Rapid determination of the main components of corn based on near-infrared spectroscopy and a BiPLS-PCA-ELM model

Lili Xu; Jinming Liu; Chunqi Wang; Zhijiang Li; Dongjie Zhang; Dongjie Zhang

doi:10.1364/AO.485099

Applied Optics
Vol. 62,
Issue 11,
pp. 2756-2765
(2023)
•https://doi.org/10.1364/AO.485099

Rapid determination of the main components of corn based on near-infrared spectroscopy and a BiPLS-PCA-ELM model

Lili Xu, Jinming Liu, Chunqi Wang, Zhijiang Li, and Dongjie Zhang

Not Accessible

Your library or personal account may give you access

Get PDF
Email
Share
Get Citation
Copy Citation Text
Lili Xu, Jinming Liu, Chunqi Wang, Zhijiang Li, and Dongjie Zhang, "Rapid determination of the main components of corn based on near-infrared spectroscopy and a BiPLS-PCA-ELM model," Appl. Opt. 62, 2756-2765 (2023)

Export Citation
- BibTex
- Endnote (RIS)
- HTML
- Plain Text
Citation alert
Save article

Check for updates

Abstract

To evaluate corn quality quickly, the feasibility of near-infrared spectroscopy (NIRS) coupled with chemometrics was analyzed to detect the moisture, oil, protein, and starch content in corn. A backward interval partial least squares (BiPLS)-principal component analysis (PCA)-extreme learning machine (ELM) quantitative analysis model was constructed based on BiPLS in conjunction with PCA and the ELM. The selection of characteristic spectral intervals was accomplished by BiPLS. The best principal components were determined by the prediction residual error sum of squares of Monte Carlo cross validation. In addition, a genetic simulated annealing algorithm was utilized to optimize the parameters of the ELM regression model. The established regression models for moisture, oil, protein, and starch can meet the demand for corn component detection with the prediction determination coefficients of 0.996, 0.990, 0.974, and 0.976; the prediction root means square errors of 0.018, 0.016, 0.067, and 0.109; and the residual prediction deviations of 15.704, 9.741, 6.330, and 6.236, respectively. The results show that the NIRS rapid detection model has higher robustness and accuracy based on the selection of characteristic spectral intervals in conjunction with spectral data dimensionality reduction and nonlinear modeling and can be used as an alternative strategy to detect multiple components in corn rapidly.

Full Article | PDF Article

More Like This

Rapid detection of carbon-nitrogen ratio for anaerobic fermentation feedstocks using near-infrared spectroscopy combined with BiPLS and GSA

Jinming Liu, Nan Li, Feng Zhen, Yonghua Xu, Wenzhe Li, and Yong Sun
Appl. Opt. 58(18) 5090-5097 (2019)

Rapid detection of talc content in flour based on near-infrared spectroscopy combined with feature wavelength selection

Changhao Bao, Changhao Zeng, Jinming Liu, and Dongjie Zhang
Appl. Opt. 61(19) 5790-5798 (2022)

Rapid detection of cellulose and hemicellulose contents of corn stover based on near-infrared spectroscopy combined with chemometrics

Na Wang, Longwei Li, Jinming Liu, Jianfei Shi, Yang Lu, Bo Zhang, Yong Sun, and Wenzhe Li
Appl. Opt. 60(15) 4282-4290 (2021)

Previous Article Next Article

Data availability

Data underlying the results presented in this paper are not publicly available at this time but may be obtained from the authors upon reasonable request.

Cited By

You do not have subscription access to this journal. Cited by links are available to subscribers only. You may subscribe either as an Optica member, or as an authorized user of your institution.

Contact your librarian or system administrator
or
Login to access Optica Member Subscription

Figures (7)

You do not have subscription access to this journal. Figure files are available to subscribers only. You may subscribe either as an Optica member, or as an authorized user of your institution.

Contact your librarian or system administrator
or
Login to access Optica Member Subscription

Tables (2)

You do not have subscription access to this journal. Article tables are available to subscribers only. You may subscribe either as an Optica member, or as an authorized user of your institution.

Contact your librarian or system administrator
or
Login to access Optica Member Subscription

Equations (10)

You do not have subscription access to this journal. Equations are available to subscribers only. You may subscribe either as an Optica member, or as an authorized user of your institution.

Contact your librarian or system administrator
or
Login to access Optica Member Subscription

Sample	Component	Mean (%)	Max (%)	Min (%)	Standard Deviation (%)
Calibration set	Moisture	10.232	10.993	9.377	0.403
	Oil	3.502	3.832	3.088	0.183
	Protein	8.672	9.711	7.654	0.481
	Starch	64.698	66.472	62.826	0.823
Validation set	Moisture	10.240	10.817	9.691	0.288
	Oil	3.487	3.716	3.212	0.154
	Protein	8.658	9.694	7.788	0.536
	Starch	64.689	65.841	63.246	0.794

