Unsupervised global optimization: applications on classification of handwritten digits and visual evoked potentials

The authors discuss the optical recognition of handwritten unconnected numerals and visual evoked potential (VEP) classification using two neural network learning paradigms. The first is an unsupervised approach, trained by the combinatorial optimization routine ALOPEX, while the second method uses...

Full description

Saved in:
Bibliographic Details
Published in:IEEE International Conference on Systems, Man and Cybernetics, 1992 pp. 381 - 386 vol.1
Main Authors: Micheli-Tzanakou, E., Dasey, T.J.
Format: Conference Proceeding
Language:English
Published: IEEE 1992
Subjects:
Artificial neural networks
Backpropagation algorithms
Biomedical engineering
Character recognition
Feature extraction
Medical diagnostic imaging
Multiple sclerosis
Neural networks
Pattern recognition
System testing
ISBN:0780307208, 9780780307209
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Abstract The authors discuss the optical recognition of handwritten unconnected numerals and visual evoked potential (VEP) classification using two neural network learning paradigms. The first is an unsupervised approach, trained by the combinatorial optimization routine ALOPEX, while the second method uses the backpropagation algorithm. The unsupervised ALOPEX trained system classifies 1000 training digits to an accuracy of 86.3%, and 500 generalizing characters 86.0% accurately. This compares to 99.8% and 93% for a network trained with the supervised backpropagation algorithm. The system was used to cluster the VEPs of normal and multiple sclerosis (MS) subjects. The method demonstrates two distinct groups of subjects, which when histogrammed illustrate that they largely correspond to the MS and control subject groups. A suitable threshold can be chosen so that the recognizer chooses no false negatives.< >
AbstractList The authors discuss the optical recognition of handwritten unconnected numerals and visual evoked potential (VEP) classification using two neural network learning paradigms. The first is an unsupervised approach, trained by the combinatorial optimization routine ALOPEX, while the second method uses the backpropagation algorithm. The unsupervised ALOPEX trained system classifies 1000 training digits to an accuracy of 86.3%, and 500 generalizing characters 86.0% accurately. This compares to 99.8% and 93% for a network trained with the supervised backpropagation algorithm. The system was used to cluster the VEPs of normal and multiple sclerosis (MS) subjects. The method demonstrates two distinct groups of subjects, which when histogrammed illustrate that they largely correspond to the MS and control subject groups. A suitable threshold can be chosen so that the recognizer chooses no false negatives.< >
Author Micheli-Tzanakou, E.
Dasey, T.J.
Author_xml – sequence: 1
  givenname: E.
  surname: Micheli-Tzanakou
  fullname: Micheli-Tzanakou, E.
  organization: Dept. of Biomed. Eng., Rutgers Univ., Piscataway, NJ, USA
– sequence: 2
  givenname: T.J.
  surname: Dasey
  fullname: Dasey, T.J.
  organization: Dept. of Biomed. Eng., Rutgers Univ., Piscataway, NJ, USA
BookMark eNotkM9OAjEYxJuoiYI8gJ76AmD_LNvWm9kokmA8iGfyQb9idWk324LRp7cR5jKZmeR3mAE5DzEgITecTThn5m7evL00E26MmAjFVTU9IwOmNJNMCaYvySilT1ZUTZkx5oqk95D2HfYHn9DSbRvX0NLYZb_zv5B9DPcUuq71m_-QaAx000JK3p0qGh39gGC_e58zBmr91udES0MLc19oeIhfhd3FMmcPbbomF64Yjk4-JMunx2XzPF68zubNw2LstcnjjUPpRK01aolcaV6h0o5Lu-YIlgsH0jlma2FVBRXUtWFG1VgDTGXFBMghuT1iPSKuut7voP9ZHV-Rf9BOXgk
ContentType Conference Proceeding
DBID 6IE
6IL
CBEJK
RIE
RIL
DOI 10.1109/ICSMC.1992.271745
DatabaseName IEEE Electronic Library (IEL) Conference Proceedings
IEEE Xplore POP ALL
IEEE Xplore All Conference Proceedings
