可用于移动设备的心律失常分类算法研究  

Study on Severe Arrhythmia Classification Methodology for Mobile Devices

作　　者：易铭[1,2,3] 郁磊[3] 王计平[3] 方强[3] 

机构地区：[1]中国科学院长春光学精密机械与物理研究所,吉林长春130000 [2]中国科学院大学,北京100049 [3]中国科学院苏州生物医学工程技术研究所,江苏苏州215163

出　　处：《计算机仿真》2014年第7期243-246,共4页Computer Simulation

摘　　要：在心律失常分类问题的研究中,将神经网络、支持向量机用于移动设备平台的室性心律失常分类时,针对数据量大导致的训练时间长、分类时间长的问题,提出了激活函数改进的岭回归极限学习机(Extreme Learning Machine,ELM)算法,以岭回归极限学习机为基础,对激活函数进行多种改进尝试。以训练时间和分类准确率等为性能指标,对比不同激活函数,以及多种分类算法,证明改进后的岭回归极限学习机算法能够快速、准确地针对室性心律失常进行分类,速度与准确性优于其它几种算法。When classifying ventricular arrhythmia based on mobile device platforms by neural networks and support vector machine, the problem of long computation time is severe. Therefore we studied ELM and improved the activation function of ridge regression ELM. Using classification accuracy in training time as the performance index, we compared variety of classification algorithms and proved that the improved RR-ELM algorithm is more quickly and ac- curately. Comprehensive consideration of speed and accuracy show that the improved RR-ELM is better than several other algorithms.

关 键 词：心电信号 室性心律失常 极限学习机 岭回归 激活函数改进 

分 类 号：TP301.6[自动化与计算机技术—计算机系统结构]