Hyperspectral detection of walnut protein contents based on improved whale optimized algorithm
Keywords:
walnut protein, hyperspectral image, whale optimized algorithm, feature selection, textural indicatorAbstract
Nondestructive and accurate estimation of walnut kernel protein content is important for food quality grading and profitability improvement of walnut packinghouses. Hyperspectral image technology provides potential solutions for walnuts nutrients detection by obtaining both spectral and textural information. However, the redundancy and large computation of spectral data prevent the widespread application of hyperspectral technology for high throughput evaluation. For walnut kernel protein inversion from hyperspectral image, this study proposed a novel feature selection method, which is named as improved whale optimized algorithm (IWOA). In the IWOA, a comprehensive feature selection criterion was applied in the iterative process, which fully considered the relevance of spectra information with target variables, representative ability of the selected wavebands to entire spectra, and redundancy of the selected wavebands. Especially in the relevance with target variables, the amplitude and shape characteristics of the spectra were both taken into consideration. Eight wavelengths around 996, 1225, 1232, 1377, 1552, 1600, 1691 and 1700 nm were then selected as the sensitive wavelengths to walnut protein. These wavelengths showed good correlation with certain chemical compounds related to protein contents mechanistically. Then three protein prediction models were established. After analysis and comparison, the model based on the selected wavelengths got better results with the one based on the full spectrum. Compared to the models based on solely spectral information, the model that combine spectral and textural information outperformed and got the best prediction results. The R2 in the calibration group was 0.9047, and the root mean square errors (RMSE) was 11.1382 g/kg. In the validation group, the R2 was 0.8537, and the RMSE was 18.9288 g/kg. The results demonstrated that the combination of the selected wavelengths through the IWOA with the textural characteristics could effectively estimate walnut protein contents. And the proposed method can be extended to the detection and inversion of other nutritional variables of nuts. Keywords: walnut protein, hyperspectral image, whale optimized algorithm, feature selection, textural indicator DOI: 10.25165/j.ijabe.20221506.7179 Citation: Zhang Y, Tian Z Z, Ma W Q, Zhang M, Yang L L. Hyperspectral detection of walnut protein contents based on improved whale optimized algorithm. Int J Agric & Biol Eng, 2022; 15(6): 235–241.References
[1] Mao X Y, Hua Y F. Composition, Structure and Functional Properties of Protein Concentrates and Isolates Produced from Walnut (Juglans regia L.). International Journal of Molecular Sciences, 2012; 13(2): 1561–1581.
[2] Mohammadi M T, Razavi S M A, Taghizadeh M. Applications of hyperspectral imaging in grains and nuts quality and safety assessment: a review. Journal of Food Measurement and Characterization, 2013; 7(3): 129–140.
[3] Vohland M, Besold J, Hill J, Fründ H. Comparing different multivariate calibration methods for the determination of soil organic carbon pools with visible to near infrared spectroscopy. Geoderma, 2011; 166(1): 198–205.
[4] Gholizadeh A, Neumann C, Chabrillat S, Wesemael B, Castaldi F, Borůvka L. Soil organic carbon estimation using VNIR–SWIR spectroscopy: The effect of multiple sensors and scanning conditions. Soil and Tillage Research, 2021; 211: 105017. doi: 10.1016/j.still.2021.105017.
[5] Pullanagari R R, Dehghan-Shoar M, Yule I J, Bhatia N. Field spectroscopy of canopy nitrogen concentration in temperate grasslands using a convolutional neural network. Remote Sensing of Environment, 2021; 257: 112353. doi: 10.1016/j.rse.2021.112353.
[6] An X F, Li M Z, Zheng L H, Liu Y M, Sun H. A portable soil nitrogen detector based on NIRS. Precision Agriculture, 2014; 15(1): 3–16.
[7] Ramirez-Paredes J P, Hernandez-Belmonte U H. Visual quality assessment of malting barley using color, shape and texture descriptors. Computers and Electronics in Agriculture, 2020; 168: 105110. doi:10.1016/j.compag.2019.105110.
[8] Zheng C X, Sun D W, Zheng L Y. Recent applications of image texture for evaluation of food qualities—A review. Trends in Food Science & Technology, 2006; 17(3): 113–128.
