Deep learning networks were established using Python 3.9.15, sci-kit learn 1.1.3 and TensorFlow 2.11.0 on a computer equipped with an NVIDIA GeForce RTX 4090 GPU and an Intel Core i912900KS CPU. Conventional classification machine learning methods were performed using Python 3.11.3 and sci-kit learn 1.2.2 on a computer equipped with an NVIDIA GeForce GTX 1650 Ti mobile GPU and an AMD Ryzen 7 4800HS mobile CPU. PCR, PLSR, and ridge regression were processed using MATLAB R2021b software (MathWorks, Natick, USA) on a computer equipped with an NVIDIA GeForce GTX 1650 Ti mobile GPU and an AMD Ryzen 7 4800HS mobile CPU.
Matlab r2021b software
Manufactured by MathWorks
Sourced in United States
MATLAB R2021b is a software package that provides a programming environment for numerical computation and visualization. It allows users to work with matrices, plot functions and data, and implement algorithms. The software includes a wide range of built-in functions and tools for various engineering and scientific applications.
Automatically generated - may contain errors
Lab products found in correlation
4 protocols using matlab r2021b software
1
Comparative Machine Learning Methods Evaluation
2
Multivariate Spectral Analysis for Sample Characterization
Check if the same lab product or an alternative is used in the 5 most similar protocols
+ Expand
Mean centralization (MC), multiplicative dispersion correction (MSC), and first derivative (1D) were applied with preprocessing using the Savitzky–Golay algorithm with a 15-point smoothing window and second-order polynomials. Thus, the calibration spectra were subjected to partial least squares regression (PLSR) with “continuous block” cross-validation used to determine the number of latent variables (LV). The original dataset was divided into two subsets selected via the Kennard–Stone algorithm: the calibration set contained 2/3 of the samples and the validation set contained 1/3. The performance of the PLSR calibration models was evaluated using the coefficient of determination (R2), mean squared error of calibration (RMSEC), mean squared error of cross-validation (RMSECV), and mean squared error of prediction (RMSEP). The modeling was concatenated using the PLS toolbox 9.2 (Eigenvector Research Inc., Wenatchee, WA, USA) in the test version of Matlab R2021b software (Mathworks, Natick, MA, USA).
3
Spectral Indices for Estimating Crop Nutrition
Check if the same lab product or an alternative is used in the 5 most similar protocols
+ Expand
A large number of SIs have been created to estimate the nutrition parameters of crops. Especially the two-band SIs including ratio spectral index (RSI), difference spectral index (DSI), and normalized differential spectral index (NDSI) are the most classic SIs algorithms (Jordan, 1969 (link); Rouse et al, 1974 ; Tucker, 1979 (link)). The calculation formula of these SIs are shown as follows.
Rλ1 and Rλ2 represent the reflectance of any two single bands in the range of 350-2500 nm, respectively, and a self-developed code in MATLAB R2021b software (The MathWorks Inc., Massachusetts, USA) was used to select the bands. The relationships between rice LPC and three SIs were analyzed for determining the optimal estimation model of LPC.
Rλ1 and Rλ2 represent the reflectance of any two single bands in the range of 350-2500 nm, respectively, and a self-developed code in MATLAB R2021b software (The MathWorks Inc., Massachusetts, USA) was used to select the bands. The relationships between rice LPC and three SIs were analyzed for determining the optimal estimation model of LPC.
4
Multivariate Spectral Analysis for Sample Characterization
Check if the same lab product or an alternative is used in the 5 most similar protocols
+ Expand
Mean centralization (MC), multiplicative dispersion correction (MSC), and first derivative (1D) were applied with preprocessing using the Savitzky–Golay algorithm with a 15-point smoothing window and second-order polynomials. Thus, the calibration spectra were subjected to partial least squares regression (PLSR) with “continuous block” cross-validation used to determine the number of latent variables (LV). The original dataset was divided into two subsets selected via the Kennard–Stone algorithm: the calibration set contained 2/3 of the samples and the validation set contained 1/3. The performance of the PLSR calibration models was evaluated using the coefficient of determination (R2), mean squared error of calibration (RMSEC), mean squared error of cross-validation (RMSECV), and mean squared error of prediction (RMSEP). The modeling was concatenated using the PLS toolbox 9.2 (Eigenvector Research Inc., Wenatchee, WA, USA) in the test version of Matlab R2021b software (Mathworks, Natick, MA, USA).
About PubCompare
Our mission is to provide scientists with the largest repository of trustworthy protocols and intelligent analytical tools, thereby offering them extensive information to design robust protocols aimed at minimizing the risk of failures.
We believe that the most crucial aspect is to grant scientists access to a wide range of reliable sources and new useful tools that surpass human capabilities.
However, we trust in allowing scientists to determine how to construct their own protocols based on this information, as they are the experts in their field.
Ready to get started?
Sign up for free.
Registration takes 20 seconds.
Available from any computer
No download required
Revolutionizing how scientists
search and build protocols!