A deep learning based feature extraction method on hyperspectral images for nondestructive prediction of TVB-N content in Pacific white shrimp (Litopenaeus vannamei)

Hyperspectral imaging (HSI) technique with spectral range of 900–1700 nm was implemented to predict total volatile basic nitrogen (TVB-N) content in Pacific white shrimp. Successive projections algorithm (SPA) and deep-learning-based stacked auto-encoders (SAEs) algorithm were comparatively used for spectral feature extraction. Least-squares support vector machine (LS-SVM), partial least squares regression (PLSR) and multiple linear regression (MLR) were used for prediction. The results demonstrated that the SAEs-based prediction models (SAEs-LS-SVM, SAEs-MLR and SAEs-PLSR) performed better than either full wavelengths-based or SPA-based prediction models. The SAEs-LS-SVM was considered to be the best model with RP2 value of 0.921, RMSEP value of 6.22 mg N [100 g]−1, RPD value of 3.58 and computational time of 3.9 ms for predicting TVB-N in prediction set. The results of this study indicated that SAEs has a high potential in the multivariate analysis of hyperspectral images for shrimp quality inspections.

[1]  Aminah Abdullah,et al.  Real-Time Monitoring of Shrimp Spoilage Using On-Package Sticker Sensor Based on Natural Dye of Curcumin , 2012, Food Analytical Methods.

[2]  Jiewen Zhao,et al.  Nondestructive measurement of total volatile basic nitrogen (TVB-N) content in salted pork in jelly using a hyperspectral imaging technique combined with efficient hypercube processing algorithms , 2013 .

[3]  S. Benjakul,et al.  Melanosis and quality changes of Pacific white shrimp (Litopenaeus vannamei) treated with catechin during iced storage. , 2009, Journal of agricultural and food chemistry.

[4]  Johan A. K. Suykens,et al.  Weighted least squares support vector machines: robustness and sparse approximation , 2002, Neurocomputing.

[5]  Da-Wen Sun,et al.  Hyperspectral imaging as an effective tool for quality analysis and control of fish and other seafoods: Current research and potential applications , 2014 .

[6]  Qibing Zhu,et al.  Model fusion for prediction of apple firmness using hyperspectral scattering image , 2012 .

[7]  Jun Yu,et al.  Coupled Deep Autoencoder for Single Image Super-Resolution , 2017, IEEE Transactions on Cybernetics.

[8]  D. P. Ariana,et al.  Evaluation of internal defect and surface color of whole pickles using hyperspectral imaging. , 2010 .

[9]  Trevor Darrell,et al.  DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition , 2013, ICML.

[10]  Geoffrey E. Hinton,et al.  Binary coding of speech spectrograms using a deep auto-encoder , 2010, INTERSPEECH.

[11]  Anthony J. Durkin,et al.  Review of short-wave infrared spectroscopy and imaging methods for biological tissue characterization , 2015, Journal of biomedical optics.

[12]  E. Fan,et al.  Extended tanh-function method and its applications to nonlinear equations , 2000 .

[13]  Li Huang,et al.  Accelerated Monte Carlo simulations with restricted Boltzmann machines , 2016, 1610.02746.

[14]  Yong He,et al.  Potential of hyperspectral imaging and multivariate analysis for rapid and non-invasive detection of gelatin adulteration in prawn , 2013 .

[15]  Dong Yu,et al.  Improved Bottleneck Features Using Pretrained Deep Neural Networks , 2011, INTERSPEECH.

[16]  Gamal ElMasry,et al.  Non-destructive assessment of instrumental and sensory tenderness of lamb meat using NIR hyperspectral imaging. , 2013, Food chemistry.

[17]  Jürgen Schmidhuber,et al.  Deep learning in neural networks: An overview , 2014, Neural Networks.

[18]  D. Jayas,et al.  Identification of wheat classes using wavelet features from near infrared hyperspectral images of bulk samples. , 2009 .

[19]  Da-Wen Sun,et al.  Recent Advances in Data Mining Techniques and Their Applications in Hyperspectral Image Processing for the Food Industry , 2014 .

[20]  Jiewen Zhao,et al.  Nondestructive quantifying total volatile basic nitrogen (TVB-N) content in chicken using hyperspectral imaging (HSI) technique combined with different data dimension reduction algorithms. , 2016, Food chemistry.

[21]  C. Okpala,et al.  Quality and shelf life assessment of Pacific white shrimp (Litopenaeus vannamei) freshly harvested and stored on ice , 2014 .

[22]  Yu-Ru Huang,et al.  Changes in Biochemical Compositions and Quality of White Shrimp (Litopenaeus vannamei) During Storage , 2016 .

[23]  Di Wu,et al.  Potential of time series-hyperspectral imaging (TS-HSI) for non-invasive determination of microbial spoilage of salmon flesh. , 2013, Talanta.

[24]  Yidan Bao,et al.  Rapid prediction of moisture content of dehydrated prawns using online hyperspectral imaging system. , 2012, Analytica chimica acta.

[25]  Sung-Kwun Oh,et al.  Design of Fuzzy k-Nearest Neighbors Classifiers based on Feature Extraction by using Stacked Autoencoder , 2015 .

[26]  Simon J. Doran,et al.  Stacked Autoencoders for Unsupervised Feature Learning and Multiple Organ Detection in a Pilot Study Using 4D Patient Data , 2013, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[27]  R. V. Rossel,et al.  Determining the composition of mineral-organic mixes using UV–vis–NIR diffuse reflectance spectroscopy , 2006 .

[28]  Jiewen Zhao,et al.  Nondestructive measurement of total volatile basic nitrogen (TVB-N) in pork meat by integrating near infrared spectroscopy, computer vision and electronic nose techniques. , 2014, Food chemistry.

[29]  Da-Wen Sun,et al.  Non-destructive and rapid determination of TVB-N content for freshness evaluation of grass carp (Ctenopharyngodon idella) by hyperspectral imaging , 2014 .

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

[31]  Xing Zhao,et al.  Spectral–Spatial Classification of Hyperspectral Data Based on Deep Belief Network , 2015, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

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

[33]  J. Xie,et al.  Inhibitory effect of a quercetin-based soaking formulation and modified atmospheric packaging (MAP) on muscle degradation of Pacific white shrimp (Litopenaeus vannamei) , 2015 .

[34]  S. I. V. Sousa,et al.  Multiple linear regression and artificial neural networks based on principal components to predict ozone concentrations , 2007, Environ. Model. Softw..

[35]  P. Kyriacou,et al.  Use of reflectance near-infrared spectroscopy to investigate the effects of daily moisturizer application on skin optical response and barrier function. , 2014, Journal of biomedical optics.