Improved Deep CNN with Parameter Initialization for Data Analysis of Near-Infrared Spectroscopy Sensors

• Published in: Sensors (Basel, Switzerland) Vol. 20; no. 3; p. 874
• Main Authors: Wang, Di, Tian, Fengchun, Yang, Simon X, Zhu, Zhiqin, Jiang, Daiyu, Cai, Bin
• Format: Journal Article
• Language: English
• Published: Switzerland MDPI AG 06.02.2020; MDPI
• Subjects: Accuracy; Algorithms; Attenuation; Cameras; Classification; Convolution; convolutional neural network; Cultivation; cultivation region discrimination; Data analysis; Data processing; Infrared analysis; Infrared detectors; Infrared spectra; Methods; Near infrared radiation; Neural networks; nir sensor; Quantitative analysis; Regularization; Sensors; Spectral sensitivity; Spectrum analysis; Support vector machines; Technology assessment; Tobacco industry; cultivation region discrimination; data analysis; convolutional neural network; NIR sensor
• ISSN: 1424-8220; 1424-8220
• DOI: 10.3390/s20030874

Near-infrared (NIR) spectral sensors can deliver the spectral response of light absorbed by materials. Data analysis technology based on NIR sensors has been a useful tool for quality identification. In this paper, an improved deep convolutional neural network (CNN) with batch normalization and MSRA (Microsoft Research Asia) initialization is proposed to discriminate the tobacco cultivation regions using data collected from NIR sensors. The network structure is created with six convolutional layers and three full connection layers, and the learning rate is controlled by exponential attenuation method. One-dimensional kernel is applied as the convolution kernel to extract features. Meanwhile, the methods of L2 regularization and dropout are used to avoid the overfitting problem, which improve the generalization ability of the network. Experimental results show that the proposed deep network structure can effectively extract the complex characteristics inside the spectrum, which proves that it has excellent recognition performance on tobacco cultivation region discrimination, and it also demonstrates that the deep CNN is more suitable for information mining and analysis of big data.