![](bg6.png)
10 CONCLUSIONS
By way of conclusion and to sum up:
• In this paper, an expert system is presented
which will offer the user a new interactive
species identification method whose main
contribution is the use of intelligent techniques
to deal with uncertainty
• It solves problems in which incomplete data is
handled. This is an important feature, since in
taxonomical classification processes
information and observations are not complete.
• IA and Internet technology offer new
advantages to the popularisation of Botany.
• The user can easily learn the features to observe
through interaction with the query interface. It
also is able to spread expert knowledge by
justifying the solution, so that the user can learn
the reasoning followed by the system.
• The model to represent the knowledge is also
useful in order to produce automatic keys or
computer-generated keys.
• The system is a practical operative tool which
may be used on-line and which will enable
different taxa comprising the Iberian
Gymnosperm flora to be recognized.
• The model can be extended to other branches of
Biology as well; it is a question of generating a
suitable knowledge base and a user interface,
while the inference system does not change.
REFERENCES
Atkinson, W. D. & Gammerman, A. 1987. An application
of expert systems technology to biological
identification. Taxon 36, 705–714.
Bartley. M. 1999.
http://www.herbaria.harvard.edu/computerlab/web_ke
ys/navikey/. Consulted 17/2/03
Castroviejo, S., Laínz, M., López González, G.,
Montserrat, P., Muñoz Garmendia, F., Paiva, J. &
Villar, L. 1986. Flora Ibérica. Plantas vasculares de
la Península Ibérica e Islas Baleares. Vol. I ed. Real
Jardín Botánico, Madrid.
Centre for Pest Information Technology and Transfer
(CPITT) at the University of Queensland .1999.
http://www.lucidcentral.com/, Consulted 17/2/03
Dallwitz, M. J., Paine, T. A. & Zurcher, E. J. 1993. User’s
guide to the DELTA System: a general system for
processing taxonomic descriptions. 4th edition.
http://biodiversity.uno.edu/delta/
Dallwitz, M. J. 2000. A comparison of interactive
identification programs. http://biodiversity
.uno.edu/delta.
Dickinson T. 1999.
http://prod.library.utoronto.ca/polyclave/. Royal
Ontario Museum Canada. Consulted 17/2/03
Durkin, J. 1994. Expert Systems. Design and development.
Ed. Prentice Hall International, London .
Fermanian T.; Michalski R. S. 1989. Weeder: An
Advisory System for the Identification of Grasses in
Turf. Agronomy Journal ,81(2), pp 313-316
Font Quer, P. 1979. Diccionario de Botánica. Ed. Labor,
Barcelona.
García Rollán, M. 1983. Claves de la flora de España.
Península y Baleares. Vol. I., ed. Ed. Mundi-Prensa,
Madrid.
Grosser D. & Conruyt N. 1999. Tree-based classification
approach for dealing with complex knowledge in
natural sciences. Proceedings of ACAI'99 - Machine
Learning and Applications. Chania (Greece).
Grove R. F. & Hulse A. C. 1999. An Internet-Based
Expert System for Reptile Identification. The First
International Conference on the Practical Application
of Java, London
Grzymala-Busse, J.W. 1991. Managing Uncertainty in
Expert Systems. Ed. Kluwer Academic Publishers.
Ignizio, J. P. 1991. Introduction to Expert Systems. The
Development and Implementation of Rule-Based
Expert Systems. Ed. McGraw-Hill, New York.
Li D., Fu Z. & Duan Y. 2002. Fish - Expert: a web-based
expert system for fish disease diagnosis. Expert
Systems with Applications 23, 311–320.
Meacham C. 1996, The Meka for Windows FAQ page.
http://ucjeps.berkeley.edu/meacham/meka/ Jepson
Herbarium U.C. Berkeley, Consulted 17/2/03
Shortlife, E., & Buchanan, B. G. 1975. A Model of
Inexact Reasoning in Medicine. Mathematical
Biosciences 23: 351-379.
XID Services, Inc. 1999. http://www.xidservices.com/.
Consulted 17/2/03
G.R.E.E.N. - AN EXPERT SYSTEM TO IDENTIFY GYMNOSPERMS
221