Denoising method for Raman spectra with low signal-to-noise ratio based on feature extraction

Zhao, Xiaoyu; Liu, G.Y.; Sui, Yao; Xu, Ming; Tong, Lewei

doi:10.1016/j.saa.2020.119374

Cited by 36 publications

(16 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Figure d shows soft thresholding (threshold >0.04). Figure e shows a wavelet transform (with db5 mother function, level 7, Bayer denoising method, threshold rule as median and level-dependent noise) . It is observed that the Gaussian filter smoothes the data affecting the lineshapes and the Fourier intensity decreases (Figure c) and soft thresholding (Figure d) hides details of the spectrum.…”

Section: Neat Solventsmentioning

confidence: 96%

A Revisit on Impulsive Stimulated Raman Spectroscopy: Importance of Spectral Dispersion of Chirped Broadband Probe

et al. 2022

View full text Add to dashboard Cite

The usefulness of a chirped broadband probe and spectral dispersion to obtain Raman spectra under nonresonant/resonant impulsive excitation is revisited. A general methodology is presented that inherently takes care of phasing the time-domain low-frequency oscillations without probe pulse compression and retrieves the absolute phase of the oscillations. As test beds, neat solvents (CCl4, CHCl3, and CH2Cl2) are used. Observation of periodic intensity modulation along detection wavelengths for particular modes is explained using a simple electric field interaction picture. This method is extended to diatomic molecule (iodine) and polyatomic molecules (Nile blue and methylene blue) to assign vibrational frequencies in ground/excited electronic state that are supported by density functional theory calculations. A comparison between frequency-domain and time-domain counterparts, i.e., stimulated Raman scattering and impulsive stimulated Raman scattering using degenerate pump–probe pairs is presented, and most importantly, it is shown how impulsive stimulated Raman scattering using chirped broadband probe retains unique advantages offered by both.

show abstract

Section: Neat Solventsmentioning

confidence: 96%

A Revisit on Impulsive Stimulated Raman Spectroscopy: Importance of Spectral Dispersion of Chirped Broadband Probe

et al. 2022

View full text Add to dashboard Cite

show abstract

“…Now, noise can be removed with a Gaussian filter with a standard deviation of around five, but with the possibility to have a Raman spike in the resulting curve. [12] To determine if there is a Raman spike in the data, the gradient is calculated. The gradient created by noise can be temporally as high as the gradient created by a Raman spike; therefore, G, the Gaussian smoothed absolute gradient is calculated.…”

Section: Gaussian Smoothing Polynomial Fitting (Gsp)mentioning

confidence: 99%

“…Now, noise can be removed with a Gaussian filter with a standard deviation of around five, but with the possibility to have a Raman spike in the resulting curve. [ 12 ]…”

Section: Data Processingmentioning

confidence: 99%

A machine learning classification methodology for Raman Hyperspectral imagery based on auto‐encoders

Goedhart

Papadakis

2022

J Raman Spectroscopy

View full text Add to dashboard Cite

Raman spectroscopy is a very sensitive, non‐destructive optical technique that is able to characterize the composition of a material. Although it is a very useful technique, its signals are rather complex and therefore require a lot of knowledge and skills to understand their meaning. This complexity increases further, when it is combined with spatial mapping, creating a three‐dimensional dataset named Raman hyperspectral imagery. The common methodology of analysing such a dataset is to use a generic supervised classification algorithm (i.e., non‐negative least square) combined with reference data. If reference data are not available, unsupervised algorithms are used to perform spectral clusterization of similar areas. This is typically achieved using standard PCA and k‐means methods. The most common problem of processing that significantly affects the results of analysis is that a raw Raman Signal consists of three sources: Raman scattering, photoluminescence and noise. The contribution weights of those components are not standard and are changing based on the sample's chemistry, which makes it very difficult to be solved. This creates the necessity for pre‐processing methods that can split this raw signal to its components. The goals of this project are to improve the unmixing performance using AI and to achieve a successful split of the raw signal into its three components. Through this study, various unsupervised methods are explored to identify the method that fits best to our microscopic RHSI data sets. Our focus is on using autoencoders for the data analysis and on a Gaussian smoothing filter combined with polynomial fittings to split the data. Results show that the selection of a classification methodology depends greatly on the application, but when a large RHSI dataset is available, the newly proposed splitting technique combined with an autoencoder classification presents the best solution.

show abstract

“…We have presented a study of the misclassification of the noisy Raman Spectrum of the Anatase polymorph in the supplementary information. Several researchers have studied the use of machine learning models for improving the signal-to-noise ratio of the Raman spectrum 72,73 . We believe that the use of these models in conjunction with our proposed model will address the above-mentioned challenge.…”

Section: Sensitivity Analysismentioning

confidence: 99%

Deep-learning framework for fully-automated recognition of TiO2 polymorphs based on Raman spectroscopy

Bhattacharya

Benavides

Gerlein

et al. 2022

Sci Rep

View full text Add to dashboard Cite

Emerging machine learning techniques can be applied to Raman spectroscopy measurements for the identification of minerals. In this project, we describe a deep learning-based solution for automatic identification of complex polymorph structures from their Raman signatures. We propose a new framework using Convolutional Neural Networks and Long Short-Term Memory networks for compound identification. We train and evaluate our model using the publicly-available RRUFF spectral database. For model validation purposes, we synthesized and identified different TiO2 polymorphs to evaluate the performance and accuracy of the proposed framework. TiO2 is a ubiquitous material playing a crucial role in many industrial applications. Its unique properties are currently used advantageously in several research and industrial fields including energy storage, surface modifications, optical elements, electrical insulation to microelectronic devices such as logic gates and memristors. The results show that our model correctly identifies pure Anatase and Rutile with a high degree of confidence. Moreover, it can also identify defect-rich Anatase and modified Rutile based on their modified Raman Spectra. The model can also correctly identify the key component, Anatase, from the P25 Degussa TiO2. Based on the initial results, we firmly believe that implementing this model for automatically detecting complex polymorph structures will significantly increase the throughput, while dramatically reducing costs.

show abstract

Denoising method for Raman spectra with low signal-to-noise ratio based on feature extraction

Cited by 36 publications

References 11 publications

A Revisit on Impulsive Stimulated Raman Spectroscopy: Importance of Spectral Dispersion of Chirped Broadband Probe

A Revisit on Impulsive Stimulated Raman Spectroscopy: Importance of Spectral Dispersion of Chirped Broadband Probe

A machine learning classification methodology for Raman Hyperspectral imagery based on auto‐encoders

Deep-learning framework for fully-automated recognition of TiO2 polymorphs based on Raman spectroscopy

Contact Info

Product

Resources

About