RESUMO
In this paper, a novel continual learning classification method (SCLM) in small sample cases is proposed, which inspired by the immune system's continuous improvement of immunity through injecting vaccines. Data-driven classification method requires a large number of historical data to establish a pattern recognition model with good generalization performance. However, in practice, the data that can be used for training is usually small and unbalanced, which lead to poor classification accuracy. In addition, batch learning method cannot improve continually classification performance by learning test phase data. In view of the above problems, SCLM generates sample as vaccine by finding the group center of training samples, so that B cells mature and activate memory cells in the train phase. In the test phase, the recognition ability of SCLM is further improved by learning new samples and updating memory cells. In order to evaluate its performance under the condition of less training samples and its possible advantages, the experiments on well-known datasets in UCI repository and reciprocating compressor faults diagnose were performed. The results show that SCLM has better classification performance than other methods when the number of training samples is insufficient. At the same time, the method of generating data has significantly improved the classification performance of other methods.
