Convolutional Autoencoder-Based Deep Learning Approach for Aerosol Emission Detection Using LiDAR Dataset

Table 3

Comparisons of current study with previous studies.

References	Techniques	Accuracy	Outcome
[2]	CNN	89%	Object recognition
[1]	Mark CNN	88%	Waveform recognition
[5]	Mod CNN	88.5%	Biomass land recognition
Our proposed	CAE with GAN	98%	Outlier aerosol recognition
	ADAM	81.41%
	AdaGrad	23.57%
	AdaDelta	38.95%
	SGD	78.41%
	RMSProp	69.55%