Design and evaluation of a multi-model, multi-level artificial neural network for eczema skin lesion detection
There are several current systems developed to identify common skin lesions such as eczema that utilize image processing and most of these apply feature extraction techniques and machine learning algorithms. These systems extract the features from pre-processed images and use them for identifying th...
Saved in:
Main Authors: | , , , , |
---|---|
Format: | text |
Published: |
Animo Repository
2016
|
Subjects: | |
Online Access: | https://animorepository.dlsu.edu.ph/faculty_research/1903 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | De La Salle University |
id |
oai:animorepository.dlsu.edu.ph:faculty_research-2902 |
---|---|
record_format |
eprints |
spelling |
oai:animorepository.dlsu.edu.ph:faculty_research-29022021-07-30T01:52:09Z Design and evaluation of a multi-model, multi-level artificial neural network for eczema skin lesion detection De Guzman, Launcelot C. Maglaque, Ryan Paolo C. Torres, Vianca May B. Zapido, Simon Philippe A. Cordel, Macario O. There are several current systems developed to identify common skin lesions such as eczema that utilize image processing and most of these apply feature extraction techniques and machine learning algorithms. These systems extract the features from pre-processed images and use them for identifying the skin lesions through machine learning as the core. This paper presents the design and evaluation of a system that implements a multi-model, multi-level system using the Artificial Neural Network (ANN) architecture for eczema detection. In this work, multi-model system is defined as architecture with different models depending on the input characteristic. The outputs of these models are integrated by a decision layer, thus multi-level, which computes the probability of an eczema case. The resulting system has 68.37% average confidence level as opposed to the 63.01% of the single level, i.e. Single model, system in the actual testing of eczema versus non-eczema cases. Furthermore, the multi-model, multi-level design produces more stable models in the training phase wherein over fitting was reduced. © 2015 IEEE. 2016-10-20T07:00:00Z text https://animorepository.dlsu.edu.ph/faculty_research/1903 Faculty Research Work Animo Repository Eczema—Diagnosis—Data processing Pattern recognition systems Neural networks (Computer science) Computer Sciences |
institution |
De La Salle University |
building |
De La Salle University Library |
continent |
Asia |
country |
Philippines Philippines |
content_provider |
De La Salle University Library |
collection |
DLSU Institutional Repository |
topic |
Eczema—Diagnosis—Data processing Pattern recognition systems Neural networks (Computer science) Computer Sciences |
spellingShingle |
Eczema—Diagnosis—Data processing Pattern recognition systems Neural networks (Computer science) Computer Sciences De Guzman, Launcelot C. Maglaque, Ryan Paolo C. Torres, Vianca May B. Zapido, Simon Philippe A. Cordel, Macario O. Design and evaluation of a multi-model, multi-level artificial neural network for eczema skin lesion detection |
description |
There are several current systems developed to identify common skin lesions such as eczema that utilize image processing and most of these apply feature extraction techniques and machine learning algorithms. These systems extract the features from pre-processed images and use them for identifying the skin lesions through machine learning as the core. This paper presents the design and evaluation of a system that implements a multi-model, multi-level system using the Artificial Neural Network (ANN) architecture for eczema detection. In this work, multi-model system is defined as architecture with different models depending on the input characteristic. The outputs of these models are integrated by a decision layer, thus multi-level, which computes the probability of an eczema case. The resulting system has 68.37% average confidence level as opposed to the 63.01% of the single level, i.e. Single model, system in the actual testing of eczema versus non-eczema cases. Furthermore, the multi-model, multi-level design produces more stable models in the training phase wherein over fitting was reduced. © 2015 IEEE. |
format |
text |
author |
De Guzman, Launcelot C. Maglaque, Ryan Paolo C. Torres, Vianca May B. Zapido, Simon Philippe A. Cordel, Macario O. |
author_facet |
De Guzman, Launcelot C. Maglaque, Ryan Paolo C. Torres, Vianca May B. Zapido, Simon Philippe A. Cordel, Macario O. |
author_sort |
De Guzman, Launcelot C. |
title |
Design and evaluation of a multi-model, multi-level artificial neural network for eczema skin lesion detection |
title_short |
Design and evaluation of a multi-model, multi-level artificial neural network for eczema skin lesion detection |
title_full |
Design and evaluation of a multi-model, multi-level artificial neural network for eczema skin lesion detection |
title_fullStr |
Design and evaluation of a multi-model, multi-level artificial neural network for eczema skin lesion detection |
title_full_unstemmed |
Design and evaluation of a multi-model, multi-level artificial neural network for eczema skin lesion detection |
title_sort |
design and evaluation of a multi-model, multi-level artificial neural network for eczema skin lesion detection |
publisher |
Animo Repository |
publishDate |
2016 |
url |
https://animorepository.dlsu.edu.ph/faculty_research/1903 |
_version_ |
1707059170934521856 |