An e-Textile-based wearable spirometer and its adaptability for context changes depending on sweat and meal

Daily continuous spirometry is expected to detect the initial symptoms of lung disease that appear in daily-life situations. Spiro Vest is an e-Textile-based wearable spi-rometer that is suitable for daily continuous spirometry because it does not require uncomfortable attachments, such as the nose-pinching clips and mouthpieces used by typical medical spirometers. However, several adaptation issues for changes in daily context must still be resolved. This paper discusses two of these remaining issues: sweat and diet. The context changes due to sweat and diet significantly increase the estimation errors of SpiroVest; however, we succeeded in reducing these errors with a simple adjustment based on representative values. In our experiments, the increase in estimation errors after context changes due to sweat and diet were reduced from 21.29 ± 15.81 (L) to 0.71 ± 0.23 (L) and from 0.75 ± 0.38 (L) to 0.30 ± 0.03 (L).