Neural Network for Recognition of County Centre Post Codes
AbstractThe work represents an artificial neural networkf01· recognitionof county centre post codes. The neural networkPOSTKLAS se1ves as the classification system for the sorting oftwo-digit address data. The de1·eloped model represents atwo-layer network which learns by using backpropagation algorithm.The method of address data recording in the model hasbeen presented. By analysing the sorting results the possibilitywas determined of applying the developed neural network forrecognition even in cases of distorted input pal/erns. The modellingwas done by means of Mat/ab programming ~ystem.
H. Demuth, M. Beale, Neural Network Too/box For Use
with Matlab, User's guide, MathWorks, 1993.
H. Gold, Z. Kavran, D. Kovacevic, 'Recognition of
geometrical properties of traffic signs with artificial neural
network', Suvremeni promet - Proceedings of the 5th
International Symposium Organisation and Safety in
Traffic, Opatija, 1997, Vol. 17, No. 3-4, pp. 330-334 (in
H. Gold, 'Neural networks in traffic and transport'',
Teaching material and instructions for omputer practice,
Fakultet prometnih znanosti, Zagrcb, 1998, p. 107
D. Hladnik, 'Automatic reading of address data',
HP-Journal Hrvatske poste, No. 4/99, pp. 15-17 (in
P. D. Wasserman, Neural Computing: The01y and Practice,
Van Nostrand Reinhold, New York, 1985.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).