Experiment 1

To find out which feature is most useful for the prediction of MMSE and GDS-15, we conducted 15 experiments with different combinations of features that will be used to train the model

Exp 1: demographic

Exp 2: health

Exp 3: social

Exp 4: psychology

Exp 5: demographic + health

Exp 6: demographic + social

Exp 7: social + health

Exp 8: social + psychology

Exp 9: health + psychology

Exp 10: demographic + psychology

Exp 11: demographic + health + social

Exp 12: demographic + health + psychology

Exp 13: demographic + psychology + social

Exp 14: psychology + health + social

Exp 15: demographic + health + social + psychology

5 models were used to predict MMSE and GDS-15.

Decision Tree Classifier
MLP Classifier
KNN Classifier
SVC Classifier
Naive Bayes

Split data train test to 80-20. Then place the 15 combinations of features, with MMSE and GDS-15 as targets respectively.

Rinse and repeat for other models.

Decision Tree

MLP Classifier

KNN Classifier

SVC Classifier

Naive Bayes

Page updated

Report abuse