Biophysical recognition system of time-series analog signals by a hebbian learning network

Kouji Tanaka, Masahiro Okamoto

Research output: Contribution to journalArticle

Abstract

We propose a biophysical recognition system of time-series analog signals based on fundamental neural information processing. The system utilizes the following process: (i) the time-series analog signals are altered to an impulse train by multi-kinds or multi-channels of transducers in a transducing process, (ii) the produced impulse train propagates within a biophysical neural network in keeping with the frequency of the impulse train, (iii) the time-series of final output patterns through the biophysical neural network are compared with samples stored in memory, and recognition and discrimination are performed according to the maximum similarity between patterns. The ability of the proposed system is verified by using artificial analog signals and utterance signals.

Original languageEnglish
Pages (from-to)38-57
Number of pages20
JournalChem-Bio Informatics Journal
Volume2
Issue number2
DOIs
Publication statusPublished - Jan 1 2002

Fingerprint

Time series
Learning
Neural networks
Aptitude
Transducers
Automatic Data Processing
Data storage equipment
Recognition (Psychology)
Discrimination (Psychology)

All Science Journal Classification (ASJC) codes

  • Biochemistry

Cite this

Biophysical recognition system of time-series analog signals by a hebbian learning network. / Tanaka, Kouji; Okamoto, Masahiro.

In: Chem-Bio Informatics Journal, Vol. 2, No. 2, 01.01.2002, p. 38-57.

Research output: Contribution to journalArticle

@article{ca7c3ed188364dd5ac53a580ca5b2edb,
title = "Biophysical recognition system of time-series analog signals by a hebbian learning network",
abstract = "We propose a biophysical recognition system of time-series analog signals based on fundamental neural information processing. The system utilizes the following process: (i) the time-series analog signals are altered to an impulse train by multi-kinds or multi-channels of transducers in a transducing process, (ii) the produced impulse train propagates within a biophysical neural network in keeping with the frequency of the impulse train, (iii) the time-series of final output patterns through the biophysical neural network are compared with samples stored in memory, and recognition and discrimination are performed according to the maximum similarity between patterns. The ability of the proposed system is verified by using artificial analog signals and utterance signals.",
author = "Kouji Tanaka and Masahiro Okamoto",
year = "2002",
month = "1",
day = "1",
doi = "10.1273/cbij.2.38",
language = "English",
volume = "2",
pages = "38--57",
journal = "Chem-Bio Informatics Journal",
issn = "1347-6297",
publisher = "Chem-Bio Informatics Society",
number = "2",

}

TY - JOUR

T1 - Biophysical recognition system of time-series analog signals by a hebbian learning network

AU - Tanaka, Kouji

AU - Okamoto, Masahiro

PY - 2002/1/1

Y1 - 2002/1/1

N2 - We propose a biophysical recognition system of time-series analog signals based on fundamental neural information processing. The system utilizes the following process: (i) the time-series analog signals are altered to an impulse train by multi-kinds or multi-channels of transducers in a transducing process, (ii) the produced impulse train propagates within a biophysical neural network in keeping with the frequency of the impulse train, (iii) the time-series of final output patterns through the biophysical neural network are compared with samples stored in memory, and recognition and discrimination are performed according to the maximum similarity between patterns. The ability of the proposed system is verified by using artificial analog signals and utterance signals.

AB - We propose a biophysical recognition system of time-series analog signals based on fundamental neural information processing. The system utilizes the following process: (i) the time-series analog signals are altered to an impulse train by multi-kinds or multi-channels of transducers in a transducing process, (ii) the produced impulse train propagates within a biophysical neural network in keeping with the frequency of the impulse train, (iii) the time-series of final output patterns through the biophysical neural network are compared with samples stored in memory, and recognition and discrimination are performed according to the maximum similarity between patterns. The ability of the proposed system is verified by using artificial analog signals and utterance signals.

UR - http://www.scopus.com/inward/record.url?scp=52649146464&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=52649146464&partnerID=8YFLogxK

U2 - 10.1273/cbij.2.38

DO - 10.1273/cbij.2.38

M3 - Article

VL - 2

SP - 38

EP - 57

JO - Chem-Bio Informatics Journal

JF - Chem-Bio Informatics Journal

SN - 1347-6297

IS - 2

ER -