SANTIA: a Matlab-based open-source toolbox for artifact detection and removal from extracellular neuronal signals

Brain Informatics

Table 6 Second dataset’s results for different architectures and sequence length: training loss, validation accuracy, testing accuracy, and testing AUROC

Network	Sequence length (ms)	Training loss	Val. Acc.	Test Acc.	Test AUROC
MLP	50	0.24	0.78	0.78	0.857
	100	0.27	0.89	0.86	0.94
	150	0.15	0.94	0.95	0.99
	200	0.16	0.94	0.96	0.98
1D-CNN	50	0.18	0.92	0.91	0.97
	100	0.15	0.94	0.96	0.97
	150	0.01	0.99	0.99	0.99
	200	0.08	0.98	0.97	0.99
LSTM	50	0.25	0.86	0.86	0.94
	100	0.26	0.89	0.89	0.96
	150	0.02	0.97	0.97	0.99
	200	0.07	0.96	0.96	0.99