Acoustic Characterization and Modeling of Silicone-Bonded Cocoa Crop Waste Using a Model Based on the Gaussian Support Vector Machine

Abstract

The sustainable management of waste from agricultural crops represents an urgent challenge. One possible solution considers waste as possible secondary raw materials for specific uses. Among these, the use of agricultural waste as a product for the assembly of panels for the sound absorption of living environments represents a particularly suitable solution. In this study, the acoustic properties of the cocoa pod husk were evaluated, using silicone as a binder. Different proportions of materials and thicknesses were evaluated. A Support Vector Machine (SVM)-based model with a Gaussian kernel was then used to predict the acoustic performance of composite materials. The results obtained suggest the adoption of this material for the acoustic correction of living environments and this methodology for the prediction of the acoustic behavior of materials.

Keywords

• natural materials
• sound absorption coefficient
• acoustic measurements
• Support Vector Machine (SVM)
• Gaussian kernel