基于Bi-LSTM与状态约束的心音分割算法  

HEART SOUND SEGMENTATION ALGORITHM BASED ON BI-LSTM AND STATE CONSTRAINTS

作　　者：王幸之 杨宏波[2,3] 宗容 潘家华[3] 王威廉 谭贺飞[1] Wang Xingzhi;Yang Hongbo;Zong Rong;Pan Jiahua;Wang Weilian;Tan Hefei(School of Information Science and Engineering,Yunnan University,Kunming 650500,Yunnan,China;Kunming Medical University,Kunming 650500,Yunnan,China;Structural Heart Disease Center,Fuwai Cardiovascular Hospital of Yunnan Province,Kunming 650102,Yunnan,China)

机构地区：[1]云南大学信息学院,云南昆明650500 [2]昆明医科大学,云南昆明650500 [3]云南省阜外心血管病医院结构心脏病病区,云南昆明650102

出　　处：《计算机应用与软件》2024年第10期269-275,303,共8页Computer Applications and Software

基　　金：国家自然科学基金项目(81960067);云南省重大科技专项项目(2018ZF017)。

摘　　要：心音分割是进行准确心音分类的前提。针对心音分割,提出一种基于双向长短时记忆网络(Bi-LSTM)与状态约束的算法。该文通过网格法确定Bi-LSTM网络中的最佳参数,并训练出心音状态识别模型;统计Bi-LSTM预测的心音状态持续时间,并计算自相关参数;利用自相关参数和心音固有状态转移规则对预测的心音状态进行约束处理。使用五折交叉验证法在PhysioNet/CinC 2016数据集上进行测试,该算法与同类算法相比,整体性能更佳。Heart sound segmentation is a prerequisite for accurate heart sound classification.Aimed at heart sound segmentation,an algorithm based on Bi-LSTM and state constraints is proposed.The optimal parameters of Bi-LSTM network were determined by grid method,and the heart sound state recognition model was trained.The duration of the heart sound state predicted by Bi-LSTM was counted,and the autocorrelation parameters were calculated.The autocorrelation parameters and heart sound inherent state transition rules were used to constrain the predicted heart sound state.Using the five-fold cross-validation method to test on the PhysioNet/CinC2016 data set,the algorithm has better overall performance than similar algorithms.

关 键 词：心音图 心音分割 Bi-LSTM网络 状态约束 自相关 

分 类 号：TP392[自动化与计算机技术—计算机应用技术]