Hongzhi Gao

Non-invasive prediction of hemoglobin levels by principal component and back propagation artificial neural network.

To facilitate non-invasive diagnosis of anemia, specific equipment was developed, and non-invasive hemoglobin (HB) detection method based on back propagation artificial neural network (BP-ANN) was studied. In this paper, we combined a broadband light source composed of 9 LEDs with grating spectrograph and Si photodiode array, and then developed a high-performance spectrophotometric system. By using this equipment, fingertip spectra of 109 volunteers were measured. In order to deduct the interference of redundant data, principal component analysis (PCA) was applied to reduce the dimensionality of collected spectra. Then the principal components of the spectra were taken as input of BP-ANN model. On this basis we obtained the optimal network structure, in which node numbers of input layer, hidden layer, and output layer was 9, 11, and 1. Calibration and correction sample sets were used for analyzing the accuracy of non-invasive hemoglobin measurement, and prediction sample set was used for testing the adaptability of the model. The correlation coefficient of network model established by this method is 0.94, standard error of calibration, correction, and prediction are 11.29g/L, 11.47g/L, and 11.01g/L respectively. The result proves that there exist good correlations between spectra of three sample sets and actual hemoglobin level, and the model has a good robustness. It is indicated that the developed spectrophotometric system has potential for the non-invasive detection of HB levels with the method of BP-ANN combined with PCA.

The use of Raman spectroscopy in food processes: A review

Abstract Raman spectroscopy is a novel method of food analysis and inspection. It is highly accurate, quick, and noninvasive. The investigation and monitoring of food processing is important because most of the foods humans eat today are processed in various ways. In this article, the use of Raman spectroscopy in food processes, such as fermentation, cooking, processed food manufacturing, and so on, are explored. The characteristics and difficulties of the Raman inspection of these processes are also discussed. According to the various research reports, Raman spectroscopy is a very powerful tool for monitoring these food processes in lab environments and is likely to see usage in situ in the future.

Development of a handheld spectrometer based on a linear variable filter and a complementary metal-oxide-semiconductor detector for measuring the internal quality of fruit

Visible and near infrared spectroscopy has long been used to predict fruit internal quality, with portable instrumentation advantageous for in-field use. We developed a handheld spectrometer using a linear variable filter (LVF) and a complementary metal-oxide-semiconductor (CMOS) linear detector array. The LVF is a bandpass filter with a centre wavelength changing linearly in one direction and can replace a grating as the light-dispersion component. An LVF was designed and fabricated specifically to work in the 620–1080 nm region and for the analysis of fruit. The optical design used an improved collimator and an LVF to yield a compact, stable and low-cost optical engine. By using a CMOS detector and other suitable electronics, the spectrometer achieved a low power consumption. The spectrometer can analyse spectral data using an onboard prediction model and can be operated from a remote smartphone, tablet or laptop computer. This paper details the design of the spectrometer and the results of its resolution and stability tests. The spectrometer operated with a resolution of less than 1.5% centre wavelength and a signal-to-noise ratio of up to 5000. The spectrometer was then used to predict the sugar content in pears. The optimised model provided an R2c value of 0.96, standard error of calibration value of 0.29 °Bx and standard error of prediction value of 0.46 °Bx. The results indicated that this LVF-based spectrometer is promising for measuring the internal quality of fruit.

Performance improved method for subtracted blood volume spectrometry using empirical mode decomposition

Subtracted blood volume spectrometry (SBVS) can eliminate the background information in near infrared spectroscopy (NIRS) noninvasive biochemical sensing. However, the spectrum obtained by this method is accompanied by serious noises which are to the disadvantage of the calibration models. Empirical mode decomposition (EMD) was applied to restrict the noises in order to improve the performance of subtracted blood volume spectrometry. Certain criteria were used to evaluate the performance of the method, such as the average correlation coefficient, and the average and standard deviation of the Euclidean distance. EMD was applied to three subtracted spectra with different ΔL, and the criteria were calculated accordingly. All of the criteria were improvement. Especially for the subtracted spectra with ΔL=0.5mm, the correlation coefficient increased from 0.9970 to 0.9999, the average Euclidean distance decreased from 0.0265 to 0.0118, and the standard deviation of the Euclidean distance decreased from 0.0148 to 0.0033 after EMD filtering. The PLS models of the processed spectra were promoted as well. These preliminary results suggest that EMD is a promising means of improving the performance of subtracted blood volume spectrometry.

Research on Measurement Conditions for Obtaining Significant, Stable, and Repeatable SERS Signal of Human Blood Serum

The Raman spectra of human blood serum can be used to identify cancer or other diseases; however, obtaining a reliable surface enhanced Raman scattering (SERS) signal of human blood serum is difficult. Two primary factors that affect SERS measurement of serum are photodegradation and sample composition, which are investigated in this research. In the end, this research proposes a promising set of measurement conditions that can both acquire reliable serum Raman signals and avoid photodegradation.