Non-destructive method of small sample sets for the maize moisture content measurement during filling based on NIRS

Tiemin Ma, Guangyue Zhang, Xue Wang, Shujuan Yi, Changyuan Wang

Abstract


In maize breeding, limitations on sampling quantity and associated costs for measuring maize grain moisture during filling are imposed by factors like the planting area of new varieties, maize plant density, effective experimental spikes, and other conditions. However, the conventional method of detecting moisture content in maize grains is slow, damages seeds, and necessitates many sample sets, particularly for high moisture content determination. Thus, a strong demand exists for a non-destructive quantitative analysis model of maize moisture content using a small sample set during grain filling. The Bayes-Merged-Bootstrap (BMB) sample optimization method, which built upon the Bayes-Bootstrap sampling method and the concept of merging, was proposed. A critical concern in dealing with small samples is the relationship between data distribution, minimum sample value, and sample size, which has been thoroughly analyzed. Compared to the Bayes-Bootstrap sample selection method, the BMB method offers distinct advantages in the optimized selection of small samples for non-destructive detection. The quantitative analysis model for maize grain moisture content was established based on the support vector machine regression. Results demonstrate that when the optimal resampling size is 1000 times or more than the original sample size using the BMB method, the model exhibits strong predictive capabilities, with a determination coefficient (R2)>0.989 and a relative prediction determination (RPD)>2.47. The results of the 3 varieties experiment demonstrate the generality of the model. Therefore, it can be applied effectively in practical maize breeding and determining grain moisture content during maize machine harvesting.
Key words: near-infrared spectroscopy; moisture content quantitative analysis; small samples optimized; maize grain during the filling stage
DOI: 10.25165/j.ijabe.20241704.8738

Citation: Ma T M, Zhang G Y, Wang X, Yi S J, Wang C Y. Non-destructive method of small sample sets for the maize moisture content measurement during filling based on NIRS. Int J Agric & Biol Eng, 2024; 17(4): 236–244.

Keywords


near-infrared spectroscopy; moisture content quantitative analysis; small samples optimized; maize grain during the filling stage

Full Text:

PDF

References


Zhu Y D, He H J, Jiang S Q, Ma H J, Chen F S, Xu B C, et al. Mining hyperspectral data for non-destructive and rapid prediction of nitrite content in ham sausages. Int J Agric & Biol Eng, 2021; 14(2): 182–187.

Song P, Kim G, Song P, Yang T, Yue X, Gu Y. Rapid and non-destructive detection method for water status and water distribution of rice seeds with different vigor. Int J Agric & Biol Eng, 2021; 14(2): 231–238.

Zhao X, Xing L Y, Shen S F, Liu J M, Zhang D X. Non-destructive 3D geometric modeling of maize root-stubble in-situ via X-ray computed tomography. Int J Agric & Biol Eng, 2020; 13(3): 174–179.

Zhang M Q, Zhao C, Shao Q J, Yang Z D, Zhang X F, Xu X F, et al. Determination of water content in corn stover silage using near-infrared spectroscopy. Int J Agric & Biol Eng, 2019; 12(6): 143–148.

de Medeiros D T, Ramalho F M G, Batista F G, Mascarenhas A R P, Chaix G, Hein P R G. Water desorption monitoring of cellulose pulps by NIR spectroscopy. Industrial Crops and Products, 2023; 192: 115989.

Su K, Maghirang E, Tan J W, Yoon J Y, Armstrong P, Kachroo P, et al. NIR spectroscopy for rapid measurement of moisture and cannabinoid contents of industrial hemp (Cannabis sativa). Industrial Crops and Products, 2022; 184: 115007.

Bernhard ., Grani C. Striking a balance in Fabry disease research: Mitigating the statistical dilemma arising from small sample size and modest event frequency in rare disorders. International Journal of Cardiology, 2023; 384: 52–53.

Cao J Z, Wang T, Sheng M, Huang Y, Mo P Q, Zhou G Q. Assessment of multi-dimensional joint probability distribution for uncertain mechanical strength parameters under small sample test data. Probabilistic Engineering Mechanics, 2023; 74: 103511.

Ma T W, Wang G, Guo R, Chen L, Ma J F. Forest fire susceptibility assessment under small sample scenario: A semi-supervised learning approach using transductive support vector machine. Journal of Environmental Management, 2024; 359: 120966.

Li X Z, Su H, Xiang L, Yao Q T, Hu A J. Transformer-based meta learning method for bearing fault identification under multiple small sample conditions. Mechanical Systems & Signal Processing, 2024; 208: 110967.

