Hand, Foot and Mouth Disease (HFMD)'s Hotspot Identification using Bipartite Network Model
Hand, foot and mouth disease (HFMD) is considered a common disease among children. However, HFMD recent outbursts in Sarawak had caused many deaths especially children below the age of ten. In this study we are building a Bipartite-Network Based Methodology Framework (BNB-MF) to locate the potentia...
Saved in:
| Main Author: | |
|---|---|
| Format: | Final Year Project Report / IMRAD |
| Language: | en |
| Published: |
Universiti Malaysia Sarawak, (UNIMAS)
2020
|
| Subjects: | |
| Online Access: | http://ir.unimas.my/id/eprint/34485/1/Nor%20Shamira%20binti%20Sabri.pdf http://ir.unimas.my/id/eprint/34485/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Hand, foot and mouth disease (HFMD) is considered a common disease among children. However, HFMD recent outbursts in Sarawak had caused many deaths especially children below the age of ten. In this study we are building a Bipartite-Network Based Methodology Framework
(BNB-MF) to locate the potential hotspot of HFMD as a way to control the number of cases in Sarawak as this disease is known to have no cure yet. The data gathered for this study were pre- processed and formulated into a model which consist of 20 location nodes and 10 human nodes. The link weight between the two sets of nodes was quantified by summing all the environmental predictors such as temperature, humidity, human and vector characteristics. The location nodes in the targeted and validated models were ranked using the web-based search algorithms according to the respective ranking values. The location node ranked based on the vector density
of the disease. Verification analysis with a root mean square error (RMSE) value of 0.000564 and 0.000812 for location and human nodes respectively, which is much lower than threshold value of 0.05. The analytical verification is then performed on HHR and Hub matrix of location nodes to show that they are correlated and proven by SRCC value of 0.874 obtained. Parameter
significance analysis was carried out to determine the relative importance of each parameter and also to produce an optimal performance of the network model. We hope the model formulated can help the public health personnel to plan intervention in an effective manner in order to
reduce the effect of the disease in the coming outbreak. |
|---|