最小二乘支持向量机算法在中医临床脉图参数﹣血压预测模型的应用
|
摘要
目的提出基于最小二乘支持向量机(LSSVM)算法的学习模型,以提高中医临床血压数据预测的准确度和效率。方法将LSSVM学习模型应用于中医临床血压数据预测。用LSSVM等式约束代替支持向量机不等式约束,将二次规划问题转化为线性方程求解问题,降低计算复杂性,加快算法收敛速度。收集320例患者的临床脉图参数及血压数据,以其中300例样本作为训练样本,训练得到LSSVM学习模型,以其余20例样本作为测试数据,用得到的LSSVM学习模型根据患者的脉图参数预测血压数据。结果实验证明,LSSVM学习模型对血压数据有较好的预测准确度。其中基于多项式核函数的LSSVM学习模型较基于径向基核函数LSSVM学习模型表现出更好的学习和预测能力,基于多项式核函数的LSSVM学习模型中收缩压、舒张压、平均动脉压预测结果的平均预测误差分别为7.88%、8.40%、6.67%,低于基于径向基核函数的LSSVM学习模型的预测误差(分别为7.95%、9.70%、7.48%)。结论本实验提出的基于LSSVM的学习模型仅通过患者的临床脉图参数就可预测患者血压数据,对中医学临床诊断有一定的参考价值。
Objective To propose a learning model based on least square support vector machine(LSSVM) algorithm to improve the accuracy and efficiency for predicting clinical blood pressure data of traditional Chinese medicine(TCM).Methods The LSSVM learning model was used to predict the clinical blood pressure of TCM. By replacing the inequality constraints of support vector machine with LSSVM equality constraints, the quadratic programming problem was transformed into a linear equation solution problem to reduce computational complexity and speed up algorithm convergence. The clinical pulse diagram parameters and blood pressure data of 320 patients were collected. Three hundred of them were used as training samples, the remaining 20 samples were used as test data. The LSSVM learning model was used to predict blood pressure data according to the pulse diagram parameters of the patients. Results Experimental results showed that the LSSVM learning model had high prediction accuracy for blood pressure data. The LSSVM learning model based on polynomial kernel function had better learning and prediction abilities than the LSSVM learning model based on radial basis kernel function. The mean prediction errors of systolic blood pressure, diastolic blood pressure and mean arterial pressure obtained by the LSSVM learning model based on polynomial kernel function were 7.88%, 8.40% and 6.67%, respectively, which were lower than those obtained by the LSSVM learning model based on radial basis kernel function(7.95%, 9.70% and 7.48%, respectively).Conclusion The LSSVM learning model proposed in this experiment can be used to predict the blood pressure data of patients only by the clinical pulse diagram parameters, and is a good reference for clinical diagnosis of TCM.
Objective To propose a learning model based on least square support vector machine(LSSVM) algorithm to improve the accuracy and efficiency for predicting clinical blood pressure data of traditional Chinese medicine(TCM).Methods The LSSVM learning model was used to predict the clinical blood pressure of TCM. By replacing the inequality constraints of support vector machine with LSSVM equality constraints, the quadratic programming problem was transformed into a linear equation solution problem to reduce computational complexity and speed up algorithm convergence. The clinical pulse diagram parameters and blood pressure data of 320 patients were collected. Three hundred of them were used as training samples, the remaining 20 samples were used as test data. The LSSVM learning model was used to predict blood pressure data according to the pulse diagram parameters of the patients. Results Experimental results showed that the LSSVM learning model had high prediction accuracy for blood pressure data. The LSSVM learning model based on polynomial kernel function had better learning and prediction abilities than the LSSVM learning model based on radial basis kernel function. The mean prediction errors of systolic blood pressure, diastolic blood pressure and mean arterial pressure obtained by the LSSVM learning model based on polynomial kernel function were 7.88%, 8.40% and 6.67%, respectively, which were lower than those obtained by the LSSVM learning model based on radial basis kernel function(7.95%, 9.70% and 7.48%, respectively).Conclusion The LSSVM learning model proposed in this experiment can be used to predict the blood pressure data of patients only by the clinical pulse diagram parameters, and is a good reference for clinical diagnosis of TCM.
引文
[1]彭显刚,胡松峰,吕大勇.基于RBF神经网络的短期负荷预测方法综述[J].电力系统保护与控制,2011,39:144-148.
