Type-2 diabetes identification from toe-photoplethysmography using Fourier decomposition method
Abstract Type-2 diabetes mellitus (DM-2) is a complicated endocrine and metabolism condition recognized as the most major non-communicable disease in the world. The complications associated with DM-2 involve cardiovascular disease, diabetic retinopathy and neuropathy. This article proposes the Fourier decomposition method for non-invasive automated type-2 diabetes detection using photoplethysmography (PPG) signals. The proposed research work comprises three major phases. In the first phase, the 5-min duration of the toe PPG signal is split into 10-s segments and decomposed into frequency subbands known as Fourier intrinsic band functions (FIBFs). Two features from each FIBF are extracted in the second phase, including kurtosis and log energy entropy. The last stage involves passing the features on to various machine learning techniques. The least-square support vector machine (radial basis function) algorithm yielded better classification results with an accuracy of 98.61%, a sensitivity of 98.96%, and a selectivity of 98.26%..
| Medienart: |
E-Artikel |
|---|
| Erscheinungsjahr: |
2023 |
|---|---|
| Erschienen: |
2023 |
| Enthalten in: |
Zur Gesamtaufnahme - volume:36 |
|---|---|
| Enthalten in: |
Neural computing & applications - 36(2023), 5 vom: 20. Nov., Seite 2429-2443 |
| Sprache: |
Englisch |
|---|
| Beteiligte Personen: |
Mishra, Bhanupriya [VerfasserIn] |
|---|
| Links: |
Volltext [lizenzpflichtig] |
|---|
| Themen: |
Fourier decomposition method |
|---|
| Anmerkungen: |
© The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2023. Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law. |
|---|
| doi: |
10.1007/s00521-023-09208-2 |
|---|
| funding: |
|
|---|---|
| Förderinstitution / Projekttitel: |
|
| PPN (Katalog-ID): |
SPR054445744 |
|---|
| LEADER | 01000naa a22002652 4500 | ||
|---|---|---|---|
| 001 | SPR054445744 | ||
| 003 | DE-627 | ||
| 005 | 20240120064806.0 | ||
| 007 | cr uuu---uuuuu | ||
| 008 | 240120s2023 xx |||||o 00| ||eng c | ||
| 024 | 7 | |a 10.1007/s00521-023-09208-2 |2 doi | |
| 035 | |a (DE-627)SPR054445744 | ||
| 035 | |a (SPR)s00521-023-09208-2-e | ||
| 040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
| 041 | |a eng | ||
| 100 | 1 | |a Mishra, Bhanupriya |e verfasserin |4 aut | |
| 245 | 1 | 0 | |a Type-2 diabetes identification from toe-photoplethysmography using Fourier decomposition method |
| 264 | 1 | |c 2023 | |
| 336 | |a Text |b txt |2 rdacontent | ||
| 337 | |a Computermedien |b c |2 rdamedia | ||
| 338 | |a Online-Ressource |b cr |2 rdacarrier | ||
| 500 | |a © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2023. Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law. | ||
| 520 | |a Abstract Type-2 diabetes mellitus (DM-2) is a complicated endocrine and metabolism condition recognized as the most major non-communicable disease in the world. The complications associated with DM-2 involve cardiovascular disease, diabetic retinopathy and neuropathy. This article proposes the Fourier decomposition method for non-invasive automated type-2 diabetes detection using photoplethysmography (PPG) signals. The proposed research work comprises three major phases. In the first phase, the 5-min duration of the toe PPG signal is split into 10-s segments and decomposed into frequency subbands known as Fourier intrinsic band functions (FIBFs). Two features from each FIBF are extracted in the second phase, including kurtosis and log energy entropy. The last stage involves passing the features on to various machine learning techniques. The least-square support vector machine (radial basis function) algorithm yielded better classification results with an accuracy of 98.61%, a sensitivity of 98.96%, and a selectivity of 98.26%. | ||
| 650 | 4 | |a Photoplethysmography |7 (dpeaa)DE-He213 | |
| 650 | 4 | |a Fourier decomposition method |7 (dpeaa)DE-He213 | |
| 650 | 4 | |a Type-2 diabetes |7 (dpeaa)DE-He213 | |
| 650 | 4 | |a Fourier intrinsic band functions |7 (dpeaa)DE-He213 | |
| 650 | 4 | |a Machine learning models |7 (dpeaa)DE-He213 | |
| 700 | 1 | |a Nirala, Neelamshobha |4 aut | |
| 700 | 1 | |a Singh, Bikesh Kumar |4 aut | |
| 773 | 0 | 8 | |i Enthalten in |t Neural computing & applications |d London : Springer, 1993 |g 36(2023), 5 vom: 20. Nov., Seite 2429-2443 |w (DE-627)SPR006628206 |w (DE-600)1480526-1 |x 1433-3058 |7 nnns |
| 773 | 1 | 8 | |g volume:36 |g year:2023 |g number:5 |g day:20 |g month:11 |g pages:2429-2443 |
| 856 | 4 | 0 | |u https://dx.doi.org/10.1007/s00521-023-09208-2 |z lizenzpflichtig |3 Volltext |
| 912 | |a GBV_USEFLAG_A | ||
| 912 | |a GBV_SPRINGER | ||
| 951 | |a AR | ||
| 952 | |d 36 |j 2023 |e 5 |b 20 |c 11 |h 2429-2443 | ||