A deep architecture for visually analyze Pap cells.

This work proposes a deep ANN architecture which accomplishes the reliable visual classification of abnormal Pap smear cell. The system is driven by independent agents where the first agent consists of a three layer ANN pretrained to closely track a reticle pattern. This net participates in a local...

Full description

Saved in:
Bibliographic Details
Main Author: Chang Tortolero, Oscar Guillermo
Format: Artículos
Language:eng
Published: 2017
Subjects:
Online Access:http://repositorio.educacionsuperior.gob.ec/handle/28000/3861
Tags: Add Tag
No Tags, Be the first to tag this record!
id oai:localhost:28000-3861
recordtype dspace
spelling oai:localhost:28000-38612017-04-13T08:02:18Z A deep architecture for visually analyze Pap cells. Chang Tortolero, Oscar Guillermo ARTIFICIAL NEURAL NETWORKS COMPUTER ARCHITECTURE TRAINING This work proposes a deep ANN architecture which accomplishes the reliable visual classification of abnormal Pap smear cell. The system is driven by independent agents where the first agent consists of a three layer ANN pretrained to closely track a reticle pattern. This net participates in a local close loop that oscillates and produces unique time-space versions of the visual data. This information is stabilized and sparsed in order to obtain compact data representations, with implicit space time content. The obtained representations are delivered to second level agents, formed by independent three layers ANNs dedicated to learning and recognition activities. To train the system a noise-balanced algorithm is employed, where the training set is composed by pap cells and white noise. This combination operating on finite databases and in a self controlled learning loop, auto develops enough cell recognition knowledge as to classify whole classes of Pap smear cells. The system has been tested in real time utilizing documented data bases. 2017-04-12T17:57:49Z 2017-04-12T17:57:49Z 2015 article Chang. O. Constante. P. Gordon. Andres. (2015). A deep architecture for visually analyze Pap cells.Automatic Control (CCAC), 2015 IEEE 2nd Colombian Conference on. Colombia. 978-1-4673-9305-8 http://repositorio.educacionsuperior.gob.ec/handle/28000/3861 eng DOI;10.1109/CCAC.2015.7345210 closedAccess
institution SENESCYT
collection Repositorio SENESCYT
biblioteca Biblioteca Senescyt
language eng
format Artículos
topic ARTIFICIAL NEURAL NETWORKS
COMPUTER ARCHITECTURE
TRAINING
spellingShingle ARTIFICIAL NEURAL NETWORKS
COMPUTER ARCHITECTURE
TRAINING
Chang Tortolero, Oscar Guillermo
A deep architecture for visually analyze Pap cells.
description This work proposes a deep ANN architecture which accomplishes the reliable visual classification of abnormal Pap smear cell. The system is driven by independent agents where the first agent consists of a three layer ANN pretrained to closely track a reticle pattern. This net participates in a local close loop that oscillates and produces unique time-space versions of the visual data. This information is stabilized and sparsed in order to obtain compact data representations, with implicit space time content. The obtained representations are delivered to second level agents, formed by independent three layers ANNs dedicated to learning and recognition activities. To train the system a noise-balanced algorithm is employed, where the training set is composed by pap cells and white noise. This combination operating on finite databases and in a self controlled learning loop, auto develops enough cell recognition knowledge as to classify whole classes of Pap smear cells. The system has been tested in real time utilizing documented data bases.
author Chang Tortolero, Oscar Guillermo
author_facet Chang Tortolero, Oscar Guillermo
author_sort Chang Tortolero, Oscar Guillermo
title A deep architecture for visually analyze Pap cells.
title_short A deep architecture for visually analyze Pap cells.
title_full A deep architecture for visually analyze Pap cells.
title_fullStr A deep architecture for visually analyze Pap cells.
title_full_unstemmed A deep architecture for visually analyze Pap cells.
title_sort deep architecture for visually analyze pap cells.
publishDate 2017
url http://repositorio.educacionsuperior.gob.ec/handle/28000/3861
_version_ 1634995197074997248
score 11,871979