Electrocardio recognition system and method based on electrocardio lead rule and residual neural network

• Main Authors: WANG CONG, XU ZHANFEI, CHI XIAOQING, SUN QINGHUA
• Format: Patent
• Language: Chinese; English
• Published: 05.08.2022
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; DIAGNOSIS; HUMAN NECESSITIES; HYGIENE; IDENTIFICATION; MEDICAL OR VETERINARY SCIENCE; PHYSICS; SURGERY

The invention discloses an electrocardio recognition system and method based on an electrocardio lead rule and a residual neural network, and the system comprises a data collection module which is used for obtaining a twelve-lead electrocardio signal; the data division module is used for grouping the twelve-lead electrocardiosignals according to the relation between the electrocardiographic lead rule and the heart anatomical position to obtain four groups of electrocardiosignals; the electrocardio recognition module is used for recognizing each group of electrocardio signals through a trained residual neural network to obtain an electrocardio signal recognition result and a position positioning result, the trained residual neural network comprises four residual network modules, each group of electrocardio signals are input into the independent residual network module, and the position positioning result is obtained. Acquiring feature vectors of each group of electrocardiosignals, combining the feature vectors