Multi-models with averaging in feature domain for non-invasive blood glucose estimation

Abstract

Diabetes is a serious chronic metabolic disease. In the recent years, more and more studies focus on the use of the non-invasive methods to achieve the blood glucose estimation. More and more consumer technology enterprises focusing on human health are committed to implementing accurate and non-invasive blood glucose algorithm in their products. The near infrared spectroscopy built in the wearable devices is one of the common approaches to achieve the non-invasive blood glucose estimation. However, due to the interference from the external environment, these wearable non-invasive methods yield the low estimation accuracy. Even if it is not medical equipment, as a consumer product, the detection accuracy will also be an important indicator for consumers. To address this issue, this paper employs different models based on different ranges of the blood glucose values for performing the blood glucose estimation. First the photoplethysmograms (PPGs) are acquired and they are denoised via the bit plane singular spectrum analysis (SSA) method. Second, the features are extracted. For the data in the training set, first the features are averaged across the measurements in the feature domain via the optimization approach. Second, the random forest is employed to sort the importance of each feature. Third, the training set is divided into three subsets according to the reference blood glucose values. Fourth, the feature vectors and the corresponding blood glucose values in the same group are employed to build an individual model. Fifth, for each feature, the average of the feature values for all the measurements in the same subset is computed. For the data in the test set, first, the sum of the weighted distances between the test feature values and the average values obtained in the above is computed for each model. Here, the weights are defined based on the importance sorted by the random forest obtained in the above. The model corresponding to the smallest sum is assigned. Finally, the blood glucose value is estimated based on the corresponding model. Compared to the state of arts methods, our proposed method can effectively improve the estimation accuracy. In particular, the mean absolute relative difference (MARD) and the percentage of the data fall in the zone A of the Clarke error grid yielded by our proposed method reaches 12.19%, and 87.0588%, respectively.