[2]丁世飞,齐丙娟,谭红艳.支持向量机理论与算法研究综述[J].电子科技大学学报,2011,40:2-10.
[3]朱群雄,甄玉山.用于化工软测量的基于移动窗的过程神经网络[J].清华大学学报(自然科学版),2012,52:1165-1170.
[4]SAIN S R,VAPNIK V N.Book review:the nature of statistical learning theory[J].Technimetrics,1996,38:409.
[5]VAPNIK V N.An overview of statistical learning theory[J].IEEE Trans Neural Netw,1999,10:988-999.
[6]王保义,王冬阳,张少敏.基于Spark和IPPSO_LSSVM的短期分布式电力负荷预测算法[J].电力自动化设备,2016,36:117-122.
[7]陈进东,潘丰.基于在线支持向量回归的非线性模型预测控制方法[J].控制与决策,2014,29:460-464.
[8]SUYKENS J A K,VANDEWALLE J.Least squares support vector machine classifiers[J].Neural Process Lett,1999,9:293-300.
[9]WANG H Q,SUN F C,CAI Y N,DING L G,CHENN.An unbiased LSSVM model for classification and regression[J].Soft Computing,2010,14:171-180.
[10]DE KRUIF B J,DE VRIES T A.Pruning error minimization in least squares support vector machines[J].IEEE Trans Neural Netw,2003,14:696-702.
[11]林升梁,刘志.基于RBF核函数的支持向量机参数选择[J].浙江工业大学学报,2007,35:163-167.
[12]胡瑾秋,郭放,张来斌.结合改进PSO算法和LSSVM的化工异常工况超早期监测预警研究[J].电子测量与仪器学报,2018,32:36-41.
[13]LI L,SU H,CHU J.Modeling of isomerization of C8 aromatics by online least squares support vector machine[J].Chin J Chem Eng,2009:17:437-444.
[14]郑蓉建,潘丰.基于PLS-LSSVM的谷氨酸发酵产物浓度预测建模[J].化工学报,2017,68:976-983.
[15]朱丽萍,吴宏进,张志枫,张瑜,许家佗,屠立平,等.54例不同性别健康大学生“寸口”脉象及脉图参数分析[J].上海中医药大学学报,2013,27:28-31.
[2]丁世飞,齐丙娟,谭红艳.支持向量机理论与算法研究综述[J].电子科技大学学报,2011,40:2-10.
[3]朱群雄,甄玉山.用于化工软测量的基于移动窗的过程神经网络[J].清华大学学报(自然科学版),2012,52:1165-1170.
[4]SAIN S R,VAPNIK V N.Book review:the nature of statistical learning theory[J].Technimetrics,1996,38:409.
[5]VAPNIK V N.An overview of statistical learning theory[J].IEEE Trans Neural Netw,1999,10:988-999.
[6]王保义,王冬阳,张少敏.基于Spark和IPPSO_LSSVM的短期分布式电力负荷预测算法[J].电力自动化设备,2016,36:117-122.
[7]陈进东,潘丰.基于在线支持向量回归的非线性模型预测控制方法[J].控制与决策,2014,29:460-464.
[8]SUYKENS J A K,VANDEWALLE J.Least squares support vector machine classifiers[J].Neural Process Lett,1999,9:293-300.
[9]WANG H Q,SUN F C,CAI Y N,DING L G,CHENN.An unbiased LSSVM model for classification and regression[J].Soft Computing,2010,14:171-180.
[10]DE KRUIF B J,DE VRIES T A.Pruning error minimization in least squares support vector machines[J].IEEE Trans Neural Netw,2003,14:696-702.
[11]林升梁,刘志.基于RBF核函数的支持向量机参数选择[J].浙江工业大学学报,2007,35:163-167.
[12]胡瑾秋,郭放,张来斌.结合改进PSO算法和LSSVM的化工异常工况超早期监测预警研究[J].电子测量与仪器学报,2018,32:36-41.
[13]LI L,SU H,CHU J.Modeling of isomerization of C8 aromatics by online least squares support vector machine[J].Chin J Chem Eng,2009:17:437-444.
[14]郑蓉建,潘丰.基于PLS-LSSVM的谷氨酸发酵产物浓度预测建模[J].化工学报,2017,68:976-983.
[15]朱丽萍,吴宏进,张志枫,张瑜,许家佗,屠立平,等.54例不同性别健康大学生“寸口”脉象及脉图参数分析[J].上海中医药大学学报,2013,27:28-31.