2017
DOI: 10.1002/cem.2977
|View full text |Cite
|
Sign up to set email alerts
|

One‐dimensional convolutional neural networks for spectroscopic signal regression

Abstract: This paper proposes a novel approach for driving chemometric analyses from spectroscopic data and based on a convolutional neural network (CNN) architecture. For such purpose, the well‐known 2‐D CNN is adapted to the monodimensional nature of spectroscopic data. In particular, filtering and pooling operations as well as equations for training are revisited. We also propose an alternative to train the resulting 1D‐CNN by means of particle swarm optimization. The resulting trained CNN architecture is successivel… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
5

Citation Types

0
97
0

Year Published

2019
2019
2023
2023

Publication Types

Select...
8

Relationship

0
8

Authors

Journals

citations
Cited by 192 publications
(101 citation statements)
references
References 32 publications
0
97
0
Order By: Relevance
“…In contrast to an artificial neural network, the convolution layer in CNN allows the model to extract small details and to be trained on the extracted details of the input data, which improves its prediction accuracy . Since then, CNNs have been widely used for image recognition or image classification, and there were several trials to use artificial intelligence algorithm to study Raman spectral data as well as different types of spectroscopic data . In this study, we suggest a platform for Raman signature classification of EVs based on CNN.…”
Section: Introductionmentioning
confidence: 99%
“…In contrast to an artificial neural network, the convolution layer in CNN allows the model to extract small details and to be trained on the extracted details of the input data, which improves its prediction accuracy . Since then, CNNs have been widely used for image recognition or image classification, and there were several trials to use artificial intelligence algorithm to study Raman spectral data as well as different types of spectroscopic data . In this study, we suggest a platform for Raman signature classification of EVs based on CNN.…”
Section: Introductionmentioning
confidence: 99%
“…In recent years, deep learning, a more advanced machine learning algorithm capable of learning complex relationships, extracting feature patterns and directly building predictive models from big data, has been applied in numerous fields . Many studies have reported excellent deep learning model performances in the chemistry and biology fields. In this study, we applied a self‐designed convolutional neural network framework named DeepIR to the pulmonary edema fluid spectra involving five causes of death to assess its performance in determining the cause of death.…”
Section: Introductionmentioning
confidence: 99%
“…Deep learning, a technique to extract features of data with multiple processing layers, has shown explosive popularity in recent years. As one of most successful deep learning models, the convolutional neural network (CNN) exhibits several merits, such as requiring little a prior knowledge, no need to design explicit features and strong ability to capture inner structures, which motivated researchers to employ it for spectral analysis . In this paper, we proposed a practical CNN model named Raman‐CNN to discriminate the blood of human from other animals by their Raman spectra.…”
Section: Introductionmentioning
confidence: 99%
“…As one of most successful deep learning models, the convolutional neural network (CNN) 18,19 exhibits several merits, such as requiring little a prior knowledge, no need to design explicit features and strong ability to capture inner structures, which motivated researchers to employ it for spectral analysis. [20][21][22][23] In this paper, we proposed a practical CNN model named Raman-CNN to discriminate the blood of human from other animals by their Raman spectra. In Raman-CNN, the preprocessing and discrimination are combined to a whole unit, which is then trained to learn parameters adaptively from calibration samples.…”
Section: Introductionmentioning
confidence: 99%