Presentation Information
[15p-P02-8]Spectral analysis by a neural network using processed data added noise as learning data
〇Masaki Oba1 (1.JAEA)
Keywords:
neural network,spectral analysis,noise
Random noise was added to the training data, which was made by mixing and processing four types of spectral data: Gd2O3, TiO2, ZrO2, and Fe2O3. The variance in the analysis results increased slightly when noise was added to the test data. The effect of noise on the test samples was greater than that of the training data, so it is thought that the effect of noise on the test samples needs to be avoided.
Comment
To browse or post comments, you must log in.Log in