CLASSIFICATION OF COMPLEX TWO-DIMENSIONAL IMAGES IN A PARALLEL DISTRIBUTED PROCESSING ARCHITECTURE
Neural network analysis is proposed and evaluated as a method of analysis of marine biological data, specifically images of plankton specimens. The quantification of the various plankton species is of great scientific importance, from modelling global climatic change to predicting the economic effec...
Main Author: | |
---|---|
Other Authors: | |
Format: | Other/Unknown Material |
Language: | English |
Published: |
University of Plymouth
1992
|
Subjects: | |
Online Access: | http://hdl.handle.net/10026.1/1843 |
id |
ftunivplympearl:oai:pearl.plymouth.ac.uk:10026.1/1843 |
---|---|
record_format |
openpolar |
spelling |
ftunivplympearl:oai:pearl.plymouth.ac.uk:10026.1/1843 2023-05-15T17:31:53+02:00 CLASSIFICATION OF COMPLEX TWO-DIMENSIONAL IMAGES IN A PARALLEL DISTRIBUTED PROCESSING ARCHITECTURE SIMPSON, ROBERT GILMOUR Faculty of Science and Technology 1992 http://hdl.handle.net/10026.1/1843 en eng University of Plymouth NOT AVAILABLE http://hdl.handle.net/10026.1/1843 Doctorate 1992 ftunivplympearl 2021-03-09T18:32:59Z Neural network analysis is proposed and evaluated as a method of analysis of marine biological data, specifically images of plankton specimens. The quantification of the various plankton species is of great scientific importance, from modelling global climatic change to predicting the economic effects of toxic red tides. A preliminary evaluation of the neural network technique is made by the development of a back-propagation system that successfully learns to distinguish between two co-occurring morphologically similar species from the North Atlantic Ocean, namely Ceratium arcticum and C. longipes. Various techniques are developed to handle the indeterminately labelled source data, pre-process the images and successfully train the networks. An analysis of the network solutions is made, and some consideration given to how the system might be extended. Plymouth Marine Laboratory Other/Unknown Material North Atlantic PEARL (Plymouth Electronic Archiv & ResearchLibrary, Plymouth University) Handle The ENVELOPE(161.983,161.983,-78.000,-78.000) |
institution |
Open Polar |
collection |
PEARL (Plymouth Electronic Archiv & ResearchLibrary, Plymouth University) |
op_collection_id |
ftunivplympearl |
language |
English |
description |
Neural network analysis is proposed and evaluated as a method of analysis of marine biological data, specifically images of plankton specimens. The quantification of the various plankton species is of great scientific importance, from modelling global climatic change to predicting the economic effects of toxic red tides. A preliminary evaluation of the neural network technique is made by the development of a back-propagation system that successfully learns to distinguish between two co-occurring morphologically similar species from the North Atlantic Ocean, namely Ceratium arcticum and C. longipes. Various techniques are developed to handle the indeterminately labelled source data, pre-process the images and successfully train the networks. An analysis of the network solutions is made, and some consideration given to how the system might be extended. Plymouth Marine Laboratory |
author2 |
Faculty of Science and Technology |
format |
Other/Unknown Material |
author |
SIMPSON, ROBERT GILMOUR |
spellingShingle |
SIMPSON, ROBERT GILMOUR CLASSIFICATION OF COMPLEX TWO-DIMENSIONAL IMAGES IN A PARALLEL DISTRIBUTED PROCESSING ARCHITECTURE |
author_facet |
SIMPSON, ROBERT GILMOUR |
author_sort |
SIMPSON, ROBERT GILMOUR |
title |
CLASSIFICATION OF COMPLEX TWO-DIMENSIONAL IMAGES IN A PARALLEL DISTRIBUTED PROCESSING ARCHITECTURE |
title_short |
CLASSIFICATION OF COMPLEX TWO-DIMENSIONAL IMAGES IN A PARALLEL DISTRIBUTED PROCESSING ARCHITECTURE |
title_full |
CLASSIFICATION OF COMPLEX TWO-DIMENSIONAL IMAGES IN A PARALLEL DISTRIBUTED PROCESSING ARCHITECTURE |
title_fullStr |
CLASSIFICATION OF COMPLEX TWO-DIMENSIONAL IMAGES IN A PARALLEL DISTRIBUTED PROCESSING ARCHITECTURE |
title_full_unstemmed |
CLASSIFICATION OF COMPLEX TWO-DIMENSIONAL IMAGES IN A PARALLEL DISTRIBUTED PROCESSING ARCHITECTURE |
title_sort |
classification of complex two-dimensional images in a parallel distributed processing architecture |
publisher |
University of Plymouth |
publishDate |
1992 |
url |
http://hdl.handle.net/10026.1/1843 |
long_lat |
ENVELOPE(161.983,161.983,-78.000,-78.000) |
geographic |
Handle The |
geographic_facet |
Handle The |
genre |
North Atlantic |
genre_facet |
North Atlantic |
op_relation |
NOT AVAILABLE http://hdl.handle.net/10026.1/1843 |
_version_ |
1766129732399661056 |