Prediction of the Freshness of Grass Carp during Storage with Electric Nose Based on Signal Sequence Merging and Wavelet Transform
Table 2
Prediction results of PLS and ANN models based on signal sequence merging and WT for K value in grass carp fillet.
DSSM
RSSM
ANN
PLS
ANN
PLS
RMSECV (mg/100 g)
RMSECV (mg/100 g)
RMSECV (mg/100 g)
RMSECV (mg/100 g)
0.8860
15.5456
0.9897
4.7495
0.8828
15.594
0.9897
4.7495
0.8548
17.4384
0.9861
5.5128
0.8246
18.8033
0.9860
5.5232
0.9088
13.8726
0.9774
7.0117
0.8755
16.0485
0.9770
7.0811
0.9690
8.2243
0.9716
7.8500
0.9601
9.2765
0.9740
7.5217
0.9270
12.5095
0.9683
8.2817
0.9539
10.0793
0.9746
7.4355
0.7907
20.5730
0.9589
9.4117
0.7907
20.5730
0.9341
11.8435
0.8817
15.7388
0.9861
5.5128
0.8462
17.7255
0.986
5.5232
0.9695
8.3167
0.9882
5.0817
0.9525
10.1157
0.9898
4.7357
0.9375
11.5559
0.9829
6.1109
0.9573
9.6091
0.9841
5.9022
0.9731
7.6938
0.9602
9.2683
0.9623
9.0384
0.9670
8.4558
0.9503
10.4359
0.9402
11.2983
0.9612
9.2136
0.9361
11.6664
The four models demonstrate outstanding performance in K value predicition and were subsequently discussed collectively. R2 and RMSECV are highlighted in bold to facilitate quick identification of the models by other researchers.
