PCA IP-core for gas applications on the heterogenous zynq platform

Abstract

Principal component analysis (PCA) is a commonly used technique for data reduction in general as well as for dimensionality reduction in gas identification systems when a sensor array is being used. This paper presents the design and implementation of a complete PCA IP core for gas application on the Zynq programmable system on chip (SoC). All steps of PCA starting from the mean computation to the projection of data onto the new space, passing by the normalization process, covariance matrix and the eigenvectors computation are developed in C and synthesized using the new Xilinx VIVADO high level synthesis (HLS). The Jacobi method is used to find the eigenvectors and different approaches for the implementation of the PCA core on the heterogeneous Zynq platform are proposed. The hardware implementation of the presented PCA algorithm for a 16 x 30 matrix is faster than the software one with a speed up of 1.41 times when executed on a desktop running a 64-bit Intel i7-3770 processor at 3.40GHz. It was achieved using an average of 23% of all resources. 2013 IEEE.