no code implementations • 1 Jan 2021 • Xinrong Hu, long wen, shushui wang, Dongpo Liang, Jian Zhuang, Yiyu Shi
Though the training data is only labeled to supervise theclassifier, the segmenter and the classifier are trained in an end-to-end manner sothat optimizing classification performance also adjusts how the abnormal beats aresegmented.