[9] Aviara N A, Liberty J T, Olatunbosun O S, Shoyombo H A, Oyeniyi S K. Potential application of hyperspectral imaging in food grain quality inspection, evaluation and control during bulk storage. Journal of Agriculture and Food Research, 2022; 8: 100288. doi: 10.1016/j.jafr.2022.100288.
[10] Caporaso N, Whitworth M B, Fisk I D. Total lipid prediction in single intact cocoa beans by hyperspectral chemical imaging. Food Chemistry, 2021; 344: 128663. doi: 10.1016/j.foodchem.2020.128663.
[11] Feng L, Wu B H, Zhu S S, He Y, Zhang C. Application of visible/infrared spectroscopy and hyperspectral imaging with machine learning techniques for identifying food varieties and geographical origins. Frontiers in Nutrition, 2021; 8: 680357. doi: 10.3389/fnut.2021.680357.
[12] Khamsopha D, Woranitta S, Teerachaichayut S. Utilizing near infrared hyperspectral imaging for quantitatively predicting adulteration in tapioca starch. Food Control, 2021; 123: 107781. doi: 10.1016/j.foodcont.2020.107781.
[13] Zhang C, Liu F, Kong W W, He Y. Application of visible and near-infrared hyperspectral imaging to determine soluble protein content in oilseed rape leaves. Sensors, 2015; 15(7): 16576–16588.
[14] Engstrom O C G, Dreier E S, Pedersen K S. Predicting protein content in grain using hyperspectral deep learning. 2021 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW). Montreal, BC, Canada: IEEE, 2021; pp.1372–1380.
[15] Gomes V, Mendes-Ferreira A, Melo-Pinto P. Application of hyperspectral imaging and deep learning for robust prediction of sugar and pH levels in wine grape berries. Sensors, 2021; 21(10): 3459.
[16] Liu Y S, Zhou S B, Han W, Li C, Liu W X, Qiu Z F, et al. Detection of adulteration in infant formula based on ensemble convolutional neural network and near-infrared spectroscopy. Foods, 2021; 10(4): 785. doi: 10.3390/FOODS10040785.
[17] Wang L, Liu H G, Li T, Li J Q, Wang Y Z. Verified the rapid evaluation of the edible safety of wild porcini mushrooms, using deep learning and PLS‐DA. Journal of the Science of Food and Agriculture, 2022; 102(4): 1531–1539.
[18] Zhang X L, Yang J, Lin T, Ying Y B. Food and agro-product quality evaluation based on spectroscopy and deep learning: A review. Trends in Food Science & Technology, 2021; 112: 431–441.
[19] Zeng J, Guo Y, Han Y Q, Li Z M, Yang Z X, Chai Q Q, et al. A review of the discriminant analysis methods for food quality based on near-infrared spectroscopy and pattern recognition. Molecules, 2021; 26(3): 749. doi: 10.3390/molecules26030749.
[20] Kamilaris A, Prenafeta-Boldú F X. Deep learning in agriculture: A survey. Computers and Electronics in Agriculture, 2018; 147: 70–90.
[21] Wang P, Fan E, Wang P. Comparative analysis of image classification algorithms based on traditional machine learning and deep learning. Pattern Recognition Letters, 2021; 141: 61–67.
[22] Brezočnik L, Fister I, Podgorelec V. Swarm intelligence algorithms for feature selection: A review. Applied Sciences, 2018; 8(9): 1521. doi: 10.3390/app8091521
[23] Kumar A, Jaiswal A. Swarm intelligence based optimal feature selection for enhanced predictive sentiment accuracy on twitter. Multimedia Tools and Applications, 2019; 78(20): 29529–29553.
[24] Nguyen B H, Xue B, Zhang M J. A survey on swarm intelligence approaches to feature selection in data mining. Swarm and Evolutionary Computation, 2020, 54: 100663. doi: 10.1016/j.swevo.2020.100663.
[25] Zhang Y, Lee W S, Li M Z, et al. Non-destructive recognition and classification of citrus fruit blemishes based on ant colony optimized spectral information. Postharvest Biology and Technology, 2018; 143: 119–128.
[26] Trivedi I N, Bhoye M, Bhesdadiya R H, Jangir P, Jangir N, Kumar A. An emission constraint environment dispatch problem solution with microgrid using whale optimization algorithm. 2016 National Power Systems Conference (NPSC). Bhubaneswar, India: IEEE, 2016; pp.1–6.
