Analog addition/subtraction on the CNN-UM chip with short-time superimposition of input signals

Hyongsuk Kim, T. Roska, Hongrak Son, Istvan Petras

Research output: Article

9 Citations (Scopus)

Abstract

The cellular-neural-network univeral machine (CNN-UM) technique which performs analog addition/substraction between image frames has been developed. The equivalent circuit of the uncoupled CNN without self feedback is reduced to a simple RC circuit. If two inputs are presented to the circuit one after another during a very short time period, the voltages that are proportional to their input signals are superimposed on the state capacitor. The output of such superimposition is a reduced version of the addition/subtraction between the two signals. Simple amplification of the output can recover the actual output. The characteristics of analog addition/subtraction with the proposed algorithm are shown via on-chip experiment. Application of the proposed algorithm to moving target detection is also presented.

Original languageEnglish
Pages (from-to)429-432
Number of pages4
JournalIEEE Transactions on Circuits and Systems I: Fundamental Theory and Applications
Volume50
Issue number3
DOIs
Publication statusPublished - márc. 2003

Fingerprint

Cellular neural networks
Networks (circuits)
Target tracking
Equivalent circuits
Amplification
Capacitors
Feedback
Electric potential
Experiments

ASJC Scopus subject areas

  • Electrical and Electronic Engineering

Cite this

@article{91b7019078e744a9a131ad1830d10f99,
title = "Analog addition/subtraction on the CNN-UM chip with short-time superimposition of input signals",
abstract = "The cellular-neural-network univeral machine (CNN-UM) technique which performs analog addition/substraction between image frames has been developed. The equivalent circuit of the uncoupled CNN without self feedback is reduced to a simple RC circuit. If two inputs are presented to the circuit one after another during a very short time period, the voltages that are proportional to their input signals are superimposed on the state capacitor. The output of such superimposition is a reduced version of the addition/subtraction between the two signals. Simple amplification of the output can recover the actual output. The characteristics of analog addition/subtraction with the proposed algorithm are shown via on-chip experiment. Application of the proposed algorithm to moving target detection is also presented.",
keywords = "Analog addition/subtraction, Cellular-neural-network univeral machine (CNN-UM), Target tracking",
author = "Hyongsuk Kim and T. Roska and Hongrak Son and Istvan Petras",
year = "2003",
month = "3",
doi = "10.1109/TCSI.2003.808908",
language = "English",
volume = "50",
pages = "429--432",
journal = "IEEE Transactions on Circuits and Systems II: Express Briefs",
issn = "1057-7122",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "3",

}

TY - JOUR

T1 - Analog addition/subtraction on the CNN-UM chip with short-time superimposition of input signals

AU - Kim, Hyongsuk

AU - Roska, T.

AU - Son, Hongrak

AU - Petras, Istvan

PY - 2003/3

Y1 - 2003/3

N2 - The cellular-neural-network univeral machine (CNN-UM) technique which performs analog addition/substraction between image frames has been developed. The equivalent circuit of the uncoupled CNN without self feedback is reduced to a simple RC circuit. If two inputs are presented to the circuit one after another during a very short time period, the voltages that are proportional to their input signals are superimposed on the state capacitor. The output of such superimposition is a reduced version of the addition/subtraction between the two signals. Simple amplification of the output can recover the actual output. The characteristics of analog addition/subtraction with the proposed algorithm are shown via on-chip experiment. Application of the proposed algorithm to moving target detection is also presented.

AB - The cellular-neural-network univeral machine (CNN-UM) technique which performs analog addition/substraction between image frames has been developed. The equivalent circuit of the uncoupled CNN without self feedback is reduced to a simple RC circuit. If two inputs are presented to the circuit one after another during a very short time period, the voltages that are proportional to their input signals are superimposed on the state capacitor. The output of such superimposition is a reduced version of the addition/subtraction between the two signals. Simple amplification of the output can recover the actual output. The characteristics of analog addition/subtraction with the proposed algorithm are shown via on-chip experiment. Application of the proposed algorithm to moving target detection is also presented.

KW - Analog addition/subtraction

KW - Cellular-neural-network univeral machine (CNN-UM)

KW - Target tracking

UR - http://www.scopus.com/inward/record.url?scp=0038005370&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0038005370&partnerID=8YFLogxK

U2 - 10.1109/TCSI.2003.808908

DO - 10.1109/TCSI.2003.808908

M3 - Article

AN - SCOPUS:0038005370

VL - 50

SP - 429

EP - 432

JO - IEEE Transactions on Circuits and Systems II: Express Briefs

JF - IEEE Transactions on Circuits and Systems II: Express Briefs

SN - 1057-7122

IS - 3

ER -