Abstract
A rapid and effective method for detecting fungal infection in choy sum seeds is necessary to ensure good yield. In this study, 127 spectra of healthy choy sum seeds and 1479 spectra of seeds of choy sum infected with Penicillium decumbens (P. decumbens) were collected using a laboratory-built hyperspectral imaging system. The imbalanced distribution of samples was improved using the synthetic minority over-sampling technique (SMOTE) algorithm. Nine classifiers were used as base classifiers; discriminant analysis was selected as the meta-learner to build the stacking ensemble learning model. The synergy interval partial least square (siPLS) algorithm was used to filter characteristic wavelengths. The SMOTE-siPLS-stacking model was developed using two wavelength ranges (460.96–516.33 nm and 696.61–753.55 nm) as input, achieving accuracy, and F1-score of 99.79% and 99.89%, respectively. The results showed that hyperspectral imaging combined with the SMOTE-siPLS-stacking model is a feasible method to detect P. decumbens.
Graphical Abstract
Similar content being viewed by others
Data Availability
Research data are not shared.
References
Abbott JA, Lu R, Upchurch BL, Stroshine RL (1997) Hortic Rev 20:1–120
Akyol K (2020) Expert Syst Appl 148:113239
Awang MK, Makhtar M, Udin N, Mansor NF (2021) Int J Adv Comput Sci Appl 12
Bach M, Werner A, Żywiec J, Pluskiewicz W (2017) Inform Sci 384:174–190
Blagus R, Lusa L (2013) BMC Bioinform 14:1–16
Branco P, Torgo L, Ribeiro RP (2016) ACM Comput Surv (CSUR) 49:1–50
Caporaso N, Whitworth MB, Fisk ID (2018) Appl Spectrosc Rev 53:667–687
Chawla NV, Bowyer KW, Hall LO, Kegelmeyer WP (2002) J Artif Intell Res 16:321–357
Farajian N, Adibi P (2021) Expert Syst Appl 169:114317
Fernández A, Garcia S, Herrera F, Chawla NV (2018) J Artificial Intell Res 61:863–905
Haixiang G, Yijing L, Shang J, Mingyun G, Yuanyue H, Bing G (2017) Expert Syst Appl 73:220–239
He H, Garcia EA (2009) IEEE Trans Knowl Data Eng 21:1263–1284
Hengyu Z (2020) 2020 Chinese Automation Congress (CAC), pp 693–697
Jadwal PK, Jain S, Pathak S, Agarwal B (2022) Microsyst Technol:1–9
Kang S, Cho S, Kang P (2015) Eng Appl Artif Intel 43:35–43
Lee H, Kim MS, Lim H-S, Park E, Lee W-H, Cho B-K (2016) Biosyst Eng 148:138–147
Li G, Zhang H, Huang H, Qiao Y, Zheng Y et al (2011) China Vegetables:9–14
Lin S, Wu Y-Z, Chen K-Y, Ye J, Yang X-W, Zhang W-D (2018) J Asian Nat Prod Res 20:445–450
López-de-Ipiña K, Cepeda H, Requejo C, Fernandez E, Calvo PM, Lafuente JV (2019) International Work-Conference on the Interplay between Natural and Artificial Computation, pp 420–427
Lu B, Dao PD, Liu J, He Y, Shang J (2020) Remote Sens (Basel) 12:2659
Norgaard L, Saudland A, Wagner J, Nielsen JP, Munck L, Engelsen SB (2000) Appl Spectrosc 54:413–419
Oksuz K, Cam BC, Kalkan S, Akbas E (2020) IEEE Trans Pattern Anal Mach Intell 43:3388–3415
