Wavelength selection method for near-infrared spectroscopy based on the combination of mutual information and genetic algorithm.

Abstract

Near-infrared (NIR) spectroscopy analysis technology has become a widely utilized analytical tool in various fields due to its convenience and efficiency. However, with the promotion of instrument precision, the spectral dimension can now be expanded to include hundreds of dimensions. This expansion results in time-consuming modeling processes and a decrease in model performance. Hence, it is crucial to carefully choose representative features before constructing models. This paper focuses on the limitations of filter algorithms, which can only sort features and cannot directly determine the best subset of features. A hybrid method of combination of the Max-Relevance Min-Redundancy (mRMR) algorithm and the Genetic Algorithm (GA), as well as filter and wrapper feature selection methods, are combined to select appropriate features automatically. This hybrid algorithm retains the features in each individual that are considered to have a strong correlation and low redundancy by the mRMR algorithms during each iteration of the GA. On the other hand, it deletes the features that are regarded as having little correlation or high redundancy. Through the process of iteration, the feature subset is continuously optimized. We use the proposed hybrid method to select features on two datasets and establish various models to verify our proposed method in this paper. The experimental results indicate the feature selection approach, which combines mRMR with the GA, covers the advantages of both feature selection methods. This approach can select features that show good predictive performance. When compared with other common feature selection methods, such as the Uninformative Variable Elimination algorithm (UVE), Competitive Adaptive Reweighted Sampling algorithm (CARS), Successive Projections Algorithm (SPA), Iteratively Retains Informative Variables (IRIV), and GA, the hybrid algorithm can select a larger number of feature variables that are both representative and informative, additionally, it significantly enhances the predictive performance of the model.