Prediction model for spectroscopy using python programming

This paper is motivated by searching for the perfect pattern for the spectroscopy spectra using artificial neural networks (ANN) using python programming coding. The pattern from the spectroscopy is based on the absorption and emission of light and other radiation by materials in relation to the wavelength dependence of these processes. Spectral equipment such as spectrometers, spectral analysers, spectrographs, or spectrophotometers is utilised to determine spectrum values. The problem in this spectroscopy is to identify the sample or analyte, which can be solved by a prediction model for spectroscopy using Python. These problems occur when finding the best algorithm of pre-processing techniques that can predict any model accurately into an understandable format for prediction models. Various types of pre-processing techniques have been used, such as Multiplicative Scatter Correction (MSC), Inverse MSC, Extended MSC (EMSC), Extended Inverse MSC, de-trending, Standard Normal Variate (SNV) and normalisation in order to get a better r2 value. In this project, we find the r2 and the root mean square error (RMSE) to evaluate the prediction values and the actual values. First, choosing pre-processing techniques and then finding the best statistical method for constructing predictive models that produce high accuracy. We used ANN in this project as a prediction model. Based on the results, we managed to achieve our objective, which is that the prediction model has more than 90% of accuracy. Furthermore, the results show that our prediction model has 1.0 accuracy at 100 Epoch with a 0.3 learning rate. Finally, we can conclude that our prediction model can be used to predict the spectroscopy-based data format.