.
-
BIOCHEMISTRY OF FASTING – A REVIEW ON METABOLIC SWITCH AND AUTOPHAGY.
Volume - 13 | Issue-1
-
ONE-POT ENVIRONMENT FRIENDLY SYNTHESIS OF IMINE DERIVATIVE OF FURFURAL AND ASSESSMENT OF ITS ANTIOXIDANT AND ANTIBACTERIAL POTENTIAL
Volume - 13 | Issue-1
-
MODELING AND ANALYSIS OF MEDIA INFLUENCE OF INFORMATION DIFFUSION ON THE SPREAD OF CORONA VIRUS PANDEMIC DISEASE (COVID-19)
Volume - 13 | Issue-1
-
INCIDENCE OF HISTOPATHOLOGICAL FINDINGS IN APPENDECTOMY SPECIMENS IN A TERTIARY CARE HOSPITAL IN TWO-YEAR TIME
Volume - 13 | Issue-1
-
SEVERITY OF URINARY TRACT INFECTION SYMPTOMS AND THE ANTIBIOTIC RESISTANCE IN A TERTIARY CARE CENTRE IN PAKISTAN
Volume - 13 | Issue-1
ENHANCING ACCURACY FOR CLASSIFYING DRUGS BASED ON PATIENT DETAIL USING NOVEL ADABOOST ENSEMBLE CLASSIFIER OVER RANDOM FOREST CLASSIFIER
Main Article Content
Abstract
Aim: To classify drugs based on patients’ health-related data using Novel Adaboost Ensemble Classifier over Random Forest classifier. Material and Methods: Classification is performed by content-based Novel Adaboost Ensemble Classifier (N=10) over random forest classifier (N=10). The sample size is calculated using GPower with pretest power as 0.9 and alpha 0.05. Results: Mean accuracy of content-based AdaBoost (98.47%) is high compared to the Random forest classifier (96.45%). The significance value for accuracy and loss is 0.331 (p>0.05). Conclusion: The mean accuracy of drug classifying based on patient detail-based AdaBoost is better than the random forest classifier.
Article Details
