Feature Selection Based on Orthogonal Constraints and Polygon Area

In today's information age, the rapidly increasing scale and complexity of data pose unprecedented challenges to traditional data analysis and machine learning algorithms [1-4]. Feature selection, a crucial research area in data mining, aims to identify the optimal subset of features, reducing the dimensionality of high-dimensional datasets and thereby enhancing the performance of learning algorithms [5-7]. Feature selection methods are commonly categorized into three types: filter, wrapper, and embedded methods [8]. Filter methods evaluate features based on predefined rules or criteria without involving learning algorithms [9]. Examples include information gain (IG) [10], maximum relevance minimum redundancy (mRMR) [11], correlation coefficient (CC) [12], Fisher [13], conditional mutual information maximization criterion (CMIM) [14], and ReliefF [15]. Wrapper methods generate various feature subsets and use learning algorithms to evaluate them, aiming to find the globally optimal subset by maximizing or minimizing an objective function [16]. In recent years, embedded methods have gained widespread attention. Wu et al. [17] introduced a supervised feature selection method, Feature Selection with Orthogonal Regression (FSOR), employing Generalized Power Iteration (GPI) and the Augmented Lagrangian Multiplier method to solve the objective function and evaluate features. Nie et al. [18] developed a Robust Feature Selection (RFS) method that uses the 2