Fetal heart rate signal data enhancement method and device based on generative adversarial network

• Main Authors: ZHAO ZHIDONG, ZHANG XIAOHONG, DENG YANJUN, ZHOU ZHIXIN, ZHANG YEFEI
• Format: Patent
• Language: Chinese; English
• Published: 15.03.2022
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; DIAGNOSIS; HANDLING RECORD CARRIERS; HUMAN NECESSITIES; HYGIENE; IDENTIFICATION; MEDICAL OR VETERINARY SCIENCE; PHYSICS; PRESENTATION OF DATA; RECOGNITION OF DATA; RECORD CARRIERS; SURGERY

The invention discloses a fetal heart rate signal data enhancement method and device based on a generative adversarial network. Designing a generator and a discriminator by adopting micro-stride convolution and step length convolution, and constructing a GAN model based on a deep convolutional neural network structure; a Wasserstein distance with gradient penalty is adopted to measure the distance between an actually-collected FHR sample and simulation data, and a model objective function is optimized; establishing an auxiliary classifier based on category constraint, and performing reverse updating operation on the model parameters of the GAN model by using the auxiliary classifier; the collected incomplete FHR signals, the noise data meeting standard normal distribution and the category labels of the real FHR samples serve as input of the model and are input into the optimized GAN model, simulation FHR data are generated, and data enhancement of the fetal heart rate signals is achieved. 本发明公开基于生成式对抗网络的胎心率信号