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.

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.

Surface-enhanced Raman spectroscopy method for classification of doxycycline hydrochloride and tylosin in duck meat using gold nanoparticles.

This paper investigated on 478 duck meat samples for the identification of 2 kinds of antibiotics, that is, doxycycline hydrochloride and tylosin, that were classified based on surface-enhanced Raman spectroscopy (SERS) combined with multivariate techniques. The optimal detection parameters, including the effects of the adsorption time, and 2 enhancement substrates (i.e., gold nanoparticles as well as gold nanoparticles and NaCl) on Raman intensities, were analyzed using single factor analysis method. The results showed that the optimal adsorption time between gold nanoparticles and analytes was 2 min, and the colloidal gold nanoparticles without NaCl as the active substrate were more conducive to enhance the Raman spectra signal. The SERS data were pretreated by using the method of adaptive iterative penalty least square method (air-PLS) and second derivative, and from which the feature vectors were extracted with the help of principal component analysis. The first four principal components scores were selected as the input values of support vector machines model. The overall classification accuracy of the test set was 100%. The experimental results showed that the combination of SERS and multivariate analysis could identify the residues of doxycycline hydrochloride and tylosin in duck meat quickly and sensitively.

Classification and detection of testosterone propionate and nandrolone residues in duck meat using surface-enhanced Raman spectroscopy coupled with multivariate analysis.

There is a critical need for a rapid and simple method of qualitative and quantitative analysis of testosterone propionate (TP) and nandrolone (NT) residues in duck meat. In this study, we applied surface-enhanced Raman spectroscopy (SERS) coupled multivariate analysis for the classification and detection of TP and NT residues in duck meat. A total of 294 duck meat extract samples were obtained from duck breast meats based on a LC-MS/MS sample preparation method with slight modification including 102 duck meat extract samples without TP and NT, 43 duck meat samples containing TP, 47 duck meat extract samples containing NT, and 102 duck meat extract samples containing TP and NT. Raw Raman spectra were pretreated by using adaptive iteratively reweighted penalized least squares (airPLS), normalization and first derivative, and then the score values of first 10 principal components were selected as the inputs of the developed models. A particle swarm optimization-support vector classification (PSO-SVC) model was created to classify all the duck meat samples into the 4 groups (i.e., control group, TP group, NT group, and TP combined with NT group) with the classification accuracies of 99.49 and 100% for training set and test set, respectively. Furthermore, 2 least squares support vector regression (LS-SVR) models were developed to predict the TP values in samples with a determination coefficient (R2) value of 0.9316, root mean square error (RMSE) value of 2.1739, and ratio of prediction to deviation (RPD) value of 3.2189 for the test set, and NT values in samples with an R2 value of 0.9038, RMSE value of 2.2914, and RPD value of 2.9701 for the test set. Surface-enhanced Raman spectroscopy technology, in combination with multivariate analysis, has the potential to become the qualitative and quantitative analysis tool for TP and NT residues in duck meat extract.

Analysis of Diethylstilbestrol Residues in Chicken Using Surface-Enhanced Raman Spectroscopy (SERS) Coupled with Multivariate Analysis.

Estrogen residues, including diethylstilbestrol in chicken, are one of the main food safety concerns all over the world owing to a series of negative effects on the human body. Surface-enhanced Raman spectroscopy (SERS) coupled with multivariate analysis was applied to detect rapidly diethylstilbestrol residues in chicken. The detection conditions, including the sizes of colloidal gold nanoparticles (Au NPs) and the additional amounts of Au NPs, chicken extract containing diethylstilbestrol, and magnesium sulfate solution, as well as the adsorption time, were optimized by a single factor experiment to obtain a better detection effect of diethylstilbestrol residues in chicken. Partial least squares regression (PLSR) was the best quantitative model for the detection of diethylstilbestrol residues in chicken by comparing four chemometric models. Diethylstilbestrol residues in chicken could be predicted by PLSR with the low root mean square error (RMSE = 0.4128 mg/L), and the high determination coefficient (R2 = 0.9811) and ratio of prediction to deviation (RPD = 7.2566) for the test set. A novel approach, which has the potential for the analysis of other estrogen residues in meat, was developed to detect rapidly the diethylstilbestrol residues in chicken by using SERS coupled with multivariate analysis.

Density Functional Theory Calculation and Raman Spectroscopy Studies of Carbamate Pesticides.

In order to obtain the molecular structure vibration information of carbamate pesticide, three carbamate pesticides (carbaryl, carbofuran and aldicarb) were optimized and calculated with B3LYP hybrid functional and 6-31G(d,p) basis set, and their experimental spectra were collected with the Raman spectrometer. The theoretically calculated spectra were compared with the experimental spectra carefully. The results indicated that the theoretically calculated spectra have a very good match with the experimental spectra. The vibrational peaks of three carbamate pesticides were assigned between the range of 400～3 200 cm-1, and the characteristic peaks of carbamate pesticide were found at 874, 1 014, 1 162 and 1 716 cm-1. The characteristic peaks of three carbamate pesticides were found by the contrast of the experimental spectra. The results can provide a theoretical basis for the detection of carbamate pesticide, and will be applied to the identification of carbamate pesticide residues in agricultural products.

[Density Functional Theory Calculation and Raman Spectroscopy Studies of Organophosphorus Pesticides].

Organophosphorus pesticides were often used for prevention and control disease and insect of plant, and are acute toxic to human and livestock by anti-ache activity. The molecular geometry of three organophosphorus pesticides(dimethoate, trichlorfon and phosalone) were constructed on Gauss View3.07, and Density functional theory (DFT) was used to optimize and calculate the vibrational wavenumbers of three organophosphorus pesticides by B3LYP hybrid functional and 6-31G(d, p) basis set. The experimental spectra of three organophosphorus pesticides were compared with the theoretically calculated spectra and Surface-enhanced Raman Scattering spectra (SERS). The results indicated that the experimental spectra and theoretically calculated spectra of three organophosphorus pesticides have a very good match. The Raman peaks of three organophosphorus pesticides were roundly assigned between the range of 400～1 800 cm(-1), and the characteristics peaks of three organophosphorus pesticides were found. The Raman vibration peak of organophosphorus pesticide may appear similar characteristic peak. The pesticide contained PO is between 1 140 and 1 320 cm(-1), the pesticide contained PS is in the range 535～750 cm(-1), and the organophosphorus pesticide contained P­O­C is n the range 920～1 088 cm-1. The different characteristic peaks of three pesticides were found by the contrast of the surface enhanced Raman spectra. This shows that the SERS method can be used to identify the organophosphorus pesticide. The results can furnish a theoretical support for qualitative and quantitative analysis of organophosphorus pesticide.