Android malware category detection using a novel feature vector-based machine learning model

Cybersecurity

Table 4 Results without Proposed Feature vector generation

Model used	A	P	R	F1-Score
RF	0.931	0.931	0.931	0.931
DT	0.897	0.897	0.897	0.897
LR	0.756	0.756	0.756	0.756
SVM	0.804	0.804	0.804	0.804
NB	0.504	0.505	0.505	0.505
KNN	0.875	0.875	0.875	0.875
AdaBoost	0.786	0.786	0.786	0.786
MLP	0.890	0.890	0.890	0.890
CNN	0.7545	0.754	0.754	0.754

A-Accuracy, P-Precision, R-Recall, RF-Random Forest, DT-Decision Tree, LR-Logistic Regression, SVM-Support Vector Machine, NB-Naïve-Bayes, KNN-K Nearest Neighbour, MLP-Multi-Layer Perceptron, CNN-Convolutional Neural Networks
The highest performance in terms of Accuracy, Precision, Recall, and F1-score are highlighted in bold