The earplug development followed by ALPINE, a hearing protection company is a trial and error method. This method leads to high material wastage. It is also a time-consuming and expensive development process. So, the objective of this thesis is to ease the error earplug development process by implementing a prediction model. The research is steered towards understanding the factors that influence the sound dampening properties in an earplug, building the dataset, and analysing the data and regression models. The regression model must be able to predict the noise attenuation provided by an earplug based on the material and design specifications for which Gaussian Process Regression (GPR) model is used. With RBF kernel function and through hyperparameter optimization, the GPR model is trained and tested on datasets.

The main finding of this thesis is that noise attenuation provided by an earplug is highly subjective. Sound perception is crucial in earplug design. Even though the most ideal sound attenuation prediction model for earplugs can be developed, in the end, everything relies on individual sound perception. So, the prediction of noise attenuation in earplugs has a higher level of uncertainty. However, with accurate age, gender, and ethnicity information, the earplugs can be modelled and designed for each group and the sound attenuation prediction model can be developed to make predictions with higher certainty.