Title | ||
---|---|---|
Investigating the identification of atypical sugarcane using NIR analysis of online mill data |
Abstract | ||
---|---|---|
•All models tested achieved >83% overall accuracy.•Downsampling led to balanced model accuracy for typical and atypical samples.•High accuracy for both classes was achieved using PLS-DA and first derivative spectra.•Second derivative spectra improved the accuracy of SVM, RF and ANN models.•Second derivative and wavelet spectra produced simpler models. |
Year | DOI | Venue |
---|---|---|
2020 | 10.1016/j.compag.2019.105111 | Computers and Electronics in Agriculture |
Keywords | Field | DocType |
Chemometric,Classification,Deterioration,Process control,Imbalanced | Mill,Computer vision,Brix,Cane,Support vector machine,Partial least squares regression,Artificial intelligence,Linear discriminant analysis,Engineering,Impact mill,Random forest,Statistics | Journal |
Volume | ISSN | Citations |
168 | 0168-1699 | 0 |
PageRank | References | Authors |
0.34 | 0 | 5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Justin Sexton | 1 | 0 | 0.34 |
Yvette Everingham | 2 | 6 | 1.59 |
David Donald | 3 | 0 | 0.34 |
Steve Staunton | 4 | 0 | 0.34 |
Ronald D. White | 5 | 7 | 0.80 |