Automatic Bowel Sound Detection under Cloth Rubbing Noise

摘要

Conventionally, bowel sound is considered an important index for understanding a patient’s intestinal condition. At present, bowel sound is determined by a doctor’s auscultation with a stethoscope. The auscultation is based on experience and intuition, and is short-term. Therefore, research has been conducted to enable a long-term and quantitative measurement of bowel sound. However, these studies measured bowel sound for bedridden patients only, and no study has yet measured them for moving patients. To measure bowel sound even for a moving patient, a portable bowel sound detection device needs to be developed. For this purpose, a new sensor that is smaller than the conventional stationary prototype, with the addition of noise resistance, is developed in this study. The noise resistance is added through signal processing conducted on a computer. This study focuses on the rubbing sound of clothes, which is the most influential noise generated when moving. In addition, a notch filter, wavelet filter, and low-pass filter are used to extract only the cloth rubbing and bowel sounds. In addition, the difference in the number of peaks and the enhancement of the bowel sound spectrum characteristics are used to distinguish between the two sounds. As a result, automatically, only the bowel sound is detected.