Application Of Neural Network In Malaria Parasites Classification
There are only a few researchers used artificial intelligence to classify malaria parasites. The purpose of this project is to classify malaria parasites into Plasmodium falciparum, Plasmodium vivax and Plasmodium malariae based on ratio of infected red blood cell’s (RBC) size to normal RBC’s...
| Main Author: | |
|---|---|
| Format: | Monograph |
| Language: | English |
| Published: |
Universiti Sains Malaysia
2006
|
| Subjects: | |
| Online Access: | http://eprints.usm.my/58563/ http://eprints.usm.my/58563/1/pplication%20Of%20Neural%20Network%20In%20Malaria%20Parasites%20Classification.pdf |
| _version_ | 1848883932878077952 |
|---|---|
| author | Lim, Chia Li |
| author_facet | Lim, Chia Li |
| author_sort | Lim, Chia Li |
| building | USM Institutional Repository |
| collection | Online Access |
| description | There are only a few researchers used artificial intelligence to classify malaria
parasites. The purpose of this project is to classify malaria parasites into Plasmodium
falciparum, Plasmodium vivax and Plasmodium malariae based on ratio of infected red
blood cell’s (RBC) size to normal RBC’s size, shape of parasite, location of chromatin,
number of chromatin, texture of infected RBC, and number of parasite per RBC using
different types of neural network. Throughout the project, the suitability of the
application of neural networks in malaria parasites classification will be investigated.
The best neural network will be implemented to build an intelligent classifier for
malaria parasites. The first stage of this project is to develop the neural network using
MATLAB Neural Network Toolbox and Borland C++ Builder. Multilayer Perceptron
(MLP) network and Radial Basis Function (RBF) network will be developed using
MATLAB in which MLP network is trained with Back Propagation, Bayesian Rule and
Levenberg-Marquardt learning algorithm and RBF network is trained with k-means
clustering algorithm. Hybrid Multilayer Perceptron (HMLP) network with modified
recursive prediction error algorithm will be developed using Borland C++ Builder. In
the second stage, comparison will be done on the performance of neural networks
developed to yield the best neural network and malaria parasites classification system
will be developed using Borland C++ Builder. Result shows that HMLP network is the
best neural network in classification of malaria parasites. It has a simple architecture,
intelligent and accurate. The final product of this project is a software system that is
capable to classify malaria parasites with high accuracy, high applicability, fast and
cheap. |
| first_indexed | 2025-11-15T18:58:40Z |
| format | Monograph |
| id | usm-58563 |
| institution | Universiti Sains Malaysia |
| institution_category | Local University |
| language | English |
| last_indexed | 2025-11-15T18:58:40Z |
| publishDate | 2006 |
| publisher | Universiti Sains Malaysia |
| recordtype | eprints |
| repository_type | Digital Repository |
| spelling | usm-585632023-05-17T02:13:28Z http://eprints.usm.my/58563/ Application Of Neural Network In Malaria Parasites Classification Lim, Chia Li T Technology TK Electrical Engineering. Electronics. Nuclear Engineering There are only a few researchers used artificial intelligence to classify malaria parasites. The purpose of this project is to classify malaria parasites into Plasmodium falciparum, Plasmodium vivax and Plasmodium malariae based on ratio of infected red blood cell’s (RBC) size to normal RBC’s size, shape of parasite, location of chromatin, number of chromatin, texture of infected RBC, and number of parasite per RBC using different types of neural network. Throughout the project, the suitability of the application of neural networks in malaria parasites classification will be investigated. The best neural network will be implemented to build an intelligent classifier for malaria parasites. The first stage of this project is to develop the neural network using MATLAB Neural Network Toolbox and Borland C++ Builder. Multilayer Perceptron (MLP) network and Radial Basis Function (RBF) network will be developed using MATLAB in which MLP network is trained with Back Propagation, Bayesian Rule and Levenberg-Marquardt learning algorithm and RBF network is trained with k-means clustering algorithm. Hybrid Multilayer Perceptron (HMLP) network with modified recursive prediction error algorithm will be developed using Borland C++ Builder. In the second stage, comparison will be done on the performance of neural networks developed to yield the best neural network and malaria parasites classification system will be developed using Borland C++ Builder. Result shows that HMLP network is the best neural network in classification of malaria parasites. It has a simple architecture, intelligent and accurate. The final product of this project is a software system that is capable to classify malaria parasites with high accuracy, high applicability, fast and cheap. Universiti Sains Malaysia 2006-05-01 Monograph NonPeerReviewed application/pdf en http://eprints.usm.my/58563/1/pplication%20Of%20Neural%20Network%20In%20Malaria%20Parasites%20Classification.pdf Lim, Chia Li (2006) Application Of Neural Network In Malaria Parasites Classification. Project Report. Universiti Sains Malaysia, Pusat Pengajian Kejuruteraan Elektrik dan Elektronik. (Submitted) |
| spellingShingle | T Technology TK Electrical Engineering. Electronics. Nuclear Engineering Lim, Chia Li Application Of Neural Network In Malaria Parasites Classification |
| title | Application Of Neural Network In Malaria Parasites Classification |
| title_full | Application Of Neural Network In Malaria Parasites Classification |
| title_fullStr | Application Of Neural Network In Malaria Parasites Classification |
| title_full_unstemmed | Application Of Neural Network In Malaria Parasites Classification |
| title_short | Application Of Neural Network In Malaria Parasites Classification |
| title_sort | application of neural network in malaria parasites classification |
| topic | T Technology TK Electrical Engineering. Electronics. Nuclear Engineering |
| url | http://eprints.usm.my/58563/ http://eprints.usm.my/58563/1/pplication%20Of%20Neural%20Network%20In%20Malaria%20Parasites%20Classification.pdf |