Classification of ECG arrhythmias based on statistical and time-frequency features
In this paper a new approach to accurately classify ECG arrhythmias through a combination of the wavelet transform and artificial neural network is presented. Three kinds of features in a very computationally efficient manner are computed as follows: 1-Joint time-frequency features (discrete wavelet...
| Main Authors: | , , , |
|---|---|
| Format: | Conference item |
| Published: |
2006
|
| _version_ | 1826257097120022528 |
|---|---|
| author | Kadbi, M Hashemi, J Mohseni, H Maghsoudi, A |
| author_facet | Kadbi, M Hashemi, J Mohseni, H Maghsoudi, A |
| author_sort | Kadbi, M |
| collection | OXFORD |
| description | In this paper a new approach to accurately classify ECG arrhythmias through a combination of the wavelet transform and artificial neural network is presented. Three kinds of features in a very computationally efficient manner are computed as follows: 1-Joint time-frequency features (discrete wavelet transform coefficients). 2-Time domain features (R-R intervals). 3-Statistical feature (form factor). Using these features, the limitations of other methods in classifying multiple kinds of arrhythmia with high accuracy for all of them at once are overcome. Finally, a cascade classifier including two ANNs has been designed. Considering the whole MIT-BIH arrhythmia database, 10 kinds of arrhythmia were classified. The overall accuracy of classification of the proposed approach is above 90%. |
| first_indexed | 2024-03-06T18:12:43Z |
| format | Conference item |
| id | oxford-uuid:03903fc0-f4ee-4b8c-aefb-9e70540535c4 |
| institution | University of Oxford |
| last_indexed | 2024-03-06T18:12:43Z |
| publishDate | 2006 |
| record_format | dspace |
| spelling | oxford-uuid:03903fc0-f4ee-4b8c-aefb-9e70540535c42022-03-26T08:47:01ZClassification of ECG arrhythmias based on statistical and time-frequency featuresConference itemhttp://purl.org/coar/resource_type/c_5794uuid:03903fc0-f4ee-4b8c-aefb-9e70540535c4Symplectic Elements at Oxford2006Kadbi, MHashemi, JMohseni, HMaghsoudi, AIn this paper a new approach to accurately classify ECG arrhythmias through a combination of the wavelet transform and artificial neural network is presented. Three kinds of features in a very computationally efficient manner are computed as follows: 1-Joint time-frequency features (discrete wavelet transform coefficients). 2-Time domain features (R-R intervals). 3-Statistical feature (form factor). Using these features, the limitations of other methods in classifying multiple kinds of arrhythmia with high accuracy for all of them at once are overcome. Finally, a cascade classifier including two ANNs has been designed. Considering the whole MIT-BIH arrhythmia database, 10 kinds of arrhythmia were classified. The overall accuracy of classification of the proposed approach is above 90%. |
| spellingShingle | Kadbi, M Hashemi, J Mohseni, H Maghsoudi, A Classification of ECG arrhythmias based on statistical and time-frequency features |
| title | Classification of ECG arrhythmias based on statistical and time-frequency features |
| title_full | Classification of ECG arrhythmias based on statistical and time-frequency features |
| title_fullStr | Classification of ECG arrhythmias based on statistical and time-frequency features |
| title_full_unstemmed | Classification of ECG arrhythmias based on statistical and time-frequency features |
| title_short | Classification of ECG arrhythmias based on statistical and time-frequency features |
| title_sort | classification of ecg arrhythmias based on statistical and time frequency features |
| work_keys_str_mv | AT kadbim classificationofecgarrhythmiasbasedonstatisticalandtimefrequencyfeatures AT hashemij classificationofecgarrhythmiasbasedonstatisticalandtimefrequencyfeatures AT mohsenih classificationofecgarrhythmiasbasedonstatisticalandtimefrequencyfeatures AT maghsoudia classificationofecgarrhythmiasbasedonstatisticalandtimefrequencyfeatures |