This paper presents a new noninvasive blood glucose monitoring method based on four near infrared spectrums and double artificial neural network analysis. We choose four near infrared wavelengths, 820 nm, 875 nm, 945 ...This paper presents a new noninvasive blood glucose monitoring method based on four near infrared spectrums and double artificial neural network analysis. We choose four near infrared wavelengths, 820 nm, 875 nm, 945 nm, 1050 nm, as transmission spectrums, and capture four fingers transmission PPG signals simultaneously. The wavelet transform algorithm is used to remove baseline drift, smooth signals and extract eight eigenvalues of each PPG signal. The eigenvalues are the input parameters of double artificial neural network analysis model. Double artificial neural network regression combines the classification recognition algorithm with prediction algorithm to improve the accuracy of measurement. Experiments show that the root mean square error of the prediction is between 0.97 mg/dL - 6.69 mg/dL, the average of root mean square error is 3.80 mg/dL.展开更多
This study aims to explore the influence brought by the decrease degree in blood glucose during the period when diabetes patients’ blood samples are collected through fasting blood and sent to the laboratory for dete...This study aims to explore the influence brought by the decrease degree in blood glucose during the period when diabetes patients’ blood samples are collected through fasting blood and sent to the laboratory for detection on the accuracy on blood glucose measurement. Methods: This study is conducted by detecting fasting blood glucose of 150 patients who came to our hospital for physical examination and collecting their general information. Blood glucose concentration is measured through centrifugation after blood samples are placed for 0 min, 60 min, 120 min and 180 min.展开更多
选取150份干扰物和浓度不同的葡萄糖样本数据,按照全干扰、缺失胆固醇、缺失乳酸、缺失白蛋白和缺失尿素将数据划分5个子集。每个子集进行卷积平滑滤波法(Savitzky-Golay smoothing,SG)处理后,建立偏最小二乘回归(Partial Least Squares...选取150份干扰物和浓度不同的葡萄糖样本数据,按照全干扰、缺失胆固醇、缺失乳酸、缺失白蛋白和缺失尿素将数据划分5个子集。每个子集进行卷积平滑滤波法(Savitzky-Golay smoothing,SG)处理后,建立偏最小二乘回归(Partial Least Squares Regression,PLSR)模型。利用克拉克误差网格(Clarke Error Grid,CEG)及t检验分析4种干扰物对葡萄糖预测影响。结果表明,子集1~5对应模型预测集相关系数(Correlation Coefficient of Prediction,R p)分别为0.9131、0.7115、0.7624、0.8578和0.8658,预测集均方根误差(Root Mean Square Error of Prediction,RMSEP)分别为54.8993、239.5512、162.3715、133.9682和106.0521 mg/dL。5个子集位于CEG的A+B区分别为100%、71.43%、66.66%、85.71%和88.89%。t检验中每1 mg/dL的胆固醇、乳酸和白蛋白分别使葡萄糖预测值降低5.288 mg/dL、增高2.214 mg/dL和增高0.031 mg/dL。故胆固醇和乳酸的影响相当显著,其次是白蛋白,而尿素的影响则相对较弱。因此,在中红外血糖定量分析中必须考虑胆固醇、乳酸和白蛋白对血糖检测的影响。展开更多
文摘This paper presents a new noninvasive blood glucose monitoring method based on four near infrared spectrums and double artificial neural network analysis. We choose four near infrared wavelengths, 820 nm, 875 nm, 945 nm, 1050 nm, as transmission spectrums, and capture four fingers transmission PPG signals simultaneously. The wavelet transform algorithm is used to remove baseline drift, smooth signals and extract eight eigenvalues of each PPG signal. The eigenvalues are the input parameters of double artificial neural network analysis model. Double artificial neural network regression combines the classification recognition algorithm with prediction algorithm to improve the accuracy of measurement. Experiments show that the root mean square error of the prediction is between 0.97 mg/dL - 6.69 mg/dL, the average of root mean square error is 3.80 mg/dL.
文摘This study aims to explore the influence brought by the decrease degree in blood glucose during the period when diabetes patients’ blood samples are collected through fasting blood and sent to the laboratory for detection on the accuracy on blood glucose measurement. Methods: This study is conducted by detecting fasting blood glucose of 150 patients who came to our hospital for physical examination and collecting their general information. Blood glucose concentration is measured through centrifugation after blood samples are placed for 0 min, 60 min, 120 min and 180 min.