2020
DOI: 10.3390/a13040075
|View full text |Cite
|
Sign up to set email alerts
|

Investigating Feature Selection and Random Forests for Inter-Patient Heartbeat Classification

Abstract: Finding an optimal combination of features and classifier is still an open problem in the development of automatic heartbeat classification systems, especially when applications that involve resource-constrained devices are considered. In this paper, a novel study of the selection of informative features and the use of a random forest classifier while following the recommendations of the Association for the Advancement of Medical Instrumentation (AAMI) and an inter-patient division of datasets is presented. Fe… Show more

Help me understand this report
View preprint versions

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
2
1

Citation Types

0
27
0

Year Published

2021
2021
2024
2024

Publication Types

Select...
7
2

Relationship

0
9

Authors

Journals

citations
Cited by 21 publications
(27 citation statements)
references
References 35 publications
(75 reference statements)
0
27
0
Order By: Relevance
“…Jose did an investigation of feature selection for heartbeat classification. He suggests that using normalized RR intervals could increase the classifier’s performance [ 25 ]. Mondejar demonstrates using several features such as RR interval, normalized RR interval, high order statistic, HBF coefficients, and wavelet transform, thus using a support vector machine (SVM) to classify each feature [ 26 ].…”
Section: Automated Heartbeats Classificationmentioning
confidence: 99%
See 1 more Smart Citation
“…Jose did an investigation of feature selection for heartbeat classification. He suggests that using normalized RR intervals could increase the classifier’s performance [ 25 ]. Mondejar demonstrates using several features such as RR interval, normalized RR interval, high order statistic, HBF coefficients, and wavelet transform, thus using a support vector machine (SVM) to classify each feature [ 26 ].…”
Section: Automated Heartbeats Classificationmentioning
confidence: 99%
“…Mondejar demonstrates using several features such as RR interval, normalized RR interval, high order statistic, HBF coefficients, and wavelet transform, thus using a support vector machine (SVM) to classify each feature [ 26 ]. Developing automatic heartbeat classification systems on resource-constrained devices is challenging, e.g., discovering an optimal mixture of features and classifiers [ 25 ].…”
Section: Automated Heartbeats Classificationmentioning
confidence: 99%
“…In recent studies, researchers have proved that performance of the base classifier can be improved with ensemble classification method. Jose et al, [27] proposed random forest ensemble classification technique to diagnose cardiac arrhythmia. In this model the more informative features were selected using ranking criteria on training dataset.…”
Section: Motivation Towards Ensemble Learningmentioning
confidence: 99%
“…Besides those two categories, some studies proposed their novel features, such as Sparse Representation [6] . Regarding feature selection, methods like principal component analysis [7] , Mutual Information (MI) score [8] , and genetic algorithm [9] are employed. As to model selection, mainstream models are: Support Vector Machine (SVM) [3] , [10] , Linear Discriminants (LDs) [11] , XGBoost [12] , Neural Network (NN) [13] and Random Forest (RF) [4] , [8] , which is employed in our work.…”
Section: Introductionmentioning
confidence: 99%