Abstract | ||
---|---|---|
Phonocardiogram (PCG) or auscultation via a stethoscope forms the basis of preliminary medical screening. But PCG recorded in an uncontrolled environment is inherently noisy. In this paper we have derived novel features from the spectral domain and autocorrelation waveforms. These are used to identify the quality of a PCG recording and accepting only diagnosable quality recordings for further analysis. These features proved to be robust irrespective of variations in devices and in data collection protocols employed to ensure consistent data quality. A freely available, large, diverse, medical-grade PCG dataset was used for creating the training models. Results show that the proposed methodology yields an accuracy score of similar to 75% on our in-house PCG dataset, collected using a low-cost smartphone-based digital stethoscope. |
Year | DOI | Venue |
---|---|---|
2017 | 10.1109/EMBC.2017.8037860 | 2017 39TH ANNUAL INTERNATIONAL CONFERENCE OF THE IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY (EMBC) |
Field | DocType | Volume |
Phonocardiogram,Data collection,Stethoscope,Data quality,Computer science,Speech recognition,Auscultation,Autocorrelation | Conference | 2017 |
ISSN | Citations | PageRank |
1094-687X | 0 | 0.34 |
References | Authors | |
2 | 7 |
Name | Order | Citations | PageRank |
---|---|---|---|
Deepan Das | 1 | 0 | 2.03 |
Rohan Banerjee | 2 | 45 | 12.28 |
Anirban Dutta Choudhury | 3 | 75 | 17.66 |
Sakyajit Bhattacharya | 4 | 2 | 3.48 |
Parijat Deshpande | 5 | 11 | 4.10 |
Arpan Pal | 6 | 195 | 51.41 |
Kayapanda Mandana | 7 | 3 | 2.10 |