Analysis of Classification and Recognition Algorithm for Imbalanced Data Fragment in Large Database
Rongguo Li*, Xiaoning Liu, Jian Xu, Cuilan Zou
Laiwu Vocational and Technical College, Laiwu, 271100, China
Abstract: In order to improve the ability of imbalanced data fragment classification and recognition in large database, and realize the optimization retrieval of large database, an imbalanced data fragment classification and recognition algorithm is proposed based on fuzzy feature clustering. Fuzzy adaptive spectral feature extraction method is used to extract the feature of imbalanced data fragment information in large database, and big data mining is carried out in combination with fuzzy directivity clustering method. The association rule scheduling method is used for the balanced scheduling of imbalanced data in large databases, vector quantization coding is carried out for the fragments of imbalanced data, and the feature extraction and information retrieval are carried out according to the quantization coding results. A fuzzy C-means clustering algorithm is used to classify and recognize the fragments of imbalanced data in large database. The simulation results show that the algorithm has high accuracy and low misclassification rate, and the ability of accessing and retrieving large databases is improved.
Keywords: Large database; Data clustering; Classification and identification; Scheduling; Quantization coding