基于子空间学习的快速自适应局部比值和判别分析OACSTPCD

Dimensionality reduction is a key technique for processing high-dimensional data,and linear discriminant analysis and its variant algorithms are effective supervised algorithms.However,most discriminant analysis algorithms have the follow-ing disadvantages:a)It cannot select more discriminative features;b)It ignores the interference of noise and redundant fea-tures in the original space;c)The computational complexity of updating the adjacency graph is high.In order to overcome these shortcomings,this paper proposed a fast adaptive local ratio sum discriminant analysis algorithm based on subspace learning.Firstly,this paper proposed a model that unified the ratio sum criterion and subspace learning to explore the potential structure of the data in the subspace,select features with more discriminative information,and avoid being affected by noise in the original space.Secondly,it used an anchor-based strategies to construct an adjacency graph to represent the local structure of the data to accelerate the learning of the adjacency graph.Finally,it introduced Shannon entropy to avoid trivial solutions,and verified the effectiveness of the algorithm by comparison experiments on multiple data sets.