Method for extracting Raman spectra characteristic variables of biological sample based on Hilbert–Huang transform

Abstract

Because Raman peaks of the biological sample are superimposed on each other, the use of characteristic peak attribution is limited to some extent. In this study, we show that Hilbert–Huang transform (HHT) provides a Raman spectral feature extracting method, especially for biological samples. First, the empirical mode decomposition algorithm was used to decompose Raman spectra into intrinsic mode functions (IMFs). It is worth noticing that the IMF frequency is single or nearly single, so its further transformation (instantaneous amplitude, instantaneous angle, instantaneous angular frequency, Hilbert spectrum, and Hilbert marginal spectrum) from Hilbert processing is monotonous instead of the raw overlapping. Then, the Hilbert marginal spectrum was selected by one‐way analysis of variance and related with the rice type to establish a partial least squares regression (PLS) model with a 95.00% accuracy. This result is better than those based on characteristic variables screened by PLS, interval PLS, principal component analysis, independent component analysis, successive projections algorithm, haar, db, and coif (85.00%, 90.00%, 82.50%, 77.50%, 90.00%, 92.50%, 80.00%, and 85.00%). These results illustrate that HHT can accurately extract the characteristic variables from biological Raman spectra. The classification accuracy based on HHT is slightly lower than those based on bior 2.4, three‐layer decomposition (97.50%) and sym 5, five‐layer decomposition (97.50%). Significantly, no parameters need to be set such as the wavelet mother function and the decomposition layer in the HHT feature extraction process. This paper provides a HHT method for Raman spectral feature extraction, which is simple and effective.

An Exploration of the Influence of Abrasive Water Jet Pressure on the Friction Signal Characteristics of Fixed Abrasive Lapping Quartz Glass Based on HHT

“…Therefore, the Hilbert marginal transform that extracts the friction signal while lapping the process of the FAP can accurately represent the changes of the signal, which is combined with the surface situation of the FAP. The HHT method includes two steps: EMD (Empirical Mode Decomposition) and Hilbert transform [26]. First, EMD is used to decompose the signal to obtain a limited number of the Intrinsic Mode Function (IMF).…”

Design of Neural Network-based Intelligent Extraction Method for Key Electronic Information

“…With the continuous improvement of computing speed and accuracy, the application of electronic information feature extraction is becoming more and more common while promoting the development of a variety of signal recognition technology speeds; the existing recognition technology, although there are many insurmountable shortcomings, with the help of this important scientific and technological development trend, but also step by step to promote the vigorous development of various industries, so that life is smarter, and greatly reduces the cost of manpower, enhance the work of the Efficiency, pattern recognition is an important technical basis, it has far-reaching impact in the field of industrial production [8][9].…”

The Classification of Rice Blast Resistant Seed Based on Ranman Spectroscopy and SVM

“…Ranman spectroscopy has the advantages of convenient operation, high sensitivity and good reproducibility, which can effectively overcome many of the shortcomings of traditional detection methods [7]. The aim is to describe difference in the biological mechanisms of rice seeds using the characteristics of Ranman spectroscopy [8]. The Ranman spectra of different-resistance rice seeds were collected to classify the rice seeds with different resistance according to the spectral features of different molecular structures inside the seeds.…”