Abstract
Most of the existing methods for wheat mildew detection are biochemical methods, which have the problems of complicated procedures and slow speed. In this paper, a novel wheat mildew detection and classification model is proposed by combining gas chromatography-ion mobility spectrometry (GC-IMS) with a broad learning network (BLN) model. Firstly, the GC-IMS fingerprint spectrums of wheat samples with different degrees of mildew are collected by GC-IMS spectrometer, and then an effective and efficient incremental learning system without the need for deep architecture is constructed to identify these fingerprint spectrums. In the BLN model, ridge regression of the pseudo-inverse is designed to find the desired connection weights, and the new weights can be updated easily by only computing the pseudo-inverse of the corresponding added node. To improve the classification accuracy of the BLN model, incremental learning and the spatial attention mechanism (SAM) are introduced into the model. Experimental results show that the training time of the proposed model is greatly reduced compared to existing deep-learning models. Under the small sample set condition, the mean average accuracy (mAP) of wheat mildew types reaches 90.32%, and the identification precision of early wheat mildew reaches 95.34%. The comprehensive index shows that the neural network model proposed in this paper can be used as an alternative model for deep learning in similar areas of image recognition. The experiment also proved that GC-IMS combined with a broad learning model is an efficient and accurate method for wheat mildew detection.
Similar content being viewed by others
Data Availability
The data supporting the findings of this study are available within the article.
References
Arroyo-Manzanares N, Martin-Gomez A, Jurado-Campos N et al (2018) Target vs spectral fingerprint data analysis of Iberian ham samples for avoiding labelling fraud using headspace - gas chromatography-ion mobility spectrometry. Food Chem 246:65–73
Chen CLP, Liu Z (2018) Broad learning system: an effective and efficient incremental learning system without the need for deep architecture. IEEE T Neur Net Lear 29(1):10–24. https://doi.org/10.1109/TNNLS.2017.2716952
Chen CLP, Wan JZ (1999) A rapid learning and dynamic stepwise updating algorithm for flat neural networks and the application to timeseries prediction. T-SMCB 29(1):62–72. https://doi.org/10.1109/3477.740166
Chen CLP, Liu Z, Feng S (2019) Universal approximation capability of broad learning system and its structural variations. IEEE T Neur Net Lear 30(4):1191–1204. https://doi.org/10.1109/TNNLS.2018.2866622
Franois JM (2006) A simple method for quantitative determination of polysaccharides in fungal cell walls. Nat Protoc 1(6):2995–3000. https://doi.org/10.1038/nprot.2006.457
Gerhardt N, Birkenmeier M, Schwolow S et al (2018) Volatile-compound fingerprinting by headspace - gas - chromatographyion-mobility spectrometry (HS-GC-IMS) as a benchtop alternative to 1H NMR profiling for assessment of the authenticity of honey. Anal Chem 90(3):1777–1785. https://doi.org/10.1021/acs.analchem.7b03748
Golzarian MR, Frick RA (2011) Classification of images of wheat, ryegrass and brome grass species at early growth stages using principal component analysis. Plant Methods 7:28. https://doi.org/10.1186/1746-4811-7-28
Goodwin SB, M’Barek SB, Dhillon B et al (2011) Finished genome of the fungal wheat pathogen mycosphaerella graminicola reveals dispensome structure chromosome plasticity, and stealth pathogenesis. PLoS Genet 7(6):1–17. https://doi.org/10.1371/journal.pgen.1002070
Güldener U, Seong KY, Boddu J et al (2006) Technological Advancement Development of a Fusarium graminearum AVymetrix GeneChip for proWling fungal gene expression in vitro and in planta. Fungal Genet Biol 43(5):316–325. https://doi.org/10.1016/j.fgb.2006.01.005
Hinton G (2009) Deep belief networks. Scholarpedia 4(6):5947. https://doi.org/10.4249/scholarpedia.5947
Hossain MZ, Goto T (2014) A rapid determination of ergosterol in grains using gas chromatography-mass spectrometry method without derivatization. Food Anal Methods 8(4):1–6. https://doi.org/10.1007/s12161-014-9983-7
Hu P, Yang W, Wang X et al (2022) Contact-free wheat mildew detection with commodity wifi. Int J Cogn Comput Eng 3:9–23. https://doi.org/10.1016/j.ijcce.2022.01.001
Isidorov V, Tyszkiewicz Z, Pironikow E (2016) Fungal succession in relation to volatile organic compounds emissions from Scots pine and Norway spruce leaf litter-decomposing fungi. Atmos Environ 131:301–306. https://doi.org/10.1016/j.atmosenv.2016.02.015
Ji F, Li H, Xu J et al (2011) Enzyme-Linked Immunosorbent-Assay for Deoxynivalenol (DON). Toxins 3(8):968–978. https://doi.org/10.3390/toxins3080968
Jiang Y, Ge H, Lian F et al (2016) Early detection of germinated wheat grains using terahertz image and chemometrics. Sci Rep 6(1):21299. https://doi.org/10.1038/srep21299
Jing K, Huang H, Jin X et al (2019) Development of Online Detection System of Grain Mildew Based on E-nose. J Chin Cereals Oils Assoc 34(2):118–124+129
