Partial Least Squares (PLS) regression has been widely used to model the relationship between predictors and responses. However, PLS may be limited in its capacity to handle complex spectral data contaminated with significant noise and interferences. In this paper, we propose a novel filter learning-based PLS (FPLS) model that integrates an adaptive filter into the PLS framework. The FPLS model is designed to maximize the covariance between the filtered spectral data and the response. This modification enables FPLS to dynamically adapt to the characteristics of the data, thereby enhancing its feature extraction and noise suppression capabilities. We have developed an efficient algorithm to solve the FPLS optimization problem and provided theoretical analyses regarding the convergence of the model, the prediction variance, and the relationships among the objective functions of FPLS, PLS, and the filter length. Furthermore, we have derived bounds for the Root Mean Squared Error of Prediction (RMSEP) and the Cosine Similarity (CS) to evaluate model performance. Experimental results using spectral datasets from Corn, Octane, Mango, and Soil Nitrogen show that the FPLS model outperforms PLS, OSCPLS, VCPLS, PoPLS, LoPLS, DOSC, OPLS, MSC, SNV, SGFilter, and Lasso in terms of prediction accuracy. The theoretical analyses align with the experimental results, emphasizing the effectiveness and robustness of the FPLS model in managing complex spectral data.
22 July 2020 in IEEE Geoscience and Remote Sensing Letters
Considering that multiple features can improve the classification performance as they contain diversity information of images, a multiple-feature latent space learning-based method is proposed for hyperspectral image (HSI) classification in this letter. In the proposed method, a latent space that contains diversity information of multiple features and transformation matrices between the latent space and features are both learned. Moreover, spatial information is used for labeling unlabeled samples in the classification. Experimental results on the Indian Pines and University of Pavia data sets demonstrate the effectiveness of the proposed method.
In complex marine environments, achieving low-cost, highly reliable, and continuous navigation is crucial for the intelligent and autonomous operation of unmanned surface vehicles (USVs). Currently, the integrated Global Navigation Satellite System and Strapdown Inertial Navigation System (GNSS/SINS) serves as the primary navigation architecture for USVs. While the cost of high-performance GNSS receivers has steadily decreased, high-precision SINS remains prohibitively expensive. Consequently, micro-electromechanical system (MEMS)-based SINS has emerged as a preferred alternative due to its favorable balance of cost, power consumption, and size. However, significant inertial sensor errors make it difficult to maintain high-precision positioning during GNSS outages. To address this limitation, the single-axis rotational inertial navigation system (SRINS) has been introduced. Nevertheless, constrained by the single-axis mechanical structure and complex sea state disturbances, the system still struggles to effectively modulate random errors and azimuth gyroscope drift, rendering it insufficient for highly demanding navigation tasks. To overcome these bottlenecks, this article systematically reviews four core technologies: (1) Comprehensive denoising and temperature drift compensation techniques for MEMS gyroscopes; (2) rapid moving-base initial alignment models under high sea state disturbances; (3) fast online calibration methods for azimuth gyroscope drift; and (4) adaptive and robust GNSS/SINS integration architectures capable of accommodating high-dynamic conditions and non-Gaussian interference. Finally, this article discusses the engineering conflict between deploying high-precision algorithms and the limited onboard computational capacity of USVs. It concludes by highlighting a highly promising navigation paradigm for future research: the integration of factor graph optimization with physics-informed deep learning.
14 August 2026 in Chemometrics and Intelligent Laboratory Systems