Evolutionary algorithm-optimized feature fusion for accurate classification of shredded tobacco using multi-sensor data
Authors:
Open Access
- 12 January 2026
- journal article
- research article
- Published by Frontiers Media SA in Frontiers in Plant Science
- Vol. 16, 1728353
Abstract
Introduction: Individual sensor systems have limitations in the complex task of classifying shredded tobacco. This study aims to overcome these limitations by developing a novel evolutionary algorithm-based feature fusion framework to enhance sensing accuracy. Methods: We fused data from three sensing modalities: GC-SAW, E-nose, and FTIR. A systematic comparison was conducted to determine the optimal fusion strategy. Seven dimensionality reduction methods were rigorously evaluated, leading to the selection of a genetic algorithm (GA) as the cornerstone for feature selection within our fusion framework. Results: Feature-level fusion was confirmed as the most effective strategy. The GA-based feature selection demonstrated exceptional performance, achieving a mean classification accuracy of 99.89% ± 0.79% across 50 independent test runs. This success stemmed from the algorithm's ability to intelligently distill the high-dimensional fused data into a compact, highly discriminative subset. Discussion/Conclusion: Our framework effectively balances information from the three sensing modalities to maximize their complementary strengths. This work confirms that evolutionary algorithm-based feature fusion is a powerful and robust method for unlocking the full potential of multi-sensor data, thereby significantly advancing the accuracy of complex plant material classification.Keywords
This publication has 43 references indexed in Scilit:
- Classification of kimchi using laser-induced breakdown spectroscopy and k-nearest neighbors modelingJournal of Food Composition and Analysis, 2024
- A systematic review of data fusion techniques for optimized structural health monitoringInformation Fusion, 2023
- Multi‐fidelity data fusion through parameter space reduction with applications to automotive engineeringInternational Journal for Numerical Methods in Engineering, 2023
- ATR-FTIR spectroscopy combined with chemometrics for quantification of total nicotine in Algerian smokeless tobacco productsMicrochemical Journal, 2023
- Deep learning methods for medical image fusion: A reviewComputers in Biology and Medicine, 2023
- Feature Selection in High Dimensional Data: A Review2023
- Cautious weighted random forestsExpert Systems with Applications, 2022
- Early Detection of Alzheimer’s Disease Using Multi-feature Fusion and an Ensemble of Classifiers2020
- Fusion of artificial senses as a robust approach to food quality assessmentJournal of Food Engineering, 2016
- An novel random forests and its application to the classification of mangroves remote sensing imageMultimedia Tools and Applications, 2015