Modern practical convolutional neural networks for multivariate regression: Applications to NIR calibration

Abstract

In this study, we investigate the use of convolutional neural networks (CNN) for near infrared (NIR) calibration. We propose a unified CNN structure that can be used for general multivariate regression purpose. The comparison between the CNN method and the partial least squares regression (PLSR) method was done on three different NIR datasets of spectra and lab reference values. Datasets are from different sources and contain 6998, 1000 and 415 training and 618, 597 and 108 validation samples, respectively. Results indicated that compared to the PLSR models, the CNN models are more accurate and less noisy. The convolutional layer in the CNN model can automatically find the suitable spectral preprocessing filter on the dataset, which significantly saves efforts in training the model.

A practical convolutional neural network model for discriminating Raman spectra of human and animal blood

“…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.…”

“…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.…”

Combining convolutional neural networks and in‐line near‐infrared spectroscopy for real‐time monitoring of the chromatographic elution process in commercial production of notoginseng total saponins

“…Deep learning allows models composed of multiple processing layers to learn multiple levels of representations and can discover intricate structures from high-dimensional data [19]. Recently, CNNs have been successfully used for classification tasks in IR [15], NIR [15], Raman [15,21] spectral analysis, and used for regression tasks in IR [22], NIR [22][23][24][25][26], Raman [27] spectral analysis. Recently, CNNs have been successfully used for classification tasks in IR [15], NIR [15], Raman [15,21] spectral analysis, and used for regression tasks in IR [22], NIR [22][23][24][25][26], Raman [27] spectral analysis.…”

“…Convolutional neural networks (CNNs), one of the most popular deep learning methods, have brought breakthroughs in processing images, video, speech, and audio [19], and are still growing at a rapid pace [20]. These studies have indicated that the CNN modeling method can have better model performance in some cases compared with some traditional machine learning methods [23,24,26], even when raw spectral data without any preprocessing were used as model inputs in the studies conducted by Acquarelli et al [15] and Zhang et al [24]. These studies have indicated that the CNN modeling method can have better model performance in some cases compared with some traditional machine learning methods [23,24,26], even when raw spectral data without any preprocessing were used as model inputs in the studies conducted by Acquarelli et al [15] and Zhang et al [24].…”

“…Recently, CNNs have been successfully used for classification tasks in IR [15], NIR [15], Raman [15,21] spectral analysis, and used for regression tasks in IR [22], NIR [22][23][24][25][26], Raman [27] spectral analysis. Moreover, Cui et al [23] have reported the "automatic preprocessing" function of the convolutional layer by visualizing convolutional layer outputs, which can give an explanation why CNN models using raw spectral data as inputs still have satisfactory performance in some reported cases. Moreover, Cui et al [23] have reported the "automatic preprocessing" function of the convolutional layer by visualizing convolutional layer outputs, which can give an explanation why CNN models using raw spectral data as inputs still have satisfactory performance in some reported cases.…”