A low-power hardware-friendly binary decision tree classifier for gas identification

Qingzheng Li, Amine Bermak

Research output: Contribution to journalArticle

18 Citations (Scopus)

Abstract

In this paper, we present a hardware friendly binary decision tree (DT) classifier for gas identification. The DT classifier is based on an axis-parallel decision tree implemented as threshold networks-one layer of threshold logic units (TLUs) followed by a programmable binary tree implemented using combinational logic circuits. The proposed DT classifier circuit removes the need for multiplication operation enabling up to 80% savings in terms of silicon area and power compared to oblique based-DT while achieving 91.36% classification accuracy without throughput degradation. The circuit was designed in 0.18 μm Charter CMOS process and tested using a data set acquired with in-house fabricated tin-oxide gas sensors.

Original languageEnglish
Pages (from-to)45-58
Number of pages14
JournalJournal of Low Power Electronics and Applications
Volume1
Issue number1
DOIs
Publication statusPublished - 9 Mar 2011
Externally publishedYes

Fingerprint

Decision trees
Classifiers
Hardware
Gases
Threshold logic
Combinatorial circuits
Binary trees
Networks (circuits)
Logic circuits
Tin oxides
Chemical sensors
Throughput
Degradation
Silicon

Keywords

  • Binary decision tree
  • Classifier
  • Gas identification
  • Hardware implementation

ASJC Scopus subject areas

  • Electrical and Electronic Engineering

Cite this

A low-power hardware-friendly binary decision tree classifier for gas identification. / Li, Qingzheng; Bermak, Amine.

In: Journal of Low Power Electronics and Applications, Vol. 1, No. 1, 09.03.2011, p. 45-58.

Research output: Contribution to journalArticle

@article{0543fb5bf92f432ba7eab94f283ffaef,
title = "A low-power hardware-friendly binary decision tree classifier for gas identification",
abstract = "In this paper, we present a hardware friendly binary decision tree (DT) classifier for gas identification. The DT classifier is based on an axis-parallel decision tree implemented as threshold networks-one layer of threshold logic units (TLUs) followed by a programmable binary tree implemented using combinational logic circuits. The proposed DT classifier circuit removes the need for multiplication operation enabling up to 80{\%} savings in terms of silicon area and power compared to oblique based-DT while achieving 91.36{\%} classification accuracy without throughput degradation. The circuit was designed in 0.18 μm Charter CMOS process and tested using a data set acquired with in-house fabricated tin-oxide gas sensors.",
keywords = "Binary decision tree, Classifier, Gas identification, Hardware implementation",
author = "Qingzheng Li and Amine Bermak",
year = "2011",
month = "3",
day = "9",
doi = "10.3390/jlpea1010045",
language = "English",
volume = "1",
pages = "45--58",
journal = "Journal of Low Power Electronics and Applications",
issn = "2079-9268",
publisher = "Multidisciplinary Digital Publishing Institute (MDPI)",
number = "1",

}

TY - JOUR

T1 - A low-power hardware-friendly binary decision tree classifier for gas identification

AU - Li, Qingzheng

AU - Bermak, Amine

PY - 2011/3/9

Y1 - 2011/3/9

N2 - In this paper, we present a hardware friendly binary decision tree (DT) classifier for gas identification. The DT classifier is based on an axis-parallel decision tree implemented as threshold networks-one layer of threshold logic units (TLUs) followed by a programmable binary tree implemented using combinational logic circuits. The proposed DT classifier circuit removes the need for multiplication operation enabling up to 80% savings in terms of silicon area and power compared to oblique based-DT while achieving 91.36% classification accuracy without throughput degradation. The circuit was designed in 0.18 μm Charter CMOS process and tested using a data set acquired with in-house fabricated tin-oxide gas sensors.

AB - In this paper, we present a hardware friendly binary decision tree (DT) classifier for gas identification. The DT classifier is based on an axis-parallel decision tree implemented as threshold networks-one layer of threshold logic units (TLUs) followed by a programmable binary tree implemented using combinational logic circuits. The proposed DT classifier circuit removes the need for multiplication operation enabling up to 80% savings in terms of silicon area and power compared to oblique based-DT while achieving 91.36% classification accuracy without throughput degradation. The circuit was designed in 0.18 μm Charter CMOS process and tested using a data set acquired with in-house fabricated tin-oxide gas sensors.

KW - Binary decision tree

KW - Classifier

KW - Gas identification

KW - Hardware implementation

UR - http://www.scopus.com/inward/record.url?scp=84906735770&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84906735770&partnerID=8YFLogxK

U2 - 10.3390/jlpea1010045

DO - 10.3390/jlpea1010045

M3 - Article

VL - 1

SP - 45

EP - 58

JO - Journal of Low Power Electronics and Applications

JF - Journal of Low Power Electronics and Applications

SN - 2079-9268

IS - 1

ER -