Minimizing false negatives of measles prediction model: An experimentation of feature selection based on domain knowledge and random forest classifier
In the context of disease prediction model, false negative error occurs when the patient is wrongly predicted as free from the disease.A prediction model development involves the process of data collection and feature selection which extracts relevant features from the dataset. Two commonly employed...
Saved in:
| Main Authors: | , , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Published: |
Blue Eyes Intelligence Engineering and Sciences Publication
2023
|
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1833411302456819712 |
|---|---|
| author | Ahmad W.M.T.W. Ghani N.L.A. Drus S.M. |
| author2 | 55163807800 |
| author_facet | 55163807800 Ahmad W.M.T.W. Ghani N.L.A. Drus S.M. |
| author_sort | Ahmad W.M.T.W. |
| building | UNITEN Library |
| collection | Institutional Repository |
| content_provider | Universiti Tenaga Nasional |
| content_source | UNITEN Institutional Repository |
| continent | Asia |
| country | Malaysia |
| description | In the context of disease prediction model, false negative error occurs when the patient is wrongly predicted as free from the disease.A prediction model development involves the process of data collection and feature selection which extracts relevant features from the dataset. Two commonly employed feature selection approaches are domain knowledge and data-driven, that suffer from bias towards past or current knowledge when applied alone.In this research, we have studied the developmentof measles prediction model by incorporating both the domain knowledge and the data-driven approaches, in particular, the Random Forest classifier.The domain expert has earlier on set the important features based uponhisprior knowledgeon measles for the purpose of minimizing the size of features. Afterward, the attributes became the input in Random Forest classifier and the least important attributes are excluded using the Mean Decrease Gini, in order to experiment its effect on the result. It is found that the removal ofseveral attributes after domain knowledge consultation can provide a good model with less false negative errors. �BEIESP. |
| format | Article |
| id | my.uniten.dspace-24413 |
| institution | Universiti Tenaga Nasional |
| publishDate | 2023 |
| publisher | Blue Eyes Intelligence Engineering and Sciences Publication |
| record_format | dspace |
| spelling | my.uniten.dspace-244132023-05-29T15:23:19Z Minimizing false negatives of measles prediction model: An experimentation of feature selection based on domain knowledge and random forest classifier Ahmad W.M.T.W. Ghani N.L.A. Drus S.M. 55163807800 56940219600 56330463900 In the context of disease prediction model, false negative error occurs when the patient is wrongly predicted as free from the disease.A prediction model development involves the process of data collection and feature selection which extracts relevant features from the dataset. Two commonly employed feature selection approaches are domain knowledge and data-driven, that suffer from bias towards past or current knowledge when applied alone.In this research, we have studied the developmentof measles prediction model by incorporating both the domain knowledge and the data-driven approaches, in particular, the Random Forest classifier.The domain expert has earlier on set the important features based uponhisprior knowledgeon measles for the purpose of minimizing the size of features. Afterward, the attributes became the input in Random Forest classifier and the least important attributes are excluded using the Mean Decrease Gini, in order to experiment its effect on the result. It is found that the removal ofseveral attributes after domain knowledge consultation can provide a good model with less false negative errors. �BEIESP. Final 2023-05-29T07:23:19Z 2023-05-29T07:23:19Z 2019 Article 10.35940/ijeat.A2640.109119 2-s2.0-85074592265 https://www.scopus.com/inward/record.uri?eid=2-s2.0-85074592265&doi=10.35940%2fijeat.A2640.109119&partnerID=40&md5=eb7c6ce92aff7e87ca6d72f9aebdefaa https://irepository.uniten.edu.my/handle/123456789/24413 9 1 3411 3414 All Open Access, Bronze Blue Eyes Intelligence Engineering and Sciences Publication Scopus |
| spellingShingle | Ahmad W.M.T.W. Ghani N.L.A. Drus S.M. Minimizing false negatives of measles prediction model: An experimentation of feature selection based on domain knowledge and random forest classifier |
| title | Minimizing false negatives of measles prediction model: An experimentation of feature selection based on domain knowledge and random forest classifier |
| title_full | Minimizing false negatives of measles prediction model: An experimentation of feature selection based on domain knowledge and random forest classifier |
| title_fullStr | Minimizing false negatives of measles prediction model: An experimentation of feature selection based on domain knowledge and random forest classifier |
| title_full_unstemmed | Minimizing false negatives of measles prediction model: An experimentation of feature selection based on domain knowledge and random forest classifier |
| title_short | Minimizing false negatives of measles prediction model: An experimentation of feature selection based on domain knowledge and random forest classifier |
| title_sort | minimizing false negatives of measles prediction model: an experimentation of feature selection based on domain knowledge and random forest classifier |
| url_provider | http://dspace.uniten.edu.my/ |