Pang L, Men S, Yan L, Xiao J (2020) IEEE Access 8:123026–123036
S. Pascucci, S. Pignatti, R. Casa, R. Darvishzadeh, W. Huang, 12 (2020) 3665.
Pristyanto Y, Nugraha AF, Dahlan A, Wirasakti LA, Zein AA, Pratama I (2022) 2022 16th International Conference on Ubiquitous Information Management and Communication (IMCOM), pp 1–5
Pristyanto Y, Nugraha AF, Pratama I, Dahlan A, Wirasakti LA (2021) 2021 15th International Conference on Ubiquitous Information Management and Communication (IMCOM), pp 1–7
Rao NR (2008) Int J Remote Sens 29:131–144
Reddy P, Panozzo J, Guthridge KM, Spangenberg GC, Rochfort SJ (2023) Sensors 23:1820
Regente M, Pinedo M, San Clemente H, Balliau T, Jamet E, De La Canal L (2017) J Exp Bot 68:5485–5495
Rout N, Mishra D, Mallick MK (2018) International Proceedings on Advances in Soft Computing, Intelligent Systems and Applications. Springer, pp 431–443
Sun W, Du Q (2019) IEEE Trans Geosci Remote Sens 7:118–139
M. Teke, H.S. Deveci, O. Haliloğlu, S.Z. Gürbüz, U. Sakarya, 2013 6th International Conference on Recent Advances in Space Technologies (RAST), 2013, pp. 171–176
Thabtah F, Hammoud S, Kamalov F, Gonsalves A (2020) Inform Sci 513:429–441
Tomaszewski M, Nalepa J, Moliszewska E, Ruszczak B, Smykala K (2023) Sci Rep 13:7671
Verbiest N, Ramentol E, Cornelis C, Herrera F (2014) Appl Soft Comput 22:511–517
Wang C, Liu B, Liu L, Zhu Y, Hou J, Liu P, Li X (2021) Artif Intell Rev 54:5205–5253
Wu S, Butt H-J (2016) Adv Mater 28:1208–1226
Xia Y, Chen K, Yang Y (2021) Inform Sci 557:421–442
Xu P, Fu L, Xu K, Sun W, Tan Q, Zhang Y, Zha X, Yang R (2023) J Food Compos Anal 119:105254
Yao Y, Kong Y, Zhang P, Zhang H, Li G et al (2017) HortScience 52:1048–1051
Zhang L, Sun J, Zhou X, Nirere A, Wu X, Dai R (2020b) J Food Process Preserv 44:e14591
Zhang N, Yang G, Pan Y, Yang X, Chen L, Zhao C (2020a) Remote Sens (Basel) 12:3188
Zheng Z, Cai Y, Li Y (2015) Comput Inform 34:1017–1037
Funding
This work was supported by the Guangzhou Science and Technology Project (grant number 202103000095), the National Natural Science Foundation of China (grant number 61975069), the Key-Area Research and Development Program of Guangdong Province (grant number 2020B090922006), the Free Exploration Project of Special Research Funds for the Central Public-Interest Scientific Institution (grant number PM-zx703-202112-338), and Guangdong Provincial Special Project for Rural Revitalization Strategy at the Provincial Level(YCN [2022] No. 92).
Author information
Authors and Affiliations
Corresponding authors
Ethics declarations
Ethical Guidelines
Ethics approval was not required for this research.
Conflict of Interest
Baiheng Xie declares that he has no conflict of interest. Bijuan Chen declares that he has no conflict of interest. Jinfang Ma declares that he has no conflict of interest. Jiaze Chen declares that he has no conflict of interest. Yongxin Zhou declares that he has no conflict of interest. Xueqin Han declares that he has no conflict of interest. Zheng Xiong declares that he has no conflict of interest. Zhanwang Yu declares that he has no conflict of interest. Furong Huang declares that he has no conflict of interest.
Additional information
Publisher’s Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Highlights
•Combined with hyperspectral imaging and machine vision methods, the diagnosis of Penicillium infection in seeds was realized.
•The stacking ensemble learning model showed excellent performance in the imbalanced classification of seeds.
•The accuracy of the diagnostic model with stacking structure was between 99.17% and 100% for the test data.
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
Xie, B., Chen, B., Ma, J. et al. Rapid Identification of Choy Sum Seeds Infected with Penicillium decumbens Based on Hyperspectral Imaging and Stacking Ensemble Learning. Food Anal. Methods 17, 416–425 (2024). https://doi.org/10.1007/s12161-024-02574-0
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s12161-024-02574-0