The Signal Extraction of Fetal Heart Rate Based on Wavelet Transform and BP Neural Network

摘要

This paper briefly introduces the collection and recognition of bio-medical signals, designs the method to collect FM signals. A detailed discussion on the system hardware, structure and functions is also given. Under LabWindows/CVI, the hardware and the driver do compatible, the hardware equipment work properly actively. The paper adopts multi threading technology for real-time analysis and makes use of latency time of CPU effectively, expedites program reflect speed, improves the program to perform efficiency. One threading is collecting data; the other threading is analyzing data. Using the method, it is broaden to analyze the signal in real-time. Wavelet transform to remove the main interference in the FM and by adding time-window to recognize with BP network; Finally the results of collecting signals and BP networks are discussed.8 pregnant women's signals of FM were collected successfully by using the sensor. The correctness rate of BP network recognition is about 83.3% by using the above measure.