[27] Mirjalili S, Lewis A. The whale optimization algorithm. Advances in Engineering Software, 2016; 95: 51–67.
[28] Mafarja M M, Mirjalili S. Hybrid whale optimization algorithm with simulated annealing for feature selection. Neurocomputing, 2017; 260: 302–312.
[29] Mafarja M, Mirjalili S. Whale optimization approaches for wrapper feature selection. Applied Soft Computing, 2018; 62: 441–453.
[30] Wang M W, Jia Z T, Luo J W, Chen M L, Wang S P, Ye Z W. A hyperspectral image classification method based on weight wavelet kernel joint sparse representation ensemble and β-whale optimization algorithm. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2021; 14: 2535–2550.
[31] Haralick R M, Shanmugam K, Dinstein I. Textural features for image classification. IEEE Transactions on Systems, Man, and Cybernetics, 1973; SMC-3(6): 610–621.
[32] Shao Y N, He Y, Cao F. Identification of rough rice species and years by visible/near-infrared reflectance spectroscopy. 2006 International Conference on Computational Intelligence and Security. Guangzhou, China: IEEE, 2006; pp.988–991.
[33] Tallada J G, Palacios-Rojas N, Armstrong P R. Prediction of maize seed attributes using a rapid single kernel near infrared instrument. Journal of Cereal Science, 2009; 50(3): 381–387.
[34] Nagao A, Uozumi J, Iwamoto M, et al. Determination of fat content in meats by near-infrared reflectance spectroscopy. Journal of Japan Oil Chemists’ Society, 1985; 34(4): 257–261.
[35] Devi K R, Srinivasan K. Synthesis, growth, morphology and characterization of ferroelectric glycine phosphite single crystals. Crystal Research and Technology, 2011; 46(12): 1265–1272.
[36] Yadav T K, Narayanaswamy R, Abu Bakar M H, Mustapha Kamil Y, Mahdi M A. Single mode tapered fiber-optic interferometer based refractive index sensor and its application to protein sensing. Optics Express, 2014; 22(19): 22802. doi: 10.1364/OE.22.022802.
[37] Capus J M, Cockcroft M G. A new technique for investigating surface flow in metal-working processes. Nature, 1954; 173(4409): 821–821.
[38] Nogales-Bueno J, Baca-Bocanegra B, Hernández-Hierro J M, Garcia R, Barroso J M, Heredia F J, et al. Assessment of total fat and fatty acids in walnuts using near-infrared hyperspectral imaging. Frontiers in Plant Science, 2021; 12: 729880. doi: 10.3389/fpls.2021.729880.
[39] Zhao X, Wang W, Ni X Z, Chu X, Li Y F, Sun C P. Evaluation of Near-Infrared Hyperspectral Imaging for Detection of Peanut and Walnut Powders in Whole Wheat Flour. Applied Sciences, 2018; 8(7): 1076. doi: 10.3390/app8071076.
[40] Rao G D, Sui J K, Zhang J G. Metabolomics reveals significant variations in metabolites and correlations regarding the maturation of walnuts ( Juglans regia L.). Biology Open, 2016; 5(6): 829–836.
[2] Mohammadi M T, Razavi S M A, Taghizadeh M. Applications of hyperspectral imaging in grains and nuts quality and safety assessment: a review. Journal of Food Measurement and Characterization, 2013; 7(3): 129–140.
[3] Vohland M, Besold J, Hill J, Fründ H. Comparing different multivariate calibration methods for the determination of soil organic carbon pools with visible to near infrared spectroscopy. Geoderma, 2011; 166(1): 198–205.
[4] Gholizadeh A, Neumann C, Chabrillat S, Wesemael B, Castaldi F, Borůvka L. Soil organic carbon estimation using VNIR–SWIR spectroscopy: The effect of multiple sensors and scanning conditions. Soil and Tillage Research, 2021; 211: 105017. doi: 10.1016/j.still.2021.105017.
[5] Pullanagari R R, Dehghan-Shoar M, Yule I J, Bhatia N. Field spectroscopy of canopy nitrogen concentration in temperate grasslands using a convolutional neural network. Remote Sensing of Environment, 2021; 257: 112353. doi: 10.1016/j.rse.2021.112353.
[6] An X F, Li M Z, Zheng L H, Liu Y M, Sun H. A portable soil nitrogen detector based on NIRS. Precision Agriculture, 2014; 15(1): 3–16.
