Table 9.

A comparison table among the proposed and current state-of-the-art techniques.

Source/Reference	Methodology	Modality	Accuracy
Pires, R. et al. [10]	Convolutional Neural Networks	RF Image	99.0%
Zhang, W. et al. [11]	Neural Networks	RF Image	98.1%
Harun, N. H. et al. [12]	MLP and Artificial Neural Network	RF Image	72.11%
Verbraak, F. D. et al. [13]	Hybrid Features and Deep Learning	RF Image	93.8%
Afrin, R. and Shill, P. C. [14]	Fused Feature and Fuzzy Logic	RF Image	95.63%
Parmar, R. et al. [15]	Neural Networks	RF Image	85%
Xu, K. et al. [16]	Neural Networks	RF Image	94.5%
Gulshan, V. et al. [18]	Deep Learning	RF Image	97.5%
Gargeya R. [19]	Data-Driven Deep Learning Algorithm	RF Image	94%
Proposed Methodology	CARGS, Post-Optimized, Fused Hybrid-Features, and Simple Logistic	BVH RF Image Dataset	99.73%
Proposed Methodology (Validation)	CARGS, Post-Optimized, Fused Hybrid-Features, and Simple Logistic	Publicly Available Dataset (RF-Image)	98.83%