Optoacoustic classification of diabetes mellitus with the synthetic impacts via optimized neural networks.

A highly accurate classification of diabetes mellitus (DM) with the synthetic impacts of several variables is first studied via optoacoustic technology in this work. For this purpose, an optoacoustic measurement apparatus of blood glucose is built, and the optoacoustic signals and peak-peak values for 625 cases of in vitro rabbit blood are obtained. The results show that although the single impact of five variables are obtained, the precise classification of DM is limited because of the synthetic impacts. Based on clinical standards, different levels of blood glucose corresponding to hypoglycaemia, normal, slight diabetes, moderate diabetes and severe diabetes are employed. Then, a wavelet neural network (WNN) is utilized to establish a classification model of DM severity. The classification accuracy is 94.4 % for the testing blood samples. To enhance the classification accuracy, particle swarm optimization (PSO) and quantum-behaved particle swarm optimization (QPSO) are successively utilized to optimize WNN, and accuracy is enhanced to 98.4 % and 100 %, respectively. It is demonstrated from comparison between several algorithms that optoacoustic technology united with the QPSO-optimized WNN algorithm can achieve precise classification of DM with synthetic impacts.

Qualitative and Quantitative Assessments of Apple Quality Using Vis Spectroscopy Combined with Improved Particle-Swarm-Optimized Neural Networks.

Exploring a cost-effective and high-accuracy optical detection method is of great significance in promoting fruit quality evaluation and grading sales. Apples are one of the most widely economic fruits, and a qualitative and quantitative assessment of apple quality based on soluble solid content (SSC) was investigated via visible (Vis) spectroscopy in this study. Six pretreatment methods and principal component analysis (PCA) were utilized to enhance the collected spectra. The qualitative assessment of apple SSC was performed using a back-propagation neural network (BPNN) combined with second-order derivative (SD) and Savitzky-Golay (SG) smoothing. The SD-SG-PCA-BPNN model's classification accuracy was 87.88%. To improve accuracy and convergence speed, a dynamic learning rate nonlinear decay (DLRND) strategy was coupled with the model. After that, particle swarm optimization (PSO) was employed to optimize the model. The classification accuracy was 100% for testing apples via the SD-SG-PCA-PSO-BPNN model combined with a Gaussian DLRND strategy. Then, quantitative assessments of apple SSC values were performed. The correlation coefficient (r) and root-square-mean error for prediction (RMSEP) in testing apples were 0.998 and 0.112 °Brix, surpassing a commercial fructose meter. The results demonstrate that Vis spectroscopy combined with the proposed synthetic model has significant value in qualitative and quantitative assessments of apple quality.

Quantitative measurement of blood glucose influenced by multiple factors via photoacoustic technique combined with optimized wavelet neural networks.

In this work, the photoacoustic (PA) quantitative measurement of blood glucose concentration (BGC) influenced by multiple factors was firstly investigated. A set of PA detection system of blood glucose considering the comprehensive influence of five factors was established. The PA signals and peak-to-peak values (PPVs) of 625 rabbit whole blood were obtained under 625 influence combinations. Due to the accurate measurement of BGC limited by the overlap PA signals, wavelet neural network (WNN) was utilized to train the PPVs of blood glucose for 500 rabbit blood. The mean square error (MSE) of BGC for 125 testing blood was approximately 6.5782 mmol/L. To decrease the MSE, the parameters of WNN were optimized by particle swarm optimization (PSO), that is, PSO-WNN algorithm was employed. Under the optimal parameters, MSE of BGC was decreased to approximately 0.48005 mmol/L. To further improve the prediction accuracy of BGC, an improved nonlinear dynamic inertia weight (NDIW) strategy of PSO was proposed, and compared with other two kinds of dynamic inertia weight strategies. Under the optimal parameters, the MSE of BGC was decreased to approximately 0.2635 mmol/L. The comparison of nine algorithms demonstrate that the PA technique combined with PSO-WNN and the improved NDIW strategy is significant in the quantitative measurement of blood glucose influenced by multiple factors.