Principal Component Analysis in Processing Photoacoustic Measurement Data

Abstract

Researchers often come across the problems of storing and processing massive data sets in machine learning tasks, as it is a time-consuming process and difficulties to interpret also arises. Not every feature of the data is necessary for predictions. These redundant data can lead to bad performances or overfitting of the model. Through this article implementation of an unsupervised learning technique, Principal Component Analysis for dimensionality reduction in preprocessing phase of photoacoustic measurement data processing is presented. It helped model deal effectively with these issues to an extent and provided sufficiently accurate prediction results.