Another pipeline in local Partial Least Squares Regression (LPLS) methods: Assessing the impact of wavelet transform integration

• Published in: Microchemical journal 2024-12, Vol.207, p.112144, Article 112144
• Main Authors: Deryck, Antoine, Niemöller, Andreas, Baeten, Vincent, Fernández Pierna, Juan Antonio
• Format: Article
• Language: English
• Subjects: Feed; Local Partial Least Squares regression; NIR spectroscopy; Wavelet transform
• ISSN: 0026-265X
• DOI: 10.1016/j.microc.2024.112144

[Display omitted] •New WLPLS method combines wavelet transform with LPLS for faster predictions.•WLPLS performs comparably to LPLS and LPLS-S.•All local methods outperform global PLS on large, heterogeneous feed datasets.•Wavelet transform in LPLS reduces computing time and the need for preprocessing.•Other methods, such as LPLS-S, offer similar or additional benefits. This study evaluates the performance of four Partial Least Squares Regression (PLS) methods, focusing on a new Local Partial Least Squares Regression (LPLS) variant integrating wavelet transformation, named WLPLS, for analyzing feed using Near-Infrared (NIR) spectroscopy. While traditional PLS methods are effective for many spectroscopic applications, their global modeling approach often reduces predictive accuracy in large, heterogeneous datasets. In contrast, LPLS adapts models to local data characteristics, which can enhance prediction but also increase computational demands (power and time). WLPLS seeks to mitigate these demands by incorporating wavelet transformation to reduce data dimensionality while effectively managing spectral variances. This research conducts a comparative analysis of WLPLS against traditional PLS, LPLS, and another LPLS pipeline reducing data dimensionality: the LPLS on global PLS scores (LPLS-S). The performance of these methods were evaluated using a large feed database containing 24,644 samples, analyzing five key constituents: ash, crude fibers, fat, moisture, and proteins. The results demonstrate that local approaches outperformed the global PLS method for this dataset and that the performance of the local methods were relatively similar to each other. The selection of the optimal method therefore depends on the specific requirements of the application, such as dataset characteristics and the required prediction speed. Future studies should broaden this comparative framework to additional datasets and contexts to ensure they are adapted for diverse applications.