Deep adaptive temporal network (DAT-Net): an effective deep learning model for parameter estimation of radar multipath interference signals

EURASIP Journal on Advances in Signal Processing

Table 1 Comparison of RMSE for parameter estimation in radar multipath interference signals across various models

Set	Parameter(s)	Signal Type	XGBoost	LSTM	LSTNet	AdaRNN	DAT-Net
1	BW	LFM	0.2356	0.0346	0.3247	0.0151	0.0051
1	BW	NLFM	0.2389	0.0352	0.0524	0.0248	0.0067
1	BW	BPSK	0.2935	0.2441	0.2297	0.0459	0.0476
1	BW	QPSK	0.2701	0.2356	0.2207	0.0840	0.0475
2	PW	LFM	0.1539	0.0680	0.0871	0.0164	0.0087
2	PW	NLFM	0.1506	0.0549	0.0788	0.0186	0.0062
2	NSP	BPSK	0.2650	0.2371	0.2307	0.1344	0.0342
2	NSP	QPSK	0.2564	0.2305	0.2022	0.0432	0.0242
3	BW, PW	LFM	–	0.1782	0.2362	0.0319	0.0193
3	BW, PW	NLFM	–	0.2040	0.2384	0.0272	0.0152
3	BW, NSP	BPSK	–	0.3235	0.3219	0.0944	0.0709
3	BW, NSP	QPSK	–	0.3142	0.3001	0.0911	0.0706