Clustering ECG complexes using Hermite functions and self-organizing maps
(2000) In IEEE Transactions on Biomedical Engineering 47(7). p.838-848- Abstract
- An integrated method for clustering of QRS complexes is presented which includes basis function representation and self-organizing neural networks (NN's). Each QRS complex is decomposed into Hermite basis functions and the resulting coefficients and width parameter are used to represent the complex. By means of this representation, unsupervised self-organizing NNs are employed to cluster the data into 25 groups. Using the MIT-BIH arrhythmia database, the resulting clusters are found to exhibit a very low degree of misclassification (1.5%). The integrated method outperforms, on the MIT-BIH database, both a published supervised learning method as well as a conventional template cross-correlation clustering method.
Please use this url to cite or link to this publication:
https://lup.lub.lu.se/record/1746323
- author
- Lagerholm, M ; Peterson, Carsten LU ; Braccini, G. ; Edenbrandt, Lars LU and Sörnmo, Leif LU
- organization
- publishing date
- 2000
- type
- Contribution to journal
- publication status
- published
- subject
- in
- IEEE Transactions on Biomedical Engineering
- volume
- 47
- issue
- 7
- pages
- 838 - 848
- publisher
- IEEE - Institute of Electrical and Electronics Engineers Inc.
- external identifiers
-
- scopus:0033918208
- ISSN
- 1558-2531
- DOI
- 10.1109/10.846677
- language
- English
- LU publication?
- yes
- id
- d005115c-7ca6-4360-9683-e729f5f5957f (old id 1746323)
- date added to LUP
- 2016-04-04 09:43:39
- date last changed
- 2024-04-13 10:32:41
@article{d005115c-7ca6-4360-9683-e729f5f5957f, abstract = {{An integrated method for clustering of QRS complexes is presented which includes basis function representation and self-organizing neural networks (NN's). Each QRS complex is decomposed into Hermite basis functions and the resulting coefficients and width parameter are used to represent the complex. By means of this representation, unsupervised self-organizing NNs are employed to cluster the data into 25 groups. Using the MIT-BIH arrhythmia database, the resulting clusters are found to exhibit a very low degree of misclassification (1.5%). The integrated method outperforms, on the MIT-BIH database, both a published supervised learning method as well as a conventional template cross-correlation clustering method.}}, author = {{Lagerholm, M and Peterson, Carsten and Braccini, G. and Edenbrandt, Lars and Sörnmo, Leif}}, issn = {{1558-2531}}, language = {{eng}}, number = {{7}}, pages = {{838--848}}, publisher = {{IEEE - Institute of Electrical and Electronics Engineers Inc.}}, series = {{IEEE Transactions on Biomedical Engineering}}, title = {{Clustering ECG complexes using Hermite functions and self-organizing maps}}, url = {{http://dx.doi.org/10.1109/10.846677}}, doi = {{10.1109/10.846677}}, volume = {{47}}, year = {{2000}}, }