Conceptual distance of numerically specified case features

W. Dubitzky, Alfons Josef Schuster, J. G. Hughes, D. A. Bell

Research output: Chapter in Book/Report/Conference proceedingConference contribution

4 Citations (Scopus)

Abstract

Case-based reasoning (CBR) systems rely on the conceptual ordering of entities called cases. If atomic case features are allowed to assume numeric as well as symbolic values, then a systematic comparison regime is needed to aggregate similarity scores. A common approach to deal with real-numbered features is normalisation. However, there are two conspicuous problems with this procedure: the similarity between two features is dependent on the corresponding values of all other cases to be ranked; and real-numbered features are often interpreted by human experts according to conceptual constraints associated with features. In such situations, a conceptual distance between two features should be determined rather than the length of a 'gap' on a linear scale. Within the framework of a comprehensive case-knowledge architecture, the notion of a concept frame that can be associated with a case feature is proposed. Through this component it is possible to represent polymorphic atomic case features, and to systematically establish the concept distance between two real-numbered feature instances.

Original languageEnglish
Title of host publicationProceedings - 1995 2nd New Zealand International Two-Stream Conference on Artificial Neural Networks and Expert Systems, ANNES 1995
EditorsGeorge Coghill, Nikola K. Kasabov
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages210-213
Number of pages4
ISBN (Electronic)0818671742, 9780818671746
DOIs
Publication statusPublished - 1995 Jan 1
Externally publishedYes
Event2nd New Zealand International Two-Stream Conference on Artificial Neural Networks and Expert Systems, ANNES 1995 - Dunedin, New Zealand
Duration: 1995 Nov 201995 Nov 23

Publication series

NameProceedings - 1995 2nd New Zealand International Two-Stream Conference on Artificial Neural Networks and Expert Systems, ANNES 1995

Conference

Conference2nd New Zealand International Two-Stream Conference on Artificial Neural Networks and Expert Systems, ANNES 1995
CountryNew Zealand
CityDunedin
Period95/11/2095/11/23

Fingerprint

Case based reasoning

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Networks and Communications

Cite this

Dubitzky, W., Schuster, A. J., Hughes, J. G., & Bell, D. A. (1995). Conceptual distance of numerically specified case features. In G. Coghill, & N. K. Kasabov (Eds.), Proceedings - 1995 2nd New Zealand International Two-Stream Conference on Artificial Neural Networks and Expert Systems, ANNES 1995 (pp. 210-213). [499473] (Proceedings - 1995 2nd New Zealand International Two-Stream Conference on Artificial Neural Networks and Expert Systems, ANNES 1995). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ANNES.1995.499473

Conceptual distance of numerically specified case features. / Dubitzky, W.; Schuster, Alfons Josef; Hughes, J. G.; Bell, D. A.

