基于支持向量机的无创血糖光谱算法①-计算机系统应用.PDF

计 算 机 系 统 应 用 2016 年 第 25 卷 第 8 期 基于支持向量机的无创血糖光谱算法① 马 爽 1,2, 蒲宝明 1 1( 中国科学院 沈阳计算技术研究所, 沈阳 110168) 2( 中国科学院大学 计算机与控制学院, 北京 100049) 摘 要: 为了实现无创血糖浓度检测, 提出了基于支持向量机回归模型的无创血糖光谱算法. 该算法使用光电容 积脉搏波(PPG)设备对志愿者指端红光、红外光交替采样得到 PPG 信号, 然后通过微创血糖仪测得血糖浓度. 对 采集到的 PPG 信号进行处理提取特征组成特征矩阵, 分别运用不同机器学习模型对特征矩阵和实时血糖浓度进 行回归训练, 得到特征矩阵与血糖浓度间的关系, 并对训练得到的函数关系进行验证, 选取出高斯核支持向量机 模型为最佳训练模型. 实验证明, 与偏最小二乘回归进行对比, 本文提出的运用核函数为高斯核的支持向量机算 法的预测准确度能提升 10%～15%, 预测的高低血糖正确率达到 98%. 关键词: 支持向量机; 无创血糖检测; 近红外光谱; 光电容积脉搏波 Non-Invasive Blood Glucose Measurement Based on Support Vector Machine Algorithm MA Shuang1,2, PU Bao-Ming1 1(Shenyang Institute of Computing Technology, Chinese Academy of Sciences, Shenyang 110168, China) 2(School of Computer and Control Engineering, University of Chinese Academy of Sciences, Beijing 100049, China) Abstract: To achieve sensing non-invasive blood glucose concentration, this paper proposes a non-invasive blood glucose spectrum algorithm based on support vector machine (SVM) model. The algorithm firstly uses a PPG device to sample red and infrared signal of volunteers to obtain the PPG signal, and then extracts the blood glucose concentration by a minimally-invasive glucometer. Compared with traditional near-infrared spectrum and regression method, the proposed algorithm could effectively improve the prediction accuracy by adopting the SVM model to find regression relationship between signal and glycemic. And the SVM model uses the Gauss-function as the kernel function. The algorithm is independently of the individual and environmental factors. The experimental results demonstrate that compared to partial least squares regression, the proposed algorithm could improve the predictive accuracy by 10%– 15%. And the algorithm’