Biological Pattern Discovery With R: Machine Learning Approaches by Zheng Rong Yang;

Author:Zheng Rong Yang;
Language: eng
Format: epub
ISBN: 9789811240133
Publisher: World Scientific Publishing Company
Published: 2022-06-15T00:00:00+00:00

Fig. 5.21.A self-organising map constructed based on the self-organising map algorithm for the short-term Fourier transform of the milk data. Each figure printed in a cell of this map stands for a cow milk concentration percentage of a spectrum.

A quantitative relationship between the cow milk concentration percentages and the spectra profiles represented by the short-term Fourier transform variables was also examined. A neural network regression model was constructed for this relationship analysis. The R package brnn was used to construct a neural network regression model. The Jackknife test was used for the generalisation test of the regression model. Afterwards, the predicted cow milk concentration percentages were compared with the measured cow milk concentration percentages. Figure 5.22 shows the outcome of this investigation. It can be seen that the correlation between the measured and predicted cow milk concentration percentages was high up to 0.9817, meaning that the spectra profile expressed by the short-term Fourier transform variables can be well-used to predict the cow milk concentration percentage with a very high accuracy. In other words, the spectra profile expressed by the short-term Fourier transform variables can be a very good predictor of the milk concentration percentages in this data set.

Download

Copyright Disclaimer:
This site does not store any files on its server. We only index and link to content provided by other sites. Please contact the content providers to delete copyright contents if any and email us, we'll remove relevant links or contents immediately.