Classification of photoplethysmographic signals using support vector machines for vascular risk assessment

Rohan Baid, Niranjana Krupa, Muhammad A M Ali

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

    3 Citations (Scopus)

    Abstract

    Cardiovascular diseases have registered a high rate of morbidity and mortality in the world, therefore the assessment of cardiovascular risk in human beings is of prime importance. In this paper Photoplethysmographic (PPG) signals recorded from 60 subjects have been classified as 'normal' or 'at risk'. In this process, we have used an Auto-Regressive exogenous input (ARX) linear parametric model for extracting features that represent the circulatory system and a support vector machine (SVM) for classifying the signals based on the four data segment selection policies; best fit, three best fit, ten best fit and average best fit. The classification method employed in this work appears to be novel. According to the sensitivity and the specificity obtained (84.615% and 92.31%, respectively), the average best fit policy was chosen as the best policy for the classification of PPG signals.

    Original languageEnglish
    Title of host publicationProceedings of the IASTED International Conference on Biomedical Engineering, BioMed 2013
    Pages183-187
    Number of pages5
    DOIs
    Publication statusPublished - 2013
    Event10th IASTED International Conference on Biomedical Engineering, BioMed 2013 - Innsbruck
    Duration: 13 Feb 201315 Feb 2013

    Other

    Other10th IASTED International Conference on Biomedical Engineering, BioMed 2013
    CityInnsbruck
    Period13/2/1315/2/13

    Fingerprint

    Risk assessment
    Support vector machines

    Keywords

    • ARX
    • Cardiovascular diseases
    • Linear Parametric model
    • PPG
    • Support vector machine

    ASJC Scopus subject areas

    • Biomedical Engineering

    Cite this

    Baid, R., Krupa, N., & Ali, M. A. M. (2013). Classification of photoplethysmographic signals using support vector machines for vascular risk assessment. In Proceedings of the IASTED International Conference on Biomedical Engineering, BioMed 2013 (pp. 183-187) https://doi.org/10.2316/P.2013.791-144

    Classification of photoplethysmographic signals using support vector machines for vascular risk assessment. / Baid, Rohan; Krupa, Niranjana; Ali, Muhammad A M.

    Proceedings of the IASTED International Conference on Biomedical Engineering, BioMed 2013. 2013. p. 183-187.

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

    Baid, R, Krupa, N & Ali, MAM 2013, Classification of photoplethysmographic signals using support vector machines for vascular risk assessment. in Proceedings of the IASTED International Conference on Biomedical Engineering, BioMed 2013. pp. 183-187, 10th IASTED International Conference on Biomedical Engineering, BioMed 2013, Innsbruck, 13/2/13. https://doi.org/10.2316/P.2013.791-144
    Baid R, Krupa N, Ali MAM. Classification of photoplethysmographic signals using support vector machines for vascular risk assessment. In Proceedings of the IASTED International Conference on Biomedical Engineering, BioMed 2013. 2013. p. 183-187 https://doi.org/10.2316/P.2013.791-144
    Baid, Rohan ; Krupa, Niranjana ; Ali, Muhammad A M. / Classification of photoplethysmographic signals using support vector machines for vascular risk assessment. Proceedings of the IASTED International Conference on Biomedical Engineering, BioMed 2013. 2013. pp. 183-187
    @inproceedings{ba7dfd2313694dc09ce9862969b98d97,
    title = "Classification of photoplethysmographic signals using support vector machines for vascular risk assessment",
    abstract = "Cardiovascular diseases have registered a high rate of morbidity and mortality in the world, therefore the assessment of cardiovascular risk in human beings is of prime importance. In this paper Photoplethysmographic (PPG) signals recorded from 60 subjects have been classified as 'normal' or 'at risk'. In this process, we have used an Auto-Regressive exogenous input (ARX) linear parametric model for extracting features that represent the circulatory system and a support vector machine (SVM) for classifying the signals based on the four data segment selection policies; best fit, three best fit, ten best fit and average best fit. The classification method employed in this work appears to be novel. According to the sensitivity and the specificity obtained (84.615{\%} and 92.31{\%}, respectively), the average best fit policy was chosen as the best policy for the classification of PPG signals.",
    keywords = "ARX, Cardiovascular diseases, Linear Parametric model, PPG, Support vector machine",
    author = "Rohan Baid and Niranjana Krupa and Ali, {Muhammad A M}",
    year = "2013",
    doi = "10.2316/P.2013.791-144",
    language = "English",
    isbn = "9780889869530",
    pages = "183--187",
    booktitle = "Proceedings of the IASTED International Conference on Biomedical Engineering, BioMed 2013",

    }

    TY - GEN

    T1 - Classification of photoplethysmographic signals using support vector machines for vascular risk assessment

    AU - Baid, Rohan

    AU - Krupa, Niranjana

    AU - Ali, Muhammad A M

    PY - 2013

    Y1 - 2013

    N2 - Cardiovascular diseases have registered a high rate of morbidity and mortality in the world, therefore the assessment of cardiovascular risk in human beings is of prime importance. In this paper Photoplethysmographic (PPG) signals recorded from 60 subjects have been classified as 'normal' or 'at risk'. In this process, we have used an Auto-Regressive exogenous input (ARX) linear parametric model for extracting features that represent the circulatory system and a support vector machine (SVM) for classifying the signals based on the four data segment selection policies; best fit, three best fit, ten best fit and average best fit. The classification method employed in this work appears to be novel. According to the sensitivity and the specificity obtained (84.615% and 92.31%, respectively), the average best fit policy was chosen as the best policy for the classification of PPG signals.

    AB - Cardiovascular diseases have registered a high rate of morbidity and mortality in the world, therefore the assessment of cardiovascular risk in human beings is of prime importance. In this paper Photoplethysmographic (PPG) signals recorded from 60 subjects have been classified as 'normal' or 'at risk'. In this process, we have used an Auto-Regressive exogenous input (ARX) linear parametric model for extracting features that represent the circulatory system and a support vector machine (SVM) for classifying the signals based on the four data segment selection policies; best fit, three best fit, ten best fit and average best fit. The classification method employed in this work appears to be novel. According to the sensitivity and the specificity obtained (84.615% and 92.31%, respectively), the average best fit policy was chosen as the best policy for the classification of PPG signals.

    KW - ARX

    KW - Cardiovascular diseases

    KW - Linear Parametric model

    KW - PPG

    KW - Support vector machine

    UR - http://www.scopus.com/inward/record.url?scp=84883850582&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=84883850582&partnerID=8YFLogxK

    U2 - 10.2316/P.2013.791-144

    DO - 10.2316/P.2013.791-144

    M3 - Conference contribution

    SN - 9780889869530

    SP - 183

    EP - 187

    BT - Proceedings of the IASTED International Conference on Biomedical Engineering, BioMed 2013

    ER -