| Summary: | 碩士 === 大同大學 === 資訊工程學系(所) === 94 === Fetal heart rate (FHR) and uterine pressure (UP) are two of the most important statistics in antenatal examination. Safe and steady fetal monitoring signals lead to non-risky fetal status. Traditionally to achieve such a status, obstetricians check fetal heart rate (FHR) and uterine pressure (UP) signals manually, and diagnose the probable status of fetus. This manual processing of such ultrasonic data takes time and labor. To overcome this problem, we proposed a cheaper and more efficient fetal non-reassuring status monitoring system to help obstetricians detect non-reassuring fetal status. At first the weighted average is employed to estimate the fetal heartbeat baseline and uterine contraction baseline, then the system recognizes heartbeat acceleration, heartbeat deceleration, uterine construction, heartbeat noise pattern, and uterine noise pattern based on those baselines. Moreover, the monitoring system considers five types of non-reassuring fetal status. Fuzzy logic is used to analyze the signals for each non-reassuring status type and 26 fuzzy rules are used to recognize non-reassuring fetal status that triggers an alarm mechanism. When non-reassuring status is found out, the alarm mechanism will be triggered for immediate treatment. We make this monitoring system modifiable and adoptable to fit the requirements of specific patients. For verification, a signal simulator is designed. The experimental results show the accurate rate can reach 95%, when our system is examined by the obstetricians.
|
|---|