[7] Ramirez-Paredes J P, Hernandez-Belmonte U H. Visual quality assessment of malting barley using color, shape and texture descriptors. Computers and Electronics in Agriculture, 2020; 168: 105110. doi:10.1016/j.compag.2019.105110.
[8] Zheng C X, Sun D W, Zheng L Y. Recent applications of image texture for evaluation of food qualities—A review. Trends in Food Science & Technology, 2006; 17(3): 113–128.
[9] Aviara N A, Liberty J T, Olatunbosun O S, Shoyombo H A, Oyeniyi S K. Potential application of hyperspectral imaging in food grain quality inspection, evaluation and control during bulk storage. Journal of Agriculture and Food Research, 2022; 8: 100288. doi: 10.1016/j.jafr.2022.100288.
[10] Caporaso N, Whitworth M B, Fisk I D. Total lipid prediction in single intact cocoa beans by hyperspectral chemical imaging. Food Chemistry, 2021; 344: 128663. doi: 10.1016/j.foodchem.2020.128663.
[11] Feng L, Wu B H, Zhu S S, He Y, Zhang C. Application of visible/infrared spectroscopy and hyperspectral imaging with machine learning techniques for identifying food varieties and geographical origins. Frontiers in Nutrition, 2021; 8: 680357. doi: 10.3389/fnut.2021.680357.
[12] Khamsopha D, Woranitta S, Teerachaichayut S. Utilizing near infrared hyperspectral imaging for quantitatively predicting adulteration in tapioca starch. Food Control, 2021; 123: 107781. doi: 10.1016/j.foodcont.2020.107781.
[13] Zhang C, Liu F, Kong W W, He Y. Application of visible and near-infrared hyperspectral imaging to determine soluble protein content in oilseed rape leaves. Sensors, 2015; 15(7): 16576–16588.
[14] Engstrom O C G, Dreier E S, Pedersen K S. Predicting protein content in grain using hyperspectral deep learning. 2021 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW). Montreal, BC, Canada: IEEE, 2021; pp.1372–1380.
[15] Gomes V, Mendes-Ferreira A, Melo-Pinto P. Application of hyperspectral imaging and deep learning for robust prediction of sugar and pH levels in wine grape berries. Sensors, 2021; 21(10): 3459.
[16] Liu Y S, Zhou S B, Han W, Li C, Liu W X, Qiu Z F, et al. Detection of adulteration in infant formula based on ensemble convolutional neural network and near-infrared spectroscopy. Foods, 2021; 10(4): 785. doi: 10.3390/FOODS10040785.
[17] Wang L, Liu H G, Li T, Li J Q, Wang Y Z. Verified the rapid evaluation of the edible safety of wild porcini mushrooms, using deep learning and PLS‐DA. Journal of the Science of Food and Agriculture, 2022; 102(4): 1531–1539.
[18] Zhang X L, Yang J, Lin T, Ying Y B. Food and agro-product quality evaluation based on spectroscopy and deep learning: A review. Trends in Food Science & Technology, 2021; 112: 431–441.
[19] Zeng J, Guo Y, Han Y Q, Li Z M, Yang Z X, Chai Q Q, et al. A review of the discriminant analysis methods for food quality based on near-infrared spectroscopy and pattern recognition. Molecules, 2021; 26(3): 749. doi: 10.3390/molecules26030749.
[20] Kamilaris A, Prenafeta-Boldú F X. Deep learning in agriculture: A survey. Computers and Electronics in Agriculture, 2018; 147: 70–90.
[21] Wang P, Fan E, Wang P. Comparative analysis of image classification algorithms based on traditional machine learning and deep learning. Pattern Recognition Letters, 2021; 141: 61–67.
[22] Brezočnik L, Fister I, Podgorelec V. Swarm intelligence algorithms for feature selection: A review. Applied Sciences, 2018; 8(9): 1521. doi: 10.3390/app8091521
[23] Kumar A, Jaiswal A. Swarm intelligence based optimal feature selection for enhanced predictive sentiment accuracy on twitter. Multimedia Tools and Applications, 2019; 78(20): 29529–29553.
[24] Nguyen B H, Xue B, Zhang M J. A survey on swarm intelligence approaches to feature selection in data mining. Swarm and Evolutionary Computation, 2020, 54: 100663. doi: 10.1016/j.swevo.2020.100663.
