Incorporating Knowledge Base for Deep Classification of Fetal Heart Rate.

In recent years, remote fetal monitoring has become more and more popular, and it has also brought many challenges. Fetal heart rate records are generally recorded by pregnant women using a fetal monitor at home. Due to the improper operation of the pregnant woman and the surrounding noise, this makes it difficult for the doctor to give an accurate diagnosis. However, the existing methods are difficult to perform well in an environment with noisy data and unbalanced data. To solve the shortcomings of existing methods, we design a novel framework, classification fetal heart rate based on convolutional neural network incorporating knowledge base. In particular, we built a knowledge base for the task of fetal heart rate classification, which can solve the problem of noise and imbalance in the data. To verify the effectiveness of our proposed framework, we conduct extensive experiments on a real-world dataset. The experimental results show that the performance of our framework is better than other methods.