Principal Component Analysis Combined with Second Order Statistical Feature Method for Malaria Parasites Classification
The main challenge in detecting malaria parasites is how to identify the subset of relevant features. The objective of this study was to identify a subset of features that are most predictive of malaria parasites using second-order statistical features and principal component analysis methods. Relev...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
2014
|
| Subjects: | |
| Online Access: | https://repository.ugm.ac.id/101150/1/2014_JATIT_10May.pdf |
| Summary: | The main challenge in detecting malaria parasites is how to identify the subset of relevant features. The objective of this study was to identify a subset of features that are most predictive of malaria parasites using second-order statistical features and principal component analysis methods. Relevant features will provide the successful implementation of the overall detection modeling, which will reduce the computational and analytical efforts. The results showed that the combination of the principal components of the feature value the correlation to the ASM, and the contrast to the correlation can separate classes of malaria parasites. |
|---|