4.7 Article

Interpretable Perturbator for Variable Selection in near-Infrared Spectral Analysis

相关参考文献

注意:仅列出部分参考文献,下载原文获取全部文献信息。
Article Chemistry, Analytical

A Universal and Accurate Method for Easily Identifying Components in Raman Spectroscopy Based on Deep Learning

Xiaqiong Fan et al.

Summary: A method called DeepRaman is proposed to solve the challenges of component identification in Raman spectra by combining the comparison ability of a pseudo-Siamese neural network (pSNN) and the input-shape flexibility of spatial pyramid pooling (SPP). DeepRaman achieves high accuracy and outperforms other methods in different application scenarios. It can be directly used on different data sets without retraining or transfer learning, and shows promising results in analyzing SERS data sets and Raman imaging data sets.

ANALYTICAL CHEMISTRY (2023)

Article Spectroscopy

Ultra-high resolution near-infrared spectrum by wavelet packet transform revealing the hydrogen bond interactions

Li Han et al.

Summary: Wavelet packet transform (WPT) was used to enhance the resolution of NIR spectra of aqueous mixtures, allowing the observation of fine details in different frequency components. The spectral features of different hydrogen-bonded compounds were identified and validated by analyzing the variation of spectral intensity with the mole ratio of H2O and D2O. The interaction between CH/NH in tert-butylamine (TBA) and OH in water was observed, identifying the structures of CH bonded to one water molecule and NH connected to one or two water molecules.

SPECTROCHIMICA ACTA PART A-MOLECULAR AND BIOMOLECULAR SPECTROSCOPY (2023)

Article Automation & Control Systems

Soft variable selection combining partial least squares and attention mechanism for multivariable calibration

Yinran Xiong et al.

Summary: In this study, a new variable selection method called 'Attention-PLS' was proposed, which combines PLS with the attention mechanism in a neural network to build a linear model between chemical properties and multivariables. The results show that Attention-PLS has better prediction performances.

CHEMOMETRICS AND INTELLIGENT LABORATORY SYSTEMS (2022)

Article Chemistry, Medicinal

Spectral Encoder to Extract the Features of Near-Infrared Spectra for Multivariate Calibration

Chaoshu Duan et al.

Summary: An autoencoder architecture is used for near-infrared spectral analysis to extract common features. Through the encoder and decoder's reverse prediction, it is possible to predict the spectral features of one instrument from the spectra of another instrument. The multi-linear regression model has similar or slightly better predictive performance compared to the partial least-squares model.

JOURNAL OF CHEMICAL INFORMATION AND MODELING (2022)

Review Chemistry, Analytical

Recent advances of chemometric calibration methods in modern spectroscopy: Algorithms, strategy, and related issues

Hai-Peng Wang et al.

Summary: This article reviews various chemometric methods applied in modern spectral analysis in recent years, emphasizing practicality, including spectral pre-processing, wavelength selection, data dimension reduction, quantitative calibration, pattern recognition, calibration transfer, calibration maintenance, and multispectral data fusion. Future trends in chemometric methods in the field of spectral analysis are also discussed.

TRAC-TRENDS IN ANALYTICAL CHEMISTRY (2022)

Article Chemistry, Analytical

Discrimination of Substandard and Falsified Formulations from Genuine Pharmaceuticals Using NIR Spectra and Machine Learning

Olatunde Awotunde et al.

Summary: This work demonstrates the effective use of a library of lab-formulated binary mixtures for field screening of substandard and falsified drugs. Additionally, a predictive algorithm based on six models shows accurate prediction for ternary mixtures and various formulations, expanding the utility of NIR spectrometers in low-resource settings.

ANALYTICAL CHEMISTRY (2022)

Article Computer Science, Artificial Intelligence

Interpreting neural networks for biological sequences by learning stochastic masks

Johannes Linder et al.

Summary: Neural networks have become an effective method for predicting biological function, but the lack of interpretability has been a challenge. To address this, the authors propose scrambler networks, which can attribute important features in biological sequences. By learning input masks, scrambler networks can identify the most crucial positions in a sequence and provide efficient feature attribution.

NATURE MACHINE INTELLIGENCE (2022)

Article Spectroscopy

Three-step hybrid strategy towards efficiently selecting variables in multivariate calibration of near-infrared spectra

Hai-Dong Yu et al.

