Applied Mechanics and Materials Vol. 443

Abstract: Many real world data is imbalanced, i.e. one category contains significantly more samples than other categories. Traditional classification methods take different categories equally and are often ineffective. Based on the comprehensive analysis of existing researches, we propose a new imbalanced data classification method based on clustering. The method clusters both majority class and minority class at first. Then, clustered minority class will be over-sampled by SMOTE while clustered majority class be under-sampled randomly. Through clustering, the proposed method can avoid the loss of useful information while resampling. Experiments on several UCI datasets show that the proposed method can effectively improve the classification results on imbalanced data.

Abstract: The paper adopts a method of a low speed processer and FPGA based hardware accelerator SOC units to develop the MP3 player, added with some peripheral devices. The experimental results show that the system has implemented the basic functions of the MP3 player, having its own advantage on increasing the decoding speed and reducing the system consumption. The system is convenient to redesign for more function in the future because its designed based on FPGA. In conclusion, it has a wide application prospect.