Dayside aurora classification via BIFs-based sparse representation using manifold learning

Abstract

Aurora is the typical ionosphere track generated by the interaction of solar wind and magnetosphere, whose modality and variation are significant to the study of space weather activity. A new aurora classification algorithm based on biologically inspired features (BIFs) and discriminative locality alignment (DLA) is proposed in this paper. First, an aurora image is represented by the BIFs, which combines the C1 units from the hierarchical model of object recognition in cortex and the gist features from the saliency map; then, the manifold learning method called DLA is used to obtain the effective sparse representation for auroras based on BIFs; finally, classification results using support vector machine and nearest neighbour with three sets of features: the C1 unit features, the gist features and the BIFs illustrate the effectiveness and robustness of our method on the real aurora image database from Chinese Arctic Yellow River Station.

Keywords:

• biologically inspired features
• C1 unit features
• gist features
• discriminative locality alignment
• dayside aurora classification

2010 AMS Subject Classifications:

• 62H30
• 65F05
• 65D19
• 68U10

This research is supported by the National Natural Science Foundation of China (41031064; 60902082), the Shaanxi Province Natural Science Fundamental Research Funded Projects (2011JQ8019), the Special Scientific Research of Marine Public Welfare Industry (201005017), the Basic Foundation for Scientific Research, the Fundamental Research Funds for the Central Universities (K5051302008), and the project sponsored by the Scientific Research Foundation for the Returned Overseas Chinese Scholars, State Education Ministry.