelectrode recording,microelectrodes,nonparametric classifier,ecg identification accuracy,variational bayesian inference,responsibility matrix,unsupervised learning,mer signal,databases,accuracy,expectation maximization algorithm,feature extraction,clustering algorithms | Frequentist inference,Bayesian inference,Pattern recognition,Naive Bayes classifier,Computer science,Wake-sleep algorithm,Unsupervised learning,Gaussian process,Artificial intelligence,Bayes estimator,Bayesian probability | Conference |
Volume | ISSN | Citations |
2013 | 1557-170X | 0 |
PageRank | References | Authors |
0.34 | 6 | 3 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Hernán Darío Vargas Cardona | 1 | 4 | 3.25 |
| Álvaro Ángel Orozco | 2 | 0 | 0.68 |
| Mauricio A. Álvarez | 3 | 165 | 23.80 |