Robust Nonnegative Matrix Factorization With Self-Initiated Multigraph Contrastive Fusion.

Graph regularized nonnegative matrix factorization (GNMF) has been widely used in data representation due to its excellent dimensionality reduction. When it comes to clustering polluted data, GNMF inevitably learns inaccurate representations, leading to models that are unusually sensitive to outliers in the data. For example, in a face dataset, obscured by items such as a mask or glasses, there is a high probability that the graph regularization term incorrectly describes the association relationship for that sample, resulting in an incorrect elicitation in the matrix factorization process. In this article, a novel self-initiated unsupervised subspace learning method named robust nonnegative matrix factorization with self-initiated multigraph contrastive fusion (RNMF-SMGF) is proposed. RNMF-SMGF is capable of creating samples with different angles and learning different graph structures based on these different angles in a self-initiated method without changing the original data. In the process of subspace learning guided by graph regularization, these different graph structures are fused into a more accurate graph structure, along with entropy regularization, L2,1/2 -norm constraints to facilitate the robust learning of the proposed model and the formation of different clusters in the low-dimensional space. To demonstrate the effectiveness of the proposed model in robust clustering, we have conducted extensive experiments on several benchmark datasets and demonstrated the effectiveness of the proposed method. The source code is available at: https://github.com/LstinWh/RNMF-SMGF/.

Diagnosis of cadmium contamination in urban and suburban soils using visible-to-near-infrared spectroscopy.

Previous studies have mostly focused on using visible-to-near-infrared spectral technique to quantitatively estimate soil cadmium (Cd) content, whereas little attention has been paid to identifying soil Cd contamination from a perspective of spectral classification. Here, we developed a framework to compare the potential of two spectral transformations (i.e., raw reflectance and continuum removal [CR]), three optimization strategies (i.e., full-spectrum, Boruta feature selection, and synthetic minority over-sampling technique [SMOTE]), and three classification algorithms (i.e., partial least squares discriminant analysis, random forest [RF], and support vector machine) for diagnosing soil Cd contamination. A total of 536 soil samples were collected from urban and suburban areas located in Wuhan City, China. Specifically, Boruta and SMOTE strategies were aimed at selecting the most informative predictors and obtaining balanced training datasets, respectively. Results indicated that soils contaminated by Cd induced decrease in spectral reflectance magnitude. Classification models developed after Boruta and SMOTE strategies out-performed to those from full-spectrum. A diagnose model combining CR preprocessing, SMOTE strategy, and RF algorithm achieved the highest validation accuracy for soil Cd (Kappa = 0.74). This study provides a theoretical reference for rapid identification of and monitoring of soil Cd contamination in urban and suburban areas.