Robust boosting neural networks with random weights for multivariate calibration of complex samples

Bian, Xihui; Diwu, Pengyao; Zhang, Caixia; Lin, Ligang; Chen, Guohui; Tan, Xiaoyao; Guo, Yibing; Cheng, Bowen

doi:10.1016/j.aca.2018.01.013

Cited by 16 publications

(10 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The commonly used pretreatment methods for biological materials and their principles, functions, and characteristics are shown in Table 1. It is worth mentioning that all of the pretreatment methods may lead to information loss from the raw spectrum, although they can improve the signal to noise ratio (Bian et al., 2018; Dong & Sun, 2013; Shi & Yu, 2017; Williams, 2020). In addition, multiple studies have shown that with the adoption of optimal datasets and the application of advanced algorithms, the effect of pretreatment on the performance of the final model was no longer significant (Shi & Yu, 2017; Dong & Sun, 2013; Bian et al., 2018; Williams, 2020; Zhang et al., 2019; Harrington, 2018; Mao et al., 2014; Mutlu et al., 2011; Chen et al., 2017; Peiris et al., 2017; Gabriel et al., 2017).…”

Section: Nirs Methodologymentioning

confidence: 99%

“…This approach usually requires two preconditions. The first one is a large number of samples collected from diverse sources (Williams, 2020;Cui & Fearn, 2018;Bian et al, 2018;Zhang et al, 2019;Dowell et al, 2006). This can be seen in the study of Zhang et al (2019), which contained 775 wheat samples from 1998 to 2005.…”

Section: Calibration Model Development and Performance Evaluationmentioning

confidence: 99%

“…Sample size in subsequent studies was increased as much as 10-fold, resulting in models' increasing robustness (Li et al, 2017;Cui & Fearn, 2018;Bian et al, 2018;Williams, 2020). In order to reach the largest range of protein content and therefore strengthen the generalizability of regression models, the source of the samples also should be diversified (Li et al, 2017;Cui & Fearn, 2018;Bian et al, 2018;Williams, 2020;Zhang et al, 2019). For example, according to studies by Bian et al (2018) and Zhang et al (2019), there was a total of 882 samples from five varieties collected in 1998-2005.…”

Section: Proteinmentioning

confidence: 99%

“…In order to reach the largest range of protein content and therefore strengthen the generalizability of regression models, the source of the samples also should be diversified (Li et al, 2017;Cui & Fearn, 2018;Bian et al, 2018;Williams, 2020;Zhang et al, 2019). For example, according to studies by Bian et al (2018) and Zhang et al (2019), there was a total of 882 samples from five varieties collected in 1998-2005. Both studies made modifications on the original neural network with random weights (NNRW) and convolutional neural network (CNN), which also contributed to the performance improvement (Bian et al, 2018;Zhang et al, 2019).…”

Section: Proteinmentioning

confidence: 99%

“…For example, according to studies by Bian et al (2018) and Zhang et al (2019), there was a total of 882 samples from five varieties collected in 1998-2005. Both studies made modifications on the original neural network with random weights (NNRW) and convolutional neural network (CNN), which also contributed to the performance improvement (Bian et al, 2018;Zhang et al, 2019). These modifications were more likely to be seen in regression methods based on neural networks such as improved RBFNN and improved DBN Mao et al, 2014).…”

Section: Proteinmentioning

confidence: 99%

See 4 more Smart Citations

Quantitative assessment of wheat quality using near‐infrared spectroscopy: A comprehensive review

Tian

Tilley

et al. 2022

Comp Rev Food Sci Food Safe

View full text Add to dashboard Cite

Wheat is one of the most widely cultivated crops throughout the world. A great need exists for wheat quality assessment for breeding, processing, and products production purposes. Near‐infrared spectroscopy (NIRS) is a rapid, low‐cost, simple, and nondestructive assessment method. Many advanced studies associated with NIRS for wheat quality assessment have been published recently, either introducing new chemometrics or attempting new assessment parameters to improve model robustness and accuracy. This review provides a comprehensive overview of NIRS methodology including its principle, spectra pretreatments, spectral wavelength selection, outlier disposal, dataset division, regression methods, and model evaluation. More importantly, the applications of NIRS in the determination of analytical parameters, rheological parameters, and end product quality of wheat are summarized. Although NIRS showed great potential in the quantitative determination of analytical parameters, there are still challenges in model robustness and accuracy in determining rheological parameters and end product quality for wheat products. Future model development needs to incorporate larger databases, integrate different spectroscopic techniques, and introduce cutting‐edge chemometrics methods. In addition, calibration based on external factors should be considered to improve the predicted results of the model. The NIRS application in micronutrients needs to be extended. Last, the idea of combining standard product sensory attributes and spectra for model development deserves further study.

show abstract

Section: Nirs Methodologymentioning

confidence: 99%

Section: Calibration Model Development and Performance Evaluationmentioning

confidence: 99%

Section: Proteinmentioning

confidence: 99%

Section: Proteinmentioning

confidence: 99%

Section: Proteinmentioning

confidence: 99%

See 3 more Smart Citations

Quantitative assessment of wheat quality using near‐infrared spectroscopy: A comprehensive review

Tian

Tilley

et al. 2022

Comp Rev Food Sci Food Safe

View full text Add to dashboard Cite

show abstract

Firefly Interval Selection Combined With Extreme Learning Machine for Spectral Quantification of Complex Samples

Wang,

Zhang,

Mpango

et al. 2024

Journal of Chemometrics

View full text Add to dashboard Cite

Firefly algorithm (FA) combined with extreme learning machine (ELM) is developed for spectral interval selection and quantitative analysis of complex samples. The method firstly segments the spectra into a certain number of intervals. Vectors with 1 and 0, which represent the interval selected or not, are used as the inputs of the FA. The RMSEP value predicted by ELM model is used as the fitness function of the FA. The activation function and number of hidden layer nodes of ELM, number of spectral intervals, population number, environmental absorbance, and constant of FA are optimized. The predictive performance of FA‐ELM is compared with full‐spectrum PLS, ELM, genetic algorithm‐ELM (GA‐ELM), and particle swarm optimization‐ELM (PSO‐ELM) by one ultraviolet (UV) spectrum dataset of gasoil and three near‐infrared (NIR) spectral datasets of corn, wheat, and tablet samples. The results show that FA‐ELM has a better performance compared with its competitors in predicting monoaromatics, water, wheat kernel texture, and active pharmaceutical ingredients (APIs) in gasoil, corn, wheat, and tablet samples.

show abstract

Near Infrared Spectroscopic Quantification Using Firefly Wavelength Interval Selection Coupled with Partial Least Squares

Bian

Zhao

Sun

et al. 2022

Sense the Real Change: Proceedings of the 20th International Conference on Near Infrared Spectroscopy

View full text Add to dashboard Cite

Robust boosting neural networks with random weights for multivariate calibration of complex samples

Cited by 16 publications

References 39 publications

Quantitative assessment of wheat quality using near‐infrared spectroscopy: A comprehensive review

Quantitative assessment of wheat quality using near‐infrared spectroscopy: A comprehensive review

Firefly Interval Selection Combined With Extreme Learning Machine for Spectral Quantification of Complex Samples

Near Infrared Spectroscopic Quantification Using Firefly Wavelength Interval Selection Coupled with Partial Least Squares

Contact Info

Product

Resources

About