Abstract
A least‐mean‐square (lms) linear prediction algorithm has been developed to accomplish detection of fetal heart tones and thereby derive heart rate from a raw signal generated by a previously described passive acoustical sensor array. The desired heart tone signal has a characteristic signature but is of extremely low amplitude and contaminated with noise consisting of large‐amplitude maternal heart tones, abdominal sounds, body motion, and environmental sounds, and also mild 60 Hz. The predictor coefficients were derived by adaptively “training” on ideal fetal heart tones recorded from several patients. The lms algorithm detects a heart tone event when the predictor mean‐square error falls below an adaptively updated threshold level. The algorithm contains logic for correction of spurious and missed heart tones. A real‐time working system was fabricated consisting of a sensor belt, front end electronics, a TMS320C25 digital signal processing board, an 80386 PC, and a strip chart recorder. The apparatus allows performance of the fetal nonstress test (NST) in a manner similar to that conventionally accomplished via ultrasound. The acoustical system was implemented in parallel with a commercial ultrasound unit on a series of patients undergoing NSTs. The heart rate records are compared.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