IEEE/IET Electronic Library (IEL) (UW System Shared)
IEEE Proceedings Order Plans (POP All) 1998-Present
DatabaseTitleList
Database_xml – sequence: 1
  dbid: RIE
  name: IEEE/IET Electronic Library
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
EndPage 386 vol.1
ExternalDocumentID 271745
GroupedDBID 6IE
6IK
6IL
AAJGR
AAWTH
ACGHX
ALMA_UNASSIGNED_HOLDINGS
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
CBEJK
OCL
RIE
RIL
ID FETCH-LOGICAL-i89t-cfe3f2688e83e17814e78f13db1ead12fa3ff0d62d74a4a6690976e6aa53402a3
IEDL.DBID RIE
ISBN 0780307208
9780780307209
IngestDate Tue Aug 26 21:50:35 EDT 2025
IsPeerReviewed false
IsScholarly true
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-i89t-cfe3f2688e83e17814e78f13db1ead12fa3ff0d62d74a4a6690976e6aa53402a3
ParticipantIDs ieee_primary_271745
PublicationCentury 1900
PublicationDate 19920000
PublicationDateYYYYMMDD 1992-01-01
PublicationDate_xml – year: 1992
  text: 19920000
PublicationDecade 1990
PublicationTitle IEEE International Conference on Systems, Man and Cybernetics, 1992
PublicationTitleAbbrev ICSMC
PublicationYear 1992
Publisher IEEE
Publisher_xml – name: IEEE
SSID ssj0000450999
Score 1.316111
Snippet The authors discuss the optical recognition of handwritten unconnected numerals and visual evoked potential (VEP) classification using two neural network...
SourceID ieee
SourceType Publisher
StartPage 381
SubjectTerms Artificial neural networks
Backpropagation algorithms
Biomedical engineering
Character recognition
Feature extraction
Medical diagnostic imaging
Multiple sclerosis
Neural networks
Pattern recognition
System testing
Title Unsupervised global optimization: applications on classification of handwritten digits and visual evoked potentials
URI https://ieeexplore.ieee.org/document/271745
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV07T8MwELagYmDiVcRbHljTJnYcO6wVFUhQVaKgbpXjB4oQSdUk5e9zdkIBiYUtvuGU2Of4--5lhK6VVpkUTAZGJnEQswz2XJikgSaMCC1TyXz0_OWBTyZiPk-nXZ9tXwtjjPHJZ2bgHn0sX5eqca6yIQHuEbNttM05b0u1Nu4UQCYO63hiLpzhklB0_XW-xmkX1IzCdHg_enocuUo9MmiV_rpcxZ8t471_vdU-6n_X6OHp5vQ5QFumOELVc1E1S7f9K6Nx2-wDl_BXeO_KLW_wz4g1LgusHHx2-UJehEuLnS_9Y5XXgKaxzl_zusIgwaCzAW1mXb6B7mVZuzwjMN4-mo1vZ6O7oLtWIchFWgfKGmpJIoQR1ESu45XhwkZUZxFYVUSspNaGOiGaxzKWCdBngCwmkZJRIJuSHqNeURbmBOHMwvoz-E5lgZdZknGqKA9ZlsE4kvIUHbrpWizbxhmLdqbO_pSeo902E9Z5Ny5Qr1415hLtqHWdV6srv9ifXrSsLA
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3NT4MwFG90mujJrxm_7cErGxQKxevissVtWeI0uy2lH4YYYRkw_31fC05NvHij7_AC7aN9X79fEboTUiScUe4oHgZOQBP459wwdiShhEkec2qr5y-jaDJh83k8bXi2LRZGKWWbz1THPNpavsxFZVJlXQKxR0C30Q4NAuLVYK1NQgV8E-Pt2NCcGdMlLmsYdr7GcVPW9Ny4O-w9jXsGq0c6tdpf16vY06V_8K_3OkTtb5Qenm7OnyO0pbITVDxnRbU0G0ChJK7pPnAO-8J7A7i8xz9r1jjPsDAOtOkYsiKca2yy6R-rtAR_Gsv0NS0LDBIMOivQptb5G-he5qXpNALzbaNZ_2HWGzjNxQpOyuLSEVr5moSMKeYrz3BeqYhpz5eJB3blEc19rV0ZEhkFPOAhBNDgtKiQc-pDuMn9U9TK8kydIZxosAAK3yk0RGaaJJEv_MilSQJjj_NzdGyma7GsqTMW9Uxd_Cm9RXuD2Xi0GA0nj5dov-6LNbmOK9QqV5W6RrtiXabF6sYu_Cd-Lq9z
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Abook&rft.genre=proceeding&rft.title=IEEE+International+Conference+on+Systems%2C+Man+and+Cybernetics%2C+1992&rft.atitle=Unsupervised+global+optimization%3A+applications+on+classification+of+handwritten+digits+and+visual+evoked+potentials&rft.au=Micheli-Tzanakou%2C+E.&rft.au=Dasey%2C+T.J.&rft.date=1992-01-01&rft.pub=IEEE&rft.isbn=9780780307209&rft.spage=381&rft.epage=386+vol.1&rft_id=info:doi/10.1109%2FICSMC.1992.271745&rft.externalDocID=271745
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=9780780307209/lc.gif&client=summon&freeimage=true
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=9780780307209/mc.gif&client=summon&freeimage=true
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=9780780307209/sc.gif&client=summon&freeimage=true