Kim B, Kim J, Ye JC (2023) Task-Agnostic Vision Transformer for Distributed Learning of Image Processing. IEEE Trans Image Process. https://doi.org/10.1109/TIP.2022.3226892
Lecun Y, Bottou L, Bengio Y et al (2001) Gradient-based learning applied to document recognition. In: Intelligent Signal Processing. Wiley-IEEE Press, New York pp 306–351. https://doi.org/10.1109/5.726791
Liu J, Xu H, Wang J et al (2023) Non-invasive diagnosis of fetal arrhythmia based on multi-domain feature and hierarchical extreme learning machine. Biomed Signal Process Control 79:419–429
Morath SU, Hung R, Bennett JW et al (2012) Fungal volatile organic compounds: A review with emphasis on their biotechnological potential. Fungal Biol Rev 26(2–3):73–83. https://doi.org/10.1016/j.fbr.2012.07.001
O’Donnell K, Ward TJ, Geiser DM et al (2004) Genealogical concordance between the mating type locus and seven other nuclear genes supports formal recognition of nine phylogenetically distinct species within the Fusarium graminearum clade. Fungal Genet Biol 41(6):600–623. https://doi.org/10.1016/j.fgb.2004.03.003
Patil RR, Kumar S (2022) Rice transformer: a novel integrated management system for controlling rice diseases. IEEE Access 10:87698–87714. https://doi.org/10.1109/ACCESS.2022.3200688
Pu D, Zhang H, Zhang Y et al (2019) Characterization of the aroma release and perception of white bread during oral processing by gas chromatography-ion mobility spectrometry and temporal dominance of sensations analysis. Food Res Int 123:612–622. https://doi.org/10.1016/j.foodres.2019.05.016
Raninen K, Nenonen R, Jrvel-Reijonen E et al (2021) Comprehensive two-dimensional gas chromatography-mass spectrometry analysis of exhaled breath compounds after whole grain diets. Molecules 26:2667. https://doi.org/10.3390/molecules26092667
Simonyan K, Zisserman A (2014) Very deep convolutional networks for large-scale image recognition. arXiv:1409.1556 [cs.CV] ICLR 2015. https://doi.org/10.48550/arXiv.1409.1556
Srivastava N, Salakhutdinov NR (2012) Multimodal learning with deep boltzmann machines. NIPS 12(2):2222–2230
Ţiplea FL, Drăgoi VF (2022) Generalized inverse based decoding. ISIT 2022:2791–2796. https://doi.org/10.48550/arXiv.2202.08640
Vincent P, Larochelle H, Bengio Y et al (2008) Extracting and composing robust features with denoising autoencoders. ICML 08:1096–1103. https://doi.org/10.1145/1390156.1390294
Wang A, Wan G, Cheng Z, Li S (2011) Incremental learning extremely random forest classifier for online learning. J Softw 22(9):2059–2074. https://doi.org/10.3724/SP.J.1001.2011.03827
Wang H, Zhao G, Qi D, Lu D (2012) Fast incremental learning method for one-class support vector machine. J Zhejiang Univ (engineering Science) 46(7):1327–1332. https://doi.org/10.3785/j.issn.1008-973X.2012.07.027
Wang X, Yang S, He J et al (2019) A green triple-locked strategy based on volatile-compound imaging, chemometrics, and markers to discriminate winter honey and sapium honey using headspace gas chromatography-ion mobility spectrometry. Food Res Int 119:960–967. https://doi.org/10.1016/j.foodres.2019.01.004
Xie J, Sun YZ, Zheng YJ et al (2016) Preparation and application of immunoaffinity column coupled with dcELISA detection for aflatoxins in eight grain foods. Food Control 73(B):445–451. https://doi.org/10.1016/j.foodcont.2016.08.035
Xu Y, Zhang S, Xiao W (2023) Inter-patient ECG classification with intra-class coherence based weighted kernel extreme learning machine. Expert Syst Appl 227:20095.1-20095.12
Xuan C, Wang W, Zheng H et al (2015) Detection of fungus on wheat kernels using FT-NIR Spectroscopy and Fuzzy Neural Network Classifier. Proceedings of 2015 International Packaging and Food Engineering & AGRO-Products Processing Academic annual Conference. Proc Chin Mech Eng Soc, pp 446–447 (in Chinese)
Zhang J, Zhang B, Dong J et al (2022) Identification of mouldy rice using an electronic nose combined with SPME-GC/MS. J Stored Prod Res 95:101921. https://doi.org/10.1016/j.jspr.2021.101921
Zhao Y, Ren F, Li Z et al (2020) Study on the volatile matter of wheat and wheat flour using GC-IMS. Sci Technol Cereals, Oils Foods 28(4):145–151
Zheng H, Zhou Z, Shi P et al (2019) Mildew wheat discrimination by electronic nose and its sensor array optimization. Chin J Sensors Actuators 32(5):688–692+710
Author information
Authors and Affiliations
Contributions
This manuscript was written by M. F. (Maixia Fu) and F. L. (Feiyu Lian). The experiments were carried out by F. L. (Feiyu Lian). The analyses and discussions of these obtained results were carried out by M. F. (Maixia Fu) and F. L. (Feiyu Lian).
Corresponding author
Ethics declarations
Competing interests
The authors declare no competing interests.
Ethical standards
Not involved.
Conflicts of Interest
The authors declare no conflict of interest.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Fu, M., Lian, F. Mildew Detection for Stored Wheat using Gas Chromatography–Ion Mobility Spectrometry and Broad Learning Network. Food Anal. Methods 17, 664–678 (2024). https://doi.org/10.1007/s12161-024-02600-1
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s12161-024-02600-1