Skip to main content
. Author manuscript; available in PMC: 2023 May 4.
Published in final edited form as: Comput Syst Sci Eng. 2023 Jan 20;46(1):13–26. doi: 10.32604/csse.2023.034172

Table 5. Comparison of the proposed SNELM with SOTA models (Unit: %).

Dataset Model κ 1 κ 2 κ 3 κ 4 κ 5 κ 6 κ 7
D1 FSV [3] 90.61 ± 1.64 90.27 ± 1.86 90.33 ± 1.62 90.44 ± 1.19 90.46 ± 1.17 80.90 ± 2.37 90.46 ± 1.17
3SBBO [4] 86.40 ± 3.00 85.81 ± 3.14 86.14 ± 3.03 86.12 ± 2.75 86.16 ± 2.77 72.42 ± 5.55 86.15 ± 2.76
CNNSP [5] 94.19 ± 1.63 93.72 ± 1.06 93.75 ± 0.97 93.95 ± 0.96 93.96 ± 0.99 87.92 ± 1.92 93.97 ± 0.98
GCMSVM [6] 72.03 ± 2.94 78.04 ± 1.72 76.66 ± 1.07 75.03 ± 1.12 74.24 ± 1.57 50.20 ± 2.17 74.29 ± 1.53
WEJ [7] 73.31 ± 2.26 78.11 ± 1.92 77.03 ± 1.35 75.71 ± 1.04 75.10 ± 1.23 51.51 ± 2.07 75.14 ± 1.22
GCMSNN [8] 74.80 ± 2.11 77.64 ± 2.05 77.02 ± 1.34 76.22 ± 0.83 75.86 ± 1.00 52.49 ± 1.64 75.89 ± 0.98
SaPSO [9] 85.14 ± 2.74 86.76 ± 1.75 86.57 ± 1.36 85.95 ± 1.14 85.82 ± 1.30 71.95 ± 2.26 85.83 ± 1.30
DLA [10] 91.82 ± 1.25 79.86 ± 1.38 82.03 ± 0.93 85.84 ± 0.65 86.64 ± 0.61 72.23 ± 1.30 86.78 ± 0.62
DeCovNet [11] 90.07 ± 2.63 90.81 ± 1.47 90.76 ± 1.32 90.44 ± 1.39 90.39 ± 1.49 80.92 ± 2.75 90.40 ± 1.48
DLM [12] 87.23 ± 2.19 88.65 ± 1.52 88.51 ± 1.27 87.94 ± 1.03 87.84 ± 1.11 75.92 ± 2.06 87.86 ± 1.11
SNELM (Ours) 96.35 ± 1.50 96.08 ± 1.05 96.10 ± 1.00 96.22 ± 0.94 96.22 ± 0.95 92.45 ± 1.87 96.22 ± 0.95
D2 FSV [3] 90.25 ± 1.27 90.03 ± 0.80 90.06 ± 0.72 90.14 ± 0.70 90.15 ± 0.73 80.29 ± 1.41 90.15 ± 0.74
3SBBO [4] 85.94 ± 1.68 84.75 ± 2.42 84.96 ± 2.16 85.34 ± 1.81 85.44 ± 1.74 70.71 ± 3.61 85.44 ± 1.73
CNNSP [5] 94.44 ± 0.73 93.63 ± 1.60 93.70 ± 1.47 94.03 ± 0.80 94.06 ± 0.76 88.08 ± 1.59 94.05 ± 0.75
GCMSVM [6] 72.38 ± 2.68 77.38 ± 1.96 76.22 ± 1.21 74.88 ± 0.86 74.21 ± 1.25 49.85 ± 1.70 74.25 ± 1.21
WEJ [7] 74.06 ± 2.96 78.06 ± 1.81 77.17 ± 1.17 76.06 ± 1.18 75.55 ± 1.58 52.21 ± 2.28 75.58 ± 1.54
GCMSNN [8] 74.66 ± 1.87 78.00 ± 1.29 77.24 ± 1.15 76.33 ± 1.18 75.92 ± 1.31 52.70 ± 2.34 75.93 ± 1.30
SaPSO [9] 85.31 ± 1.94 86.09 ± 1.43 86.01 ± 1.10 85.70 ± 0.76 85.64 ± 0.87 71.44 ± 1.49 85.65 ± 0.86
DLA [10] 93.28 ± 1.14 78.66 ± 2.51 81.41 ± 1.76 85.97 ± 1.29 86.93 ± 1.10 72.74 ± 2.41 87.14 ± 1.06
DeCovNet [11] 90.03 ± 1.22 90.34 ± 1.25 90.33 ± 1.07 90.19 ± 0.68 90.17 ± 0.69 80.39 ± 1.35 90.18 ± 0.68
DLM [12] 87.37 ± 1.51 88.12 ± 1.94 88.06 ± 1.75 87.75 ± 1.31 87.71 ± 1.29 75.52 ± 2.62 87.71 ± 1.29
SNELM (Ours) 96.00 ± 1.25 96.28 ± 1.16 96.28 ± 1.13 96.14 ± 0.96 96.13 ± 0.96 92.29 ± 1.91 96.14 ± 0.96

Note: Bold means the best. CNNSP [5], DLA [10], DeCovNet [11], and DLM [12] are deep learning models.