[25] Zhang Y, Lee W S, Li M Z, et al. Non-destructive recognition and classification of citrus fruit blemishes based on ant colony optimized spectral information. Postharvest Biology and Technology, 2018; 143: 119–128.
[26] Trivedi I N, Bhoye M, Bhesdadiya R H, Jangir P, Jangir N, Kumar A. An emission constraint environment dispatch problem solution with microgrid using whale optimization algorithm. 2016 National Power Systems Conference (NPSC). Bhubaneswar, India: IEEE, 2016; pp.1–6.
[27] Mirjalili S, Lewis A. The whale optimization algorithm. Advances in Engineering Software, 2016; 95: 51–67.
[28] Mafarja M M, Mirjalili S. Hybrid whale optimization algorithm with simulated annealing for feature selection. Neurocomputing, 2017; 260: 302–312.
[29] Mafarja M, Mirjalili S. Whale optimization approaches for wrapper feature selection. Applied Soft Computing, 2018; 62: 441–453.
[30] Wang M W, Jia Z T, Luo J W, Chen M L, Wang S P, Ye Z W. A hyperspectral image classification method based on weight wavelet kernel joint sparse representation ensemble and β-whale optimization algorithm. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2021; 14: 2535–2550.
[31] Haralick R M, Shanmugam K, Dinstein I. Textural features for image classification. IEEE Transactions on Systems, Man, and Cybernetics, 1973; SMC-3(6): 610–621.
[32] Shao Y N, He Y, Cao F. Identification of rough rice species and years by visible/near-infrared reflectance spectroscopy. 2006 International Conference on Computational Intelligence and Security. Guangzhou, China: IEEE, 2006; pp.988–991.
[33] Tallada J G, Palacios-Rojas N, Armstrong P R. Prediction of maize seed attributes using a rapid single kernel near infrared instrument. Journal of Cereal Science, 2009; 50(3): 381–387.
[34] Nagao A, Uozumi J, Iwamoto M, et al. Determination of fat content in meats by near-infrared reflectance spectroscopy. Journal of Japan Oil Chemists’ Society, 1985; 34(4): 257–261.
[35] Devi K R, Srinivasan K. Synthesis, growth, morphology and characterization of ferroelectric glycine phosphite single crystals. Crystal Research and Technology, 2011; 46(12): 1265–1272.
[36] Yadav T K, Narayanaswamy R, Abu Bakar M H, Mustapha Kamil Y, Mahdi M A. Single mode tapered fiber-optic interferometer based refractive index sensor and its application to protein sensing. Optics Express, 2014; 22(19): 22802. doi: 10.1364/OE.22.022802.
[37] Capus J M, Cockcroft M G. A new technique for investigating surface flow in metal-working processes. Nature, 1954; 173(4409): 821–821.
[38] Nogales-Bueno J, Baca-Bocanegra B, Hernández-Hierro J M, Garcia R, Barroso J M, Heredia F J, et al. Assessment of total fat and fatty acids in walnuts using near-infrared hyperspectral imaging. Frontiers in Plant Science, 2021; 12: 729880. doi: 10.3389/fpls.2021.729880.
[39] Zhao X, Wang W, Ni X Z, Chu X, Li Y F, Sun C P. Evaluation of Near-Infrared Hyperspectral Imaging for Detection of Peanut and Walnut Powders in Whole Wheat Flour. Applied Sciences, 2018; 8(7): 1076. doi: 10.3390/app8071076.
[40] Rao G D, Sui J K, Zhang J G. Metabolomics reveals significant variations in metabolites and correlations regarding the maturation of walnuts ( Juglans regia L.). Biology Open, 2016; 5(6): 829–836.
Downloads
Published
2022-12-27
How to Cite
Zhang, Y., Tian, Z., Ma, W., Zhang, M., & Yang, L. (2022). Hyperspectral detection of walnut protein contents based on improved whale optimized algorithm. International Journal of Agricultural and Biological Engineering, 15(6), 235–241. Retrieved from https://ijabe.migration.pkpps03.publicknowledgeproject.org/index.php/ijabe/article/view/7179
Issue
Section
Agro-product and Food Processing Systems
License
IJABE is an international peer reviewed open access journal, adopting Creative Commons Copyright Notices as follows.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
