Implementing the Kalman Filter Algorithm in Parallel Form: Denoising Sound Wave as a Case Study

Background: Kalman filter and its variants had achieved great success in many applications in the field of technology. However, the kalman filter is under heavy computations burden. Under big data, it becomes pretty slow. On the other hand, the computer industry has now entered the multicore era with hardware computational capacity increased by adding more processors (cores) on one chip, the sequential processors will not be available in near future, so we should have to move to parallel computations. Objective: This paper focuses on how to make Kalman Filter faster on multicore machines and implementing the parallel form of Kalman Filter equations to denoise sound wave as a case study. Method: Splitting the all signal points into large segments of data and applying equations on each segment simultaneously. After that, we merge the filtered points again in one large signal. Results: Our Parallel form of Kalman Filter can achieve nearly linear speed-up. Conclusion: Through implementing the parallel form of Kalman Filter equations on the noisy sound wave as a case study and using various numbers of cores, it is found that a kalman filter algorithm can be efficiently implemented in parallel by splitting the all signal points into large segments of data and applying equations on each segment simultaneously.