Recurrent neural network classifier for three layer conceptual network and performance evaluation
This article was published in JOURNAL OF COMPUTERS [© 2010 ACADEMY PUBLISHER] and the definite version is available at : http://www.jcomputers.us/vol5/jcp0501-05.pdf The article website is at: http://www.jcomputers.us/
Príomhchruthaitheoirí: | , |
---|---|
Rannpháirtithe: | |
Formáid: | Alt |
Teanga: | English |
Foilsithe / Cruthaithe: |
© 2010 ACADEMY PUBLISHER
2016
|
Ábhair: | |
Rochtain ar líne: | http://hdl.handle.net/10361/6618 |
id |
10361-6618 |
---|---|
record_format |
dspace |
spelling |
10361-66182016-11-09T07:10:18Z Recurrent neural network classifier for three layer conceptual network and performance evaluation Md. Khalilur, Rhaman Endo, Tsutomu Department of Computer Science and Engineering, BRAC University Three layer conceptual network Knowledge representation Recurrent neural network. Engineering This article was published in JOURNAL OF COMPUTERS [© 2010 ACADEMY PUBLISHER] and the definite version is available at : http://www.jcomputers.us/vol5/jcp0501-05.pdf The article website is at: http://www.jcomputers.us/ Natural language has traditionally been handled using symbolic computation and recursive processes. Classification of natural language by using neural network is a hard problem. Past few years several recurrent neural network (RNN) architectures have emerged which have been used for several smaller natural language problems. In this paper, we adopt Elman RNN classifier for disease classification for a doctor patient-dialog system. We find that the Elman RNN is able to find a representation for natural language. Contextual analysis in dialog is also a major problem. A three layers memory structure was adopted to address the challenge which we referred to as ”Three Layer Conceptual Network” (TLCN). This highly efficient network simulates the human brain by discourse information. An extended case structure framework is used to represent the knowledge. We used the same case frame structure to train and examine the RNN classifier. This system prototype is based on doctor-patients dialogs. The over all system performance achieved 84% accuracy. Disease identification accuracy depends on number of disease and number of utterances. The performance evaluation is also discussed in this paper. Published 2016-10-20T06:45:30Z 2016-10-20T06:45:30Z 2010-01 Article Rhaman, M. K. (2010). Recurrent neural network classifier for three layer conceptual network and performance evaluation . JOURNAL OF COMPUTERS, 5(1), 40–48. doi:10.4304/jcp.5.1.40-48 1796-203X http://hdl.handle.net/10361/6618 en http://www.jcomputers.us/vol5/jcp0501-05.pdf © 2010 ACADEMY PUBLISHER |
institution |
Brac University |
collection |
Institutional Repository |
language |
English |
topic |
Three layer conceptual network Knowledge representation Recurrent neural network. Engineering |
spellingShingle |
Three layer conceptual network Knowledge representation Recurrent neural network. Engineering Md. Khalilur, Rhaman Endo, Tsutomu Recurrent neural network classifier for three layer conceptual network and performance evaluation |
description |
This article was published in JOURNAL OF COMPUTERS [© 2010 ACADEMY PUBLISHER] and the definite version is available at : http://www.jcomputers.us/vol5/jcp0501-05.pdf The article website is at: http://www.jcomputers.us/ |
author2 |
Department of Computer Science and Engineering, BRAC University |
author_facet |
Department of Computer Science and Engineering, BRAC University Md. Khalilur, Rhaman Endo, Tsutomu |
format |
Article |
author |
Md. Khalilur, Rhaman Endo, Tsutomu |
author_sort |
Md. Khalilur, Rhaman |
title |
Recurrent neural network classifier for three layer conceptual network and performance evaluation |
title_short |
Recurrent neural network classifier for three layer conceptual network and performance evaluation |
title_full |
Recurrent neural network classifier for three layer conceptual network and performance evaluation |
title_fullStr |
Recurrent neural network classifier for three layer conceptual network and performance evaluation |
title_full_unstemmed |
Recurrent neural network classifier for three layer conceptual network and performance evaluation |
title_sort |
recurrent neural network classifier for three layer conceptual network and performance evaluation |
publisher |
© 2010 ACADEMY PUBLISHER |
publishDate |
2016 |
url |
http://hdl.handle.net/10361/6618 |
work_keys_str_mv |
AT mdkhalilurrhaman recurrentneuralnetworkclassifierforthreelayerconceptualnetworkandperformanceevaluation AT endotsutomu recurrentneuralnetworkclassifierforthreelayerconceptualnetworkandperformanceevaluation |
_version_ |
1814309177870254080 |