Moisture Content Quantization of Masson Pine Seedling Leaf Based on Stacked Autoencoder with Near-Infrared Spectroscopy

Masson pine is widely planted in southern China, and moisture content of the pine seedling leaves is an important index for evaluating the vigor of seedlings. For precisely predicting leaf moisture content, near-infrared spectroscopy analysis is applied in the experiment, which is a cost-effective, high-speed, and noninvasive material content prediction tool. To further improve the spectroscopy analysis accuracy, in this study, a new analysis model is proposed which integrates a stacked autoencoder for extracting hierarchical output-related features layer by layer and a support vector regression model to leverage these features for precisely predicting moisture contents. Compared with traditional spectroscopy analysis method like partial least squares regression and basic support vector regression, the proposed model shows great superiority for leaf moisture content prediction, with R2 value 0.9946 and root-mean squared error (RMSE) value 0.1636 in calibration set and R2 value 0.9621 and RMSE 0.4249 in prediction set.

[1]  Yike Guo,et al.  Feature extraction with stacked autoencoders for epileptic seizure detection , 2014, 2014 36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[2]  Engin Avci.  Selecting of the optimal feature subset and kernel parameters in digital modulation classification by using hybrid genetic algorithm-support vector machines: HGASVM , 2009, Expert Syst. Appl..

[3]  J. Posom,et al.  Evaluation of the moisture content of Jatropha curcas kernels and the heating value of the oil-extracted residue using near-infrared spectroscopy , 2015 .

[4]  Heping Zhu,et al.  Plant Pest Detection Using an Artificial Nose System: A Review , 2018, Sensors.

[5]  D. Centeno,et al.  Physiological responses to water deficit and changes in leaf cell wall composition as modulated by seasonality in the Brazilian resurrection plant Barbacenia purpurea , 2016 .

[6]  S. Wold,et al.  PLS-regression: a basic tool of chemometrics , 2001 .

[7]  Roman M. Balabin,et al.  Neural network (ANN) approach to biodiesel analysis: Analysis of biodiesel density, kinematic viscosity, methanol and water contents using near infrared (NIR) spectroscopy , 2011 .

[8]  Svein Solberg,et al.  Assessments of tree crown condition of two Masson pine forests in the acid rain region in south China , 2007 .

[9]  Wenting Han,et al.  Leaf Chlorophyll Content Estimation of Winter Wheat Based on Visible and Near-Infrared Sensors , 2016, Sensors.

[10]  R. Meder,et al.  Monitoring water potential and relative water content in Eucalyptus Camaldulensis using near infrared spectroscopy , 2017 .

[11]  S. O. Ferreira,et al.  Estimation of leaf water content in sunflower under drought conditions by means of spectral reflectance , 2017 .

[12]  L. Duponchel,et al.  Support vector machines (SVM) in near infrared (NIR) spectroscopy: Focus on parameters optimization and model interpretation , 2009 .

[13]  Xiao Wang,et al.  Soft sensor based on stacked auto-encoder deep neural network for air preheater rotor deformation prediction , 2018, Adv. Eng. Informatics.

[14]  Yansheng Li,et al.  Unsupervised Spectral–Spatial Feature Learning With Stacked Sparse Autoencoder for Hyperspectral Imagery Classification , 2015, IEEE Geoscience and Remote Sensing Letters.

[15]  Tawfik A. Saleh,et al.  Statistical analysis of phenols adsorption on diethylenetriamine-modified activated carbon , 2018 .

[16]  Florian Metze,et al.  Extracting deep bottleneck features using stacked auto-encoders , 2013, 2013 IEEE International Conference on Acoustics, Speech and Signal Processing.

[17]  Leona S. Aiken,et al.  Multiple Linear Regression , 2003 .

[18]  Yoshua Bengio,et al.  Extracting and composing robust features with denoising autoencoders , 2008, ICML '08.

[19]  B. Leblon,et al.  Determination of moisture content and basic specific gravity of Populus tremuloides (Michx.) and Populus balsamifera (L.) logs using a portable near-infrared spectrometer , 2015 .

[20]  Pascal Vincent,et al.  Stacked Denoising Autoencoders: Learning Useful Representations in a Deep Network with a Local Denoising Criterion , 2010, J. Mach. Learn. Res..

[21]  Sunday Olusanya Olatunji,et al.  Predicting of the refractive index of haemoglobin using the Hybrid GA-SVR approach , 2018, Comput. Biol. Medicine.

[22]  Rongnian Tang,et al.  Detection of Nitrogen Content in Rubber Leaves Using Near-Infrared (NIR) Spectroscopy with Correlation-Based Successive Projections Algorithm (SPA) , 2018, Applied spectroscopy.

[23]  Mohd Amiruddin Abd Rahman,et al.  Estimating the refractive index of oxygenated and deoxygenated hemoglobin using genetic algorithm - support vector regression model , 2018, Comput. Methods Programs Biomed..

[24]  Yee Whye Teh,et al.  A Fast Learning Algorithm for Deep Belief Nets , 2006, Neural Computation.

[25]  Biao Huang,et al.  Deep Learning-Based Feature Representation and Its Application for Soft Sensor Modeling With Variable-Wise Weighted SAE , 2018, IEEE Transactions on Industrial Informatics.

[26]  L. Buydens,et al.  Visualisation and interpretation of Support Vector Regression models. , 2007, Analytica chimica acta.

[27]  Shirong Liu,et al.  Positive interactions between Pinus massoniana and Castanopsis hystrix species in the uneven-aged mixed plantations can produce more ecosystem carbon in subtropical China , 2017 .