On-line Realization of SVM Kalman Filter for MEMS Gyro

The on-line realization of kalman filter based on Support Vector Machine (SVM) is presented in this paper. The process of kalman filter based on SVM is that: the real-time gyro signals are classified into different groups by SVM, then different signals belonged to different groups are de-noised by different filters. Examples with actual experiment demonstrate that the method has apparent superiority for filtering gyro random noise. The simulation results indicate that the proposed method is valid and practical on filtering and de-noising of MEMS gyro. This method can also be used to process the output signal of other kinds of gyroscope.