Title :
A reconfigurable hardware implementation of tree classifiers based on a custom chip and a CPLD for gas sensors applications
Author :
Bermak, Amine ; Martinez, Dinique
Author_Institution :
Dept. of EEE, Hong Kong Univ. of Sci. & Technol., China
Abstract :
This paper describes a hardware implementation of tree classifiers based on a custom VLSI chip and a CPLD chip. The tree classifier comprises a first layer of threshold logic unit, implemented on a reconfigurable custom chip, followed by a logical function implemented using a CPLD chip. We first describe the architecture of tree classifiers and compare its performance with support vector machine (SVM) for different data sets. The reconfigurability of the hardware (number of classifiers, topology and precision) is discussed. Experimental results show that the hardware presents a number of interesting features such as reconfigurability, as well as improved fault tolerance.
Keywords :
VLSI; decision trees; fault tolerance; gas sensors; programmable logic devices; support vector machines; SVM; custom VLSI chip; data sets; fault tolerance; gas sensors; logical function; reconfigurable custom chip; reconfigurable hardware implementation; support vector machine; threshold logic unit; tree classifiers; Classification tree analysis; Gas detectors; Hardware;
Conference_Titel :
TENCON 2004. 2004 IEEE Region 10 Conference
Print_ISBN :
0-7803-8560-8
DOI :
10.1109/TENCON.2004.1414349