How to use the MACHINE LEARNING section of XYOM for outlines data ?
- Please enter directly the raw coordinates of the pseudolandmarks, … … provided RAW PSEUDOLANDMARKS has been selected. XYOM then performs the following previous steps for you:
- Computing and saving the NEF from unknown data (or PCs of NEF) <– CHARACTERIZATION
- Computing and saving the NEF from reference data (or PCs of NEF) <– CHARACTERIZATION
- Selecting the same number of columns for each file (unknown and reference) <– MISCELLANEOUS (Working with data files, Extraction)
- Please enter the subdivision of the reference file, activate the SUBMIT button and see the report
If WEIGHTS were saved, new unknown (transformed to NEF or PCs of NEFs, with the same number of columns used for the learning process) could be tentatively identified using the IDENTIFICATION section of XYOM, withNEF or PCs of NEFs, as reference data.
Another way to apply ANN to outlines data is possible, as follows
- Do not enter directly the raw coordinates of the pseudolandmarks
- Concatenate the raw pseudolandmarks of unknown and reference data <– MISCELLANEOUS (Working with data files, Concatenate, By Rows)
- Compute the NEF (or PCs of NEF) from the concatenated unknown and reference data <– CHARACTERIZATION
- Extract and save the unknown NEF (or PCs of NEF) <– MISCELLANEOUS (Working with data files, Extraction)
- Extract and save the reference NEF (or PCs of NEF) <– MISCELLANEOUS (Working with data files, Extraction)
- Enter these data in the Multilayer Perceptron, enter the subdivision of the reference file, activate the SUBMIT button and see the report
If weights were saved, new unknown (transformed to NEF or PCs of NEFs, with the same number of columns used for the learning process) could be tentatively identified using the IDENTIFICATION section of XYOM.