Interpretable Multiobjective Feature Selection via Visualization in Froth Flotation Process

Visual-based working condition recognition methods are pivotal in the froth flotation process. However, the high dimensionality of visual features generated by the feature extraction technologies reduces the efficiency of recognition algorithms. This article proposes a multiobjective feature selection method based on binary state transition algorithm (MOFS-BSTA). First, a Shapley-based filter method is utilized to reduce the search space. Then, the MOFS-BSTA is employed to generate a set of nondominated solutions. However, selecting a satisfactory choice from a large set of solutions imposes a significant cognitive burden on users. Therefore, a clustering-based t-SNE method is proposed to visualize all nondominated solutions and determine the optimal feature combination. The MOFS-BSTA is applied to a gold-antimony froth flotation process. The experimental results demonstrate that six efficient features, namely high-frequency energy, bubble size, hue, relative red component, coarseness, and stability, significantly enhance the accuracy of working condition recognition.