Aydi W, Alduais F S. Estimating Weibull parameters using least squares and multilayer perceptron vs. Bayes estimation. Computers, Materials & Continua, 2022; 71(2): 4033–4050.

Kim I, Kang H-Y, Khang Y H. Comparison of Bayesian spatio-temporal models for small-area life expectancy: A simulation study. American Journal of Epidemiology, 2023; 192(8): 1396–1405.

Peng Z Q, Sun Z Y, Chen J, Ping Z, Dong K Y, Li J, et al. A fault diagnosis approach for electromechanical actuators with simulating model under small experimental data sample condition. Actuators, 2022; 11(3): 66.

Pawel S, Consonni G, Held L. Bayesian approaches to designing replication studies. arXiv e-prints, 2022.

Xu J, Mu R J, Xiong C. A Bayesian stochastic approximation method. Journal of Statistical Planning and Inference, 2021; 211: 391–401.

Luo Y J, Yang X H, Ouyang C P, Wan Y, He S X. Merging naive Bayes and causal rules for text sentiment analysis. Journal of Physics: Conference Series, 2021; 1757: 012034.

Zhang W, Jiang J H. Bootstrap-based resampling methods for software reliability measurement under small sample condition. Journal of Circuits, Systems and Computers, 2024; 33(9): 2450161.

Heikkinen R, Hmlinen H, Kiljunen M, Kärkkäinen S, Schilder J, Jone R I. A Bayesian stable isotope mixing model for coping with multiple isotopes, multiple trophic steps and small sample sizes. Methods in Ecology and Evolution, 2022; 13(11): 2586–2602.

Qi C C, Liu W Z. Tomato production prediction based on deep learning algorithm-Cascade-PSPNET and Bayes. International Journal of Pattern Recognition and Artificial Intelligence, 2023(14): 37.

Canepa A. Small sample adjustment for hypotheses testing on cointegrating vectors. Journal of Time Series Econometrics, 2022; 14(1): 51–85.

Jha M K, Tripathi Y M, Dey S. Multicomponent stress-strength reliability estimation based on unit generalized Rayleigh distribution. International Journal of Quality & Reliability Management, 2021; 38(10): 2048–2079.

Kline B. Bayes factors based on p-values and sets of priors with restricted strength. The American Statistician, 2022; 76(3): 203–213.

Yang X Y, Xie L Y, Zhao B F, Kong X W, Wu N X. An iterative method for parameter estimation of the three-parameter Weibull distribution based on a small sample size with a fixed shape parameter. International Journal of Structural Stability and Dynamics, 2022; 22(12): 2250125.

Liu Y, Liu Z Y, Qiao F, Xu L L, Xu Z. Identification of Perna viridis contaminated with diarrhetic shellfish poisoning toxins in vitro using NIRS and a discriminative non-negative representation-based classifier. Spectrochimica Acta Part A: Molecular and biomolecular Spectroscopy, 2023; 294: 122514.

Zheng G F, Wang Q Y, Cai C. Criterion to determine the minimum sample size for load spectrum measurement and statistical extrapolation. Measurement, 2021; 178: 109387.

Odgers J, Kappatou C, Misener R, García Muñoz S, Filipp S. Probabilistic predictions for partial least squares using bootstrap. AIChE Journal, 2023; 69(7): e18071.

Wang X, Ma T, Yang T, Song P, Xie Q, Chen Z G. Moisture quantitative analysis with small sample set of maize grain in filling stage based on near infrared spectroscopy. Transactions of the CSAE, 2018; 34(13): 203–210. (in Chinese)

Wang X, Ma T M, Yang T, Song P, Chen Z G, Xie H. Monitoring model for predicting maize grain moisture at filling stage using NIRS and a small sample size. Int J Agric & Biol Eng, 2019; 12(2): 132–140.

Goldstein H, Carpenter J, Kenward M G. Bayesian models for weighted data with missing values: a bootstrap approach. Journal of the Royal Statistical Society Series C: Applied Statistics, 2018; 67(4): 1071–1081.

Kleebmek T, Thongmual N. Estimating missing data with Bayes Bootstrap regression imputation. Burapha Science Journal, 2021; 26(2): 816–826. (in Thai language

Luo X H, Wei C D, Wang Y R. Comparison of reliability parameters estimation methods for exponential distribution under small samples. Statistics & Decision, 2018; 493(1): 14–17. (in Chinese)

Salazar J J, Pyrcz M J. Geostatistical significance of differences for spatial subsurface phenomenon. Journal of Petroleum Science and Engineering, 2021; 203: 108694.




Copyright (c) 2024 International Journal of Agricultural and Biological Engineering

Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 International License.

2023-2026 Copyright IJABE Editing and Publishing Office