SPECTROCHIMICA ACTA PART A-MOLECULAR AND BIOMOLECULAR SPECTROSCOPY (2020)

Review Chemistry, Analytical

An overview of variable selection methods in multivariate analysis of near-infrared spectra

Yong-Huan Yun et al.

TRAC-TRENDS IN ANALYTICAL CHEMISTRY (2019)

Review Chemistry, Analytical

Deep learning for vibrational spectral analysis: Recent progress and a practical guide

Jie Yang et al.

ANALYTICA CHIMICA ACTA (2019)

Article Chemistry, Analytical

DeepSpectra: An end-to-end deep learning approach for quantitative spectral analysis

Xiaolei Zhang et al.

ANALYTICA CHIMICA ACTA (2019)

Article Automation & Control Systems

A variable informative criterion based on weighted voting strategy combined with LASSO for variable selection in multivariate calibration

Ruoqiu Zhang et al.

CHEMOMETRICS AND INTELLIGENT LABORATORY SYSTEMS (2019)

Article Chemistry, Analytical

Convolutional neural network for hyperspectral data analysis and effective wavelengths selection

Yisen Liu et al.

ANALYTICA CHIMICA ACTA (2019)

Article Chemistry, Multidisciplinary

A variable importance criterion for variable selection in near-infrared spectral analysis

Jin Zhang et al.

SCIENCE CHINA-CHEMISTRY (2019)

Article Automation & Control Systems

Combination of heuristic optimal partner bands for variable selection in near-infrared spectral analysis

Jin Zhang et al.

JOURNAL OF CHEMOMETRICS (2018)

Review Chemistry, Analytical

Near infrared spectroscopy: A mature analytical technique with new perspectives - A review

Celio Pasquini

ANALYTICA CHIMICA ACTA (2018)

Article Computer Science, Artificial Intelligence

Recent advances in convolutional neural networks

Jiuxiang Gu et al.

PATTERN RECOGNITION (2018)

Article Automation & Control Systems

Selecting temperature-dependent variables in near-infrared spectra for aquaphotomics

Xiaoyu Cui et al.

CHEMOMETRICS AND INTELLIGENT LABORATORY SYSTEMS (2018)

Article Instruments & Instrumentation

Fiber-Content Measurement of Wool-Cashmere Blends Using Near-Infrared Spectroscopy

Jinfeng Zhou et al.

APPLIED SPECTROSCOPY (2017)

Article Chemistry, Analytical

Convolutional neural networks for vibrational spectroscopic data analysis

Jacopo Acquarelli et al.

ANALYTICA CHIMICA ACTA (2017)

Article Chemistry, Analytical

Using variable combination population analysis for variable selection in multivariate calibration

Yong-Huan Yun et al.

ANALYTICA CHIMICA ACTA (2015)

Article Automation & Control Systems

Variable selection based on locally linear embedding mapping for near-infrared spectral analysis

Ruifeng Shan et al.

CHEMOMETRICS AND INTELLIGENT LABORATORY SYSTEMS (2014)

Article Chemistry, Analytical

Multivariate calibration of near-infrared spectra by using influential variables

Xueguang Shao et al.

ANALYTICAL METHODS (2012)

Review Automation & Control Systems

A review of variable selection methods in Partial Least Squares Regression

Tahir Mehmood et al.

CHEMOMETRICS AND INTELLIGENT LABORATORY SYSTEMS (2012)

Article Chemistry, Analytical

Model-population analysis and its applications in chemical and biological modeling

Hong-Dong Li et al.

TRAC-TRENDS IN ANALYTICAL CHEMISTRY (2012)

Article Automation & Control Systems

A wavelength selection method based on randomization test for near-infrared spectral analysis

Heng Xu et al.

CHEMOMETRICS AND INTELLIGENT LABORATORY SYSTEMS (2009)

Article Automation & Control Systems

A variable selection method based on uninformative variable elimination for multivariate calibration of near-infrared spectra

Wensheng Cai et al.

CHEMOMETRICS AND INTELLIGENT LABORATORY SYSTEMS (2008)

Article Chemistry, Analytical

Assuring specificity for a multivariate near-infrared (NIR) calibration: The example of the Chambersburg Shoot-out 2002 data set

Karl H. Norris et al.

JOURNAL OF PHARMACEUTICAL AND BIOMEDICAL ANALYSIS (2008)