Mamat @ Mohammad, Farisah (2012) Tuberculosis prediction system using artificial neural network / Farisah Mamat @ Mohammad. Degree thesis, Universiti Teknologi MARA Terengganu.
Abstract
Tuberculosis could be predicted using the Artificial Neural Network. This system will reduce the time and cost to predict the tuberculosis disease. ANN will use past datas to run and compare with the new data that will predict whether the individual contracted tuberculosis disease or not. There are a lot of techniques that can be used to make predictions, but the technique which is suitable to be used to make this prediction is neural network system This is because the neural network has two other types of techniques which can be used as feed forward and backward techniques. Back-propagation is one of the feed forward techniques that can be used when we know what the output that will carry out after the information (data) are keyed in. The prediction used in Neural Network technique is whereby some of the data about the symptoms of tuberculosis are used as prediction to see whether the suspected person is infected with tuberculosis or not. The prototype used is in form of an engine that makes some data predictions accuracy are almost the same or even better than previous manual data process.
Metadata
Item Type: | Thesis (Degree) | ||||||
---|---|---|---|---|---|---|---|
Creators: |
|
||||||
Contributors: |
|
||||||
Subjects: | R Medicine > R Medicine (General) > Medical personnel and the public. Physician and the public R Medicine > RA Public aspects of medicine > Communicable diseases and public health R Medicine > RC Internal Medicine > Tuberculosis |
||||||
Divisions: | Universiti Teknologi MARA, Terengganu > Kuala Terengganu Campus > Faculty of Computer and Mathematical Sciences | ||||||
Programme: | Bachelor of Computer Science (Hons) | ||||||
Item ID: | 35180 | ||||||
Uncontrolled Keywords: | Tuberculosis ; Artificial Neural Network ; Disease | ||||||
URI: | http://ir.uitm.edu.my/id/eprint/35180 |
Download
![]() |
Text
35180.pdf Download (131kB) |
Fulltext
ID Number
35180

View in Google Scholar
Actions (login required)
![]() |
View Item |