On the Projection Matrices Influence in the Classification of Compressed Sensed ECG Signals

Fira, Monica; Goraș, Liviu; Cleju, Nicolae; Barabasa, Constantin

doi:10.14569/ijacsa.2012.030823

Cited by 5 publications

(4 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Therefore, it is necessary to classify the heartbeats. One option is to use a KNN classifier or any other classifier trained with various compressed beats [15,17]. Another option for classifying the heartbeats is a first reconstruction with the mega-dictionary on the upper branch of Figure 3 and the analysis of alpha coefficients corresponding to the mega-dictionary, i.e., the pathological class associated with the heartbeats is the same as the class in which the atom in the mega-dictionary with the highest coefficient belongs at reconstruction with the BP algorithm.…”

Section: Acceptance Of the Compression Methodsmentioning

confidence: 99%

“…Many of the papers that address CS focus on how to build specific dictionaries for signal reconstruction [13][14][15][16][17][18][19][20][21][22][23][24][25][26]. In the case of the ECG signal, due to its particularities, namely, the quasi-periodicity of the P, Q, R and S waves and the preservation of their shapes, many of the methods proposed in the literature focus on the advantages offered by these features specific to the ECG signal [27][28][29][30][31][32][33][34][35][36][37].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A Study on Dictionary Selection in Compressive Sensing for ECG Signals Compression and Classification

2022

Self Cite

View full text Add to dashboard Cite

The paper proposes a comparative analysis of the projection matrices and dictionaries used for compressive sensing (CS) of electrocardiographic signals (ECG), highlighting the compromises between the complexity of preprocessing and the accuracy of reconstruction. Starting from the basic notions of CS theory, this paper proposes the construction of dictionaries (constructed directly by cardiac patterns with R-waves, centered or not-centered) specific to the application and the results of their testing. Several types of projection matrices are also analyzed and discussed. The reconstructed signals are analyzed quantitatively and qualitatively by standard distortion measures and by the classification of the reconstructed signals. We used a k-nearest neighbors (KNN) classifier to evaluate the reconstructed models. The KNN module was trained with the models from the mega-dictionary used in the classification block and tested with the models reconstructed with class-specific dictionaries. In addition to the KNN classifier, a neural network was used to test the reconstructed signals. The neural network was a multilayer perceptron (MLP). Moreover, the results are compared with those obtained with other compression methods, and ours proved to be superior.

show abstract

Section: Acceptance Of the Compression Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

A Study on Dictionary Selection in Compressive Sensing for ECG Signals Compression and Classification

2022

Self Cite

View full text Add to dashboard Cite

show abstract

“…Fira et al [14] investigaron los resultados de la clasificación de la comprensión de señales de ECG basandose en diferentes tipos de matrices de proyección. Se clasifican las señales comprimidas usando KNN, se analiza respecto a las matrices de proyección y a los resultádos obtenidos.…”

Section: Estado Del Arteunclassified

Algoritmos genéticos aplicados a la optimización de características en la clasificación de arritmias cardiacas utilizando los clasificadores KNN y naive Bayes

Padilla-Navarro¹,

Gonzalez-Reyna²,

Aguilera-González³

et al. 2017

RCS

View full text Add to dashboard Cite

Resumen. Muchas muertes en el mundo suceden a consecuencia de enfermedades cardiovasculares. El método propuesto combina metaheuristícas-Algoritmos Genéticos (AG)-, y los clasificadores KNN y Naive Bayes. Las pruebas se realizaron a través de una base de datos del Massachusetts Institute of Technology-Beth Israel Hospital (MIT-BIH) [1]. Las metaheurísticas se implementan para mejorar el rendimiento de los clasificadores. Los resultados experimentales demuestran que se logra hasta un 94 % de precisión en la clasificación.

show abstract

“…Therefore there is a need for classification of the compressed cardiac beats. One solution is to use a K-NN classifier, trained with a set of compressed cardiac beats [15,17]. Another option would be to attempt an initial reconstruction with universal mega-dictionary, consider the class of the most significant atom used in the reconstruction, and subsequently perform a final reconstruction using the dictionary of that particular class only [16].…”

Section: B Cardiac Patterns Compressed Sensing -Cpcsmentioning

confidence: 99%

On projection matrices and dictionaries in ECG compressive sensing - A comparative study

Fira¹,

Goraș

2014

12th Symposium on Neural Network Applications in Electrical Engineering (NEUREL)

Self Cite

View full text Add to dashboard Cite

In this communication we propose and discuss comparatively several techniques for ECG signal compression inspired from the fundamentals of compressed sensing (CS) theory, focusing on acquisition techniques, projection matrices and reconstruction dictionaries and on the effects of the preprocessing involved. Essentially, we investigate and discuss two approaches. The first approach for ECG signal compression relies on the direct CS acquisition of the signal with no preprocessing of the waveforms before taking the projections, neither for the construction of the dictionaries. This "genuine" CS we will call patient specific classical compressed sensing (PSCCS) since the dictionary is built from patient initial recordings. The second approach implements a specific preprocessing stage designed to enhance sparsity and improve recoverability, based on segmenting the signal into single heart beats (also known as cardiac patterns) -denoted further as cardiac patterns compressed sensing -(CPCS)since in this case the acquired signals and the dictionary atoms are preprocessed segmented cardiac beats without or with centering of the R wave.

show abstract

On the Projection Matrices Influence in the Classification of Compressed Sensed ECG Signals

Cited by 5 publications

References 10 publications

A Study on Dictionary Selection in Compressive Sensing for ECG Signals Compression and Classification

A Study on Dictionary Selection in Compressive Sensing for ECG Signals Compression and Classification

Algoritmos genéticos aplicados a la optimización de características en la clasificación de arritmias cardiacas utilizando los clasificadores KNN y naive Bayes

On projection matrices and dictionaries in ECG compressive sensing - A comparative study

Contact Info

Product

Resources

About