Dry Electrode-Based Body Fat Estimation System with Anthropometric Data for Use in a Wearable Device
The bioelectrical impedance analysis (BIA) method is widely used to predict percent body fat (PBF). However, it requires four to eight electrodes, and it takes a few minutes to accurately obtain the measurement results. In this study, we propose a faster and more accurate method that utilizes a smal...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2019-05-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/19/9/2177 |
| _version_ | 1798039026120261632 |
|---|---|
| author | Seung-Chul Shin Jinkyu Lee Soyeon Choe Hyuk In Yang Jihee Min Ki-Yong Ahn Justin Y. Jeon Hong-Goo Kang |
| author_facet | Seung-Chul Shin Jinkyu Lee Soyeon Choe Hyuk In Yang Jihee Min Ki-Yong Ahn Justin Y. Jeon Hong-Goo Kang |
| author_sort | Seung-Chul Shin |
| collection | DOAJ |
| description | The bioelectrical impedance analysis (BIA) method is widely used to predict percent body fat (PBF). However, it requires four to eight electrodes, and it takes a few minutes to accurately obtain the measurement results. In this study, we propose a faster and more accurate method that utilizes a small dry electrode-based wearable device, which predicts whole-body impedance using only upper-body impedance values. Such a small electrode-based device typically needs a long measurement time due to increased parasitic resistance, and its accuracy varies by measurement posture. To minimize these variations, we designed a sensing system that only utilizes contact with the wrist and index fingers. The measurement time was also reduced to five seconds by an effective parameter calibration network. Finally, we implemented a deep neural network-based algorithm to predict the PBF value by the measurement of the upper-body impedance and lower-body anthropometric data as auxiliary input features. The experiments were performed with 163 amateur athletes who exercised regularly. The performance of the proposed system was compared with those of two commercial systems that were designed to measure body composition using either a whole-body or upper-body impedance value. The results showed that the correlation coefficient (<inline-formula> <math display="inline"> <semantics> <msup> <mrow> <mi>r</mi> </mrow> <mn>2</mn> </msup> </semantics> </math> </inline-formula>) value was improved by about 9%, and the standard error of estimate (SEE) was reduced by 28%. |
| first_indexed | 2024-04-11T21:48:15Z |
| format | Article |
| id | doaj.art-077ecf4bcb274cf9b606d8bf4e05d4f0 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-04-11T21:48:15Z |
| publishDate | 2019-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-077ecf4bcb274cf9b606d8bf4e05d4f02022-12-22T04:01:20ZengMDPI AGSensors1424-82202019-05-01199217710.3390/s19092177s19092177Dry Electrode-Based Body Fat Estimation System with Anthropometric Data for Use in a Wearable DeviceSeung-Chul Shin0Jinkyu Lee1Soyeon Choe2Hyuk In Yang3Jihee Min4Ki-Yong Ahn5Justin Y. Jeon6Hong-Goo Kang7The Department of Electrical and Electronic Engineering, Yonsei University, Shinchon-dong, Seodaemun-gu, Seoul 03722, KoreaThe Department of Electrical and Electronic Engineering, Yonsei University, Shinchon-dong, Seodaemun-gu, Seoul 03722, KoreaThe Department of Electrical and Electronic Engineering, Yonsei University, Shinchon-dong, Seodaemun-gu, Seoul 03722, KoreaThe Department of Sport Industry Studies, Yonsei University, Shinchon-dong, Seodaemun-gu, Seoul 03722, KoreaThe Department of Sport Industry Studies, Yonsei University, Shinchon-dong, Seodaemun-gu, Seoul 03722, KoreaThe Faculty of Kinesiology, Sport, and Recreation, University of Alberta, 1-115 University Hall, 116 St. and 85 Ave., Edmonton, AB T6G 2R3, CanadaThe Department of Sport Industry Studies, Yonsei University, Shinchon-dong, Seodaemun-gu, Seoul 03722, KoreaThe Department of Electrical and Electronic Engineering, Yonsei University, Shinchon-dong, Seodaemun-gu, Seoul 03722, KoreaThe bioelectrical impedance analysis (BIA) method is widely used to predict percent body fat (PBF). However, it requires four to eight electrodes, and it takes a few minutes to accurately obtain the measurement results. In this study, we propose a faster and more accurate method that utilizes a small dry electrode-based wearable device, which predicts whole-body impedance using only upper-body impedance values. Such a small electrode-based device typically needs a long measurement time due to increased parasitic resistance, and its accuracy varies by measurement posture. To minimize these variations, we designed a sensing system that only utilizes contact with the wrist and index fingers. The measurement time was also reduced to five seconds by an effective parameter calibration network. Finally, we implemented a deep neural network-based algorithm to predict the PBF value by the measurement of the upper-body impedance and lower-body anthropometric data as auxiliary input features. The experiments were performed with 163 amateur athletes who exercised regularly. The performance of the proposed system was compared with those of two commercial systems that were designed to measure body composition using either a whole-body or upper-body impedance value. The results showed that the correlation coefficient (<inline-formula> <math display="inline"> <semantics> <msup> <mrow> <mi>r</mi> </mrow> <mn>2</mn> </msup> </semantics> </math> </inline-formula>) value was improved by about 9%, and the standard error of estimate (SEE) was reduced by 28%.https://www.mdpi.com/1424-8220/19/9/2177bioelectrical impedance analysisdeep learningpercent body fatupper-body measurementsettling value estimation |
| spellingShingle | Seung-Chul Shin Jinkyu Lee Soyeon Choe Hyuk In Yang Jihee Min Ki-Yong Ahn Justin Y. Jeon Hong-Goo Kang Dry Electrode-Based Body Fat Estimation System with Anthropometric Data for Use in a Wearable Device Sensors bioelectrical impedance analysis deep learning percent body fat upper-body measurement settling value estimation |
| title | Dry Electrode-Based Body Fat Estimation System with Anthropometric Data for Use in a Wearable Device |
| title_full | Dry Electrode-Based Body Fat Estimation System with Anthropometric Data for Use in a Wearable Device |
| title_fullStr | Dry Electrode-Based Body Fat Estimation System with Anthropometric Data for Use in a Wearable Device |
| title_full_unstemmed | Dry Electrode-Based Body Fat Estimation System with Anthropometric Data for Use in a Wearable Device |
| title_short | Dry Electrode-Based Body Fat Estimation System with Anthropometric Data for Use in a Wearable Device |
| title_sort | dry electrode based body fat estimation system with anthropometric data for use in a wearable device |
| topic | bioelectrical impedance analysis deep learning percent body fat upper-body measurement settling value estimation |
| url | https://www.mdpi.com/1424-8220/19/9/2177 |
| work_keys_str_mv | AT seungchulshin dryelectrodebasedbodyfatestimationsystemwithanthropometricdataforuseinawearabledevice AT jinkyulee dryelectrodebasedbodyfatestimationsystemwithanthropometricdataforuseinawearabledevice AT soyeonchoe dryelectrodebasedbodyfatestimationsystemwithanthropometricdataforuseinawearabledevice AT hyukinyang dryelectrodebasedbodyfatestimationsystemwithanthropometricdataforuseinawearabledevice AT jiheemin dryelectrodebasedbodyfatestimationsystemwithanthropometricdataforuseinawearabledevice AT kiyongahn dryelectrodebasedbodyfatestimationsystemwithanthropometricdataforuseinawearabledevice AT justinyjeon dryelectrodebasedbodyfatestimationsystemwithanthropometricdataforuseinawearabledevice AT honggookang dryelectrodebasedbodyfatestimationsystemwithanthropometricdataforuseinawearabledevice |