In this paper, we present the implementation of the Infomax algorithm on a computing unit featuring a typical embedded processor of the ARM family and a second partial execution on a custom CPU developed through the FPGA technology. The computational unit will be the “core” of an instrument which aims at allowing the pregnant mothers a real time monitoring of her and the fetus health state. The Infomax algorithm belongs to the Independent Component Analysis family and serves to separate the fetal ECG from the mother’s one. Also the evaluation of the wide literature and the corresponding debate is illustrated together with the motivations for the choice. In terms of performance, both the implementations are suitable for the project’s goal, but the FPGA overcomes the ARM processor (on a reduced portion of the algorithm) by an order of magnitude
A Wearable Intelligent System for The Health of Expectant Mom’s and of Their Children
DANESE, GIOVANNI;LEPORATI, FRANCESCO;MATRONE, GIULIA;
2011-01-01
Abstract
In this paper, we present the implementation of the Infomax algorithm on a computing unit featuring a typical embedded processor of the ARM family and a second partial execution on a custom CPU developed through the FPGA technology. The computational unit will be the “core” of an instrument which aims at allowing the pregnant mothers a real time monitoring of her and the fetus health state. The Infomax algorithm belongs to the Independent Component Analysis family and serves to separate the fetal ECG from the mother’s one. Also the evaluation of the wide literature and the corresponding debate is illustrated together with the motivations for the choice. In terms of performance, both the implementations are suitable for the project’s goal, but the FPGA overcomes the ARM processor (on a reduced portion of the algorithm) by an order of magnitudeI documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
