Prediction of firmness of sweet potato using VNIR hyperspectral imaging and machine learning

Ahmed, Md Toukir

Permalink

https://hdl.handle.net/2142/132850 Copy

Description

Title

Prediction of firmness of sweet potato using VNIR hyperspectral imaging and machine learning

Author(s)

Ahmed, Md Toukir

Issue Date

2023

Keyword(s)

Agricultural and Biological Engineering

Abstract

Hyperspectral imaging coupled with machine learning is recently considered a tremendously innovative approach to address accurate predictive analysis in agricultural and biological domains. This study used some linear (partial least squares regression (PLSR), multiple linear regression (MLR)), and non-linear (support vector regression (SVR)) machine learning-based regression methods to predict the firmness of sweet potatoes of different varieties using spectral data extracted from the images collected using a visible near-infrared hyperspectral imaging system (400–1000 nm). Moreover, some important feature wavelengths were also identified using the recursive feature elimination (RFE) technique to show the pixel-wise distribution of firmness in the sweet potato and to aid the development of a low-cost multispectral system for industrial applications. The predictive results were outstanding, a testament to the ever-growing application of hyperspectral image analysis along with machine learning.

Type of Resource

• Text
• Image

Language

eng

Handle URL

https://hdl.handle.net/2142/132850

Copyright and License Information

Copyright 2023 Md Toukir Ahmed

Owning Collections