Robust heart sound segmentation based on spectral change detection and genetic algorithms

Alonso-Arévalo, Miguel A.; Cruz-Gutiérrez, Alejandro; Ibarra-Hernández, Roilhi F.; García–Canseco, Eloísa; Conte-Galvan, Roberto

doi:10.1016/j.bspc.2020.102208

Cited by 20 publications

(17 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The inspiration to undertake research on evolutionary computation (EC) [ 29 ] was the imitation of nature in its mechanism of natural selection, inheritance and functioning. Genetic algorithms (GAs) [ 31 ] are a part of evolutionary computation techniques, which have been used with success in fields such as the vehicle routing problem [ 32 ], feature selection [ 33 ], optimization [ 34 ], heart sound segmentation [ 35 ] or traveling salesman problem [ 36 ].…”

Section: State Of the Artmentioning

confidence: 99%

Hyperspectral Classification of Blood-Like Substances Using Machine Learning Methods Combined with Genetic Algorithms in Transductive and Inductive Scenarios

Palka

Książek

Pławiak

et al. 2021

Sensors

View full text Add to dashboard Cite

This study is focused on applying genetic algorithms (GAs) to model and band selection in hyperspectral image classification. We use a forensic-inspired data set of seven hyperspectral images with blood and five visually similar substances to test GA-optimised classifiers in two scenarios: when the training and test data come from the same image and when they come from different images, which is a more challenging task due to significant spectral differences. In our experiments, we compare GA with a classic model optimisation through a grid search. Our results show that GA-based model optimisation can reduce the number of bands and create an accurate classifier that outperforms the GS-based reference models, provided that, during model optimisation, it has access to examples similar to test data. We illustrate this with experiments highlighting the importance of a validation set.

show abstract

Section: State Of the Artmentioning

confidence: 99%

Hyperspectral Classification of Blood-Like Substances Using Machine Learning Methods Combined with Genetic Algorithms in Transductive and Inductive Scenarios

Palka

Książek

Pławiak

et al. 2021

Sensors

View full text Add to dashboard Cite

show abstract

“…Miguel et al developed a method for separating PCG signals into silences and basic heart sounds. The segments were then joined with a simple genetic technique called differential evolution, and the results indicate a mean F1 score of 98.5% and 93.6% [ 25 ].…”

Section: Introductionmentioning

confidence: 99%

Diagnosis of cardiac abnormalities based on phonocardiogram using a novel fuzzy matching feature extraction method

Yang

Xiang

et al. 2022

BMC Med Inform Decis Mak

View full text Add to dashboard Cite

Background The diagnosis of cardiac abnormalities based on heart sound signal is a research hotspot in recent years. The early diagnosis of cardiac abnormalities has a crucial significance for the treatment of heart diseases. Methods For the sake of achieving more practical clinical applications of automatic recognition of cardiac abnormalities, here we proposed a novel fuzzy matching feature extraction method. First of all, a group of Gaussian wavelets are selected and then optimized based on a template signal. Convolutional features of test signal and the template signal are then computed. Matching degree and matching energy features between template signal and test signal in time domain and frequency domain are then extracted. To test performance of proposed feature extraction method, machine learning algorithms such as K-nearest neighbor, support vector machine, random forest and multilayer perceptron with grid search parameter optimization are constructed to recognize heart disease using the extracted features based on phonocardiogram signals. Results As a result, we found that the best classification accuracy of random forest reaches 96.5% under tenfold cross validation using the features extracted by the proposed method. Further, Mel-Frequency Cepstral Coefficients of phonocardiogram signals combing with features extracted by our algorithm are evaluated. Accuracy, sensitivity and specificity of integrated features reaches 99.0%, 99.4% and 99.7% respectively when using support vector machine, which achieves the best performance among all reported algorithms based on the same dataset. On several common features, we used independent sample t-tests. The results revealed that there are significant differences (p < 0.05) between 5 categories. Conclusion It can be concluded that our proposed fuzzy matching feature extraction method is a practical approach to extract powerful and interpretable features from one-dimensional signals for heart sound diagnostics and other pattern recognition task.

show abstract

“…The inspiration to undertake research on evolutionary computation (EC) [2] was the imitation of nature in its mechanism of natural selection, inheritance and functioning. Genetic algorithms (GA) [40] are a part of evolutionary computation techniques, used with success in the field such as vehicle routing problem [27], feature selection [46], optimization [5], heart sound segmentation [1] or traveling salesmen problem [6] Genetic algorithms are one of the leading approaches to solve optimisation problems [37]. Optimization problems are computationally complex,therefore they are often solved with heuristic methods, which make it possible to find a near-optimal solution faster.…”

Section: Evolutionary Computation and Genetic Algorithmsmentioning

confidence: 99%

“…If it is a gene responsible for a parameter of the support vector machine, its value is replaced by the new value of the given parameter from the set range (acceptable values are shown in table 1). If we draw a gene that represents a feature, its value is replaced by the opposite one e.g from 'not selected' (0) to 'selected' (1). Values of our genetic algorithm parameters are presented in Tab.…”

Section: Model Selection With Genetic Algorithmsmentioning

confidence: 99%

Hyperspectral classification of blood-like substances using machine learning methods combined with genetic algorithms in transductive and inductive scenarios

Palka¹,

Książek²,

Pławiak³

et al. 2020

Preprint

View full text Add to dashboard Cite

This study is focused on applying genetic algorithms (GA) to model and band selection in hyperspectral image classification. We use a forensic-inspired data set of seven hyperspectral images with blood and five visually similar substances to test GA-optimised classifiers in two scenarios: when the training and test data come from the same image and when they come from different images, which is a more challenging task due to significant spectra differences. In our experiments we compare GA with a classic model optimisation through grid search. Our results show that GA-based model optimisation can reduce the number of bands and create an accurate classifier that outperforms the GS-based reference models, provided that during model optimisation it has access to examples similar to test data. We illustrate this with experiment highlighting the importance of a validation set.

show abstract

Robust heart sound segmentation based on spectral change detection and genetic algorithms

Cited by 20 publications

References 26 publications

Hyperspectral Classification of Blood-Like Substances Using Machine Learning Methods Combined with Genetic Algorithms in Transductive and Inductive Scenarios

Hyperspectral Classification of Blood-Like Substances Using Machine Learning Methods Combined with Genetic Algorithms in Transductive and Inductive Scenarios

Diagnosis of cardiac abnormalities based on phonocardiogram using a novel fuzzy matching feature extraction method

Hyperspectral classification of blood-like substances using machine learning methods combined with genetic algorithms in transductive and inductive scenarios

Contact Info

Product

Resources

About