Proceedings - 1995 2nd New Zealand International Two-Stream Conference on Artificial Neural Networks and Expert Systems, ANNES 1995. ed. / George Coghill; Nikola K. Kasabov. Institute of Electrical and Electronics Engineers Inc., 1995. p. 210-213 499473 (Proceedings - 1995 2nd New Zealand International Two-Stream Conference on Artificial Neural Networks and Expert Systems, ANNES 1995).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Dubitzky, W, Schuster, AJ, Hughes, JG & Bell, DA 1995, Conceptual distance of numerically specified case features. in G Coghill & NK Kasabov (eds), Proceedings - 1995 2nd New Zealand International Two-Stream Conference on Artificial Neural Networks and Expert Systems, ANNES 1995., 499473, Proceedings - 1995 2nd New Zealand International Two-Stream Conference on Artificial Neural Networks and Expert Systems, ANNES 1995, Institute of Electrical and Electronics Engineers Inc., pp. 210-213, 2nd New Zealand International Two-Stream Conference on Artificial Neural Networks and Expert Systems, ANNES 1995, Dunedin, New Zealand, 95/11/20. https://doi.org/10.1109/ANNES.1995.499473
Dubitzky W, Schuster AJ, Hughes JG, Bell DA. Conceptual distance of numerically specified case features. In Coghill G, Kasabov NK, editors, Proceedings - 1995 2nd New Zealand International Two-Stream Conference on Artificial Neural Networks and Expert Systems, ANNES 1995. Institute of Electrical and Electronics Engineers Inc. 1995. p. 210-213. 499473. (Proceedings - 1995 2nd New Zealand International Two-Stream Conference on Artificial Neural Networks and Expert Systems, ANNES 1995). https://doi.org/10.1109/ANNES.1995.499473
Dubitzky, W. ; Schuster, Alfons Josef ; Hughes, J. G. ; Bell, D. A. / Conceptual distance of numerically specified case features. Proceedings - 1995 2nd New Zealand International Two-Stream Conference on Artificial Neural Networks and Expert Systems, ANNES 1995. editor / George Coghill ; Nikola K. Kasabov. Institute of Electrical and Electronics Engineers Inc., 1995. pp. 210-213 (Proceedings - 1995 2nd New Zealand International Two-Stream Conference on Artificial Neural Networks and Expert Systems, ANNES 1995).
@inproceedings{39fcca29249440018fbce80e7f01bf1b,
title = "Conceptual distance of numerically specified case features",
abstract = "Case-based reasoning (CBR) systems rely on the conceptual ordering of entities called cases. If atomic case features are allowed to assume numeric as well as symbolic values, then a systematic comparison regime is needed to aggregate similarity scores. A common approach to deal with real-numbered features is normalisation. However, there are two conspicuous problems with this procedure: the similarity between two features is dependent on the corresponding values of all other cases to be ranked; and real-numbered features are often interpreted by human experts according to conceptual constraints associated with features. In such situations, a conceptual distance between two features should be determined rather than the length of a 'gap' on a linear scale. Within the framework of a comprehensive case-knowledge architecture, the notion of a concept frame that can be associated with a case feature is proposed. Through this component it is possible to represent polymorphic atomic case features, and to systematically establish the concept distance between two real-numbered feature instances.",
author = "W. Dubitzky and Schuster, {Alfons Josef} and Hughes, {J. G.} and Bell, {D. A.}",
year = "1995",
month = "1",
day = "1",
doi = "10.1109/ANNES.1995.499473",
language = "English",
series = "Proceedings - 1995 2nd New Zealand International Two-Stream Conference on Artificial Neural Networks and Expert Systems, ANNES 1995",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "210--213",
editor = "George Coghill and Kasabov, {Nikola K.}",
booktitle = "Proceedings - 1995 2nd New Zealand International Two-Stream Conference on Artificial Neural Networks and Expert Systems, ANNES 1995",

}

TY - GEN

T1 - Conceptual distance of numerically specified case features

AU - Dubitzky, W.

AU - Schuster, Alfons Josef

AU - Hughes, J. G.

AU - Bell, D. A.

PY - 1995/1/1

Y1 - 1995/1/1

N2 - Case-based reasoning (CBR) systems rely on the conceptual ordering of entities called cases. If atomic case features are allowed to assume numeric as well as symbolic values, then a systematic comparison regime is needed to aggregate similarity scores. A common approach to deal with real-numbered features is normalisation. However, there are two conspicuous problems with this procedure: the similarity between two features is dependent on the corresponding values of all other cases to be ranked; and real-numbered features are often interpreted by human experts according to conceptual constraints associated with features. In such situations, a conceptual distance between two features should be determined rather than the length of a 'gap' on a linear scale. Within the framework of a comprehensive case-knowledge architecture, the notion of a concept frame that can be associated with a case feature is proposed. Through this component it is possible to represent polymorphic atomic case features, and to systematically establish the concept distance between two real-numbered feature instances.

AB - Case-based reasoning (CBR) systems rely on the conceptual ordering of entities called cases. If atomic case features are allowed to assume numeric as well as symbolic values, then a systematic comparison regime is needed to aggregate similarity scores. A common approach to deal with real-numbered features is normalisation. However, there are two conspicuous problems with this procedure: the similarity between two features is dependent on the corresponding values of all other cases to be ranked; and real-numbered features are often interpreted by human experts according to conceptual constraints associated with features. In such situations, a conceptual distance between two features should be determined rather than the length of a 'gap' on a linear scale. Within the framework of a comprehensive case-knowledge architecture, the notion of a concept frame that can be associated with a case feature is proposed. Through this component it is possible to represent polymorphic atomic case features, and to systematically establish the concept distance between two real-numbered feature instances.

UR - http://www.scopus.com/inward/record.url?scp=2342503640&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=2342503640&partnerID=8YFLogxK

U2 - 10.1109/ANNES.1995.499473

DO - 10.1109/ANNES.1995.499473

M3 - Conference contribution

T3 - Proceedings - 1995 2nd New Zealand International Two-Stream Conference on Artificial Neural Networks and Expert Systems, ANNES 1995

SP - 210

EP - 213

BT - Proceedings - 1995 2nd New Zealand International Two-Stream Conference on Artificial Neural Networks and Expert Systems, ANNES 1995

A2 - Coghill, George

A2 - Kasabov, Nikola K.

PB - Institute of Electrical and Electronics Engineers Inc.

ER -