Composition	Model	Wavelengths	Number of Neurons	Elapsed Time/s	PCs	$R_{c}^{2}$	$R_{p}^{2}$	RMSEC (%)	RMSEP (%)	RPD
Moisture	Full-PLS	699	—	215	20	0.999	0.989	0.004	0.029	9.816
	Full-ELM	699	35	284	20	0.975	0.838	0.063	0.120	2.404
	Full-PCA-ELM	699	15	149	20	0.991	0.974	0.037	0.049	5.880
	BiPLS	267	—	70	20	0.999	0.992	0.010	0.026	10.974
	BiPLS-ELM	267	20	186	20	0.992	0.972	0.037	0.050	5.730
	BiPLS-PCA-ELM	267	15	120	20	0.999	0.996	0.009	0.018	15.704
Oil	Full-PLS	699	—	210	14	0.998	0.947	0.008	0.037	4.181
	Full-ELM	699	15	228	14	0.951	0.880	0.039	0.060	2.551
	Full-PCA-ELM	699	15	160	14	0.904	0.882	0.054	0.057	2.706
	BiPLS	84	—	72	14	0.999	0.989	0.007	0.018	9.661
	BiPLS-ELM	84	30	172	14	0.998	0.982	0.010	0.022	7.105
	BiPLS-PCA-ELM	84	15	135	14	0.997	0.990	0.003	0.016	9.741
Protein	Full-PLS	700	—	214	19	0.995	0.959	0.038	0.089	4.758
	Full-ELM	700	10	208	19	0.966	0.905	0.094	0.145	2.913
	Full-PCA-ELM	700	15	158	19	0.962	0.907	0.099	0.133	3.171
	BiPLS	69	—	67	19	0.988	0.973	0.057	0.071	5.957
	BiPLS-ELM	69	15	155	19	0.985	0.960	0.063	0.087	4.860
	BiPLS-PCA-ELM	69	15	129	19	0.976	0.974	0.079	0.067	6.330
Starch	Full-PLS	700	—	217	13	0.997	0.964	0.045	0.131	5.161
	Full-ELM	700	10	218	13	0.960	0.784	0.169	0.275	2.462
	Full-PCA-ELM	700	15	162	13	0.972	0.897	0.140	0.203	3.339
	BiPLS	195	—	67	13	0.992	0.968	0.077	0.128	5.306
	BiPLS-ELM	195	30	175	13	0.976	0.907	0.132	0.200	3.382
	BiPLS-PCA-ELM	195	15	131	13	0.995	0.976	0.059	0.109	6.236

Sample	Component	Mean (%)	Max (%)	Min (%)	Standard Deviation (%)
Calibration set	Moisture	10.232	10.993	9.377	0.403
	Oil	3.502	3.832	3.088	0.183
	Protein	8.672	9.711	7.654	0.481
	Starch	64.698	66.472	62.826	0.823
Validation set	Moisture	10.240	10.817	9.691	0.288
	Oil	3.487	3.716	3.212	0.154
	Protein	8.658	9.694	7.788	0.536
	Starch	64.689	65.841	63.246	0.794

Composition	Model	Wavelengths	Number of Neurons	Elapsed Time/s	PCs	$R_{c}^{2}$	$R_{p}^{2}$	RMSEC (%)	RMSEP (%)	RPD
Moisture	Full-PLS	699	—	215	20	0.999	0.989	0.004	0.029	9.816
	Full-ELM	699	35	284	20	0.975	0.838	0.063	0.120	2.404
	Full-PCA-ELM	699	15	149	20	0.991	0.974	0.037	0.049	5.880
	BiPLS	267	—	70	20	0.999	0.992	0.010	0.026	10.974
	BiPLS-ELM	267	20	186	20	0.992	0.972	0.037	0.050	5.730
	BiPLS-PCA-ELM	267	15	120	20	0.999	0.996	0.009	0.018	15.704
Oil	Full-PLS	699	—	210	14	0.998	0.947	0.008	0.037	4.181
	Full-ELM	699	15	228	14	0.951	0.880	0.039	0.060	2.551
	Full-PCA-ELM	699	15	160	14	0.904	0.882	0.054	0.057	2.706
	BiPLS	84	—	72	14	0.999	0.989	0.007	0.018	9.661
	BiPLS-ELM	84	30	172	14	0.998	0.982	0.010	0.022	7.105
	BiPLS-PCA-ELM	84	15	135	14	0.997	0.990	0.003	0.016	9.741
Protein	Full-PLS	700	—	214	19	0.995	0.959	0.038	0.089	4.758
	Full-ELM	700	10	208	19	0.966	0.905	0.094	0.145	2.913
	Full-PCA-ELM	700	15	158	19	0.962	0.907	0.099	0.133	3.171
	BiPLS	69	—	67	19	0.988	0.973	0.057	0.071	5.957
	BiPLS-ELM	69	15	155	19	0.985	0.960	0.063	0.087	4.860
	BiPLS-PCA-ELM	69	15	129	19	0.976	0.974	0.079	0.067	6.330
Starch	Full-PLS	700	—	217	13	0.997	0.964	0.045	0.131	5.161
	Full-ELM	700	10	218	13	0.960	0.784	0.169	0.275	2.462
	Full-PCA-ELM	700	15	162	13	0.972	0.897	0.140	0.203	3.339
	BiPLS	195	—	67	13	0.992	0.968	0.077	0.128	5.306
	BiPLS-ELM	195	30	175	13	0.976	0.907	0.132	0.200	3.382
	BiPLS-PCA-ELM	195	15	131	13	0.995	0.976	0.059	0.109	6.236

Abstract

Data availability

Cited By

Figures (7)

Tables (2)

Equations (10)

Applied Optics