Table 3

Comparison results of the last two proposed algorithm in white, babble, fl6 and leopard noises with different SNRs. We report the Average Precision (AP) for each class, and the mean Average Precision (mAP) over all the classes.

Noise scenarioFigure 2a Figure 2b 
NoiseSNRnssmeannssmean
white-100.86230.93810.93100.86960.94050.9313
-50.87920.94220.93800.88410.94500.9397
00.88650.94380.94140.89040.94690.9437
50.88920.94410.94280.89270.94740.9454
100.88960.94360.94320.89320.94730.9461
babble-100.79570.91480.90560.79530.91630.9034
-50.81990.92540.91590.82680.92990.9180
00.84670.93470.92630.85630.93950.9300
50.86820.94030.93390.87540.94440.9373
100.88110.94290.93870.88490.94650.9411
f16-100.77920.90990.89190.81120.92540.9120
-50.80220.92340.90610.84180.93610.9232
00.83830.93500.92080.86550.94220.9311
50.86730.94060.93100.87890.94520.9363
100.88100.94250.93710.88640.94670.9403
leopard-100.69220.88620.87030.75480.91000.8720
-50.71000.89660.87790.76930.91870.8786
00.74040.91020.88870.78710.92670.8849
50.78060.92300.89890.80720.93320.8906
100.81970.93180.90560.82590.93750.8958
network parameters363186647108

or Create an Account

Close subscription notice
Close access options