Research Article
An Efficient and Fast Model Reduced Kernel KNN for Human Activity Recognition
Table 4
The distribution of K neighbors in benchmarks and real-world data.
| Benchmarks | K number of neighbors | 2 | 3 | 4 | 5 | 6 | 7 | 8 |
| Iris | 94.70 | 95.20 | 91.73 | 88.53 | 89.47 | 85.26 | 89.95 | Heart | 91.66 | 88.13 | 88.89 | 88.93 | 89.43 | 89.46 | 88.18 | Breast | 82.77 | 81.25 | 80.62 | 80.13 | 79.38 | 78.02 | 78.14 | Diabetes | 84.32 | 84.28 | 83.45 | 84.58 | 84.39 | 84.46 | 84.67 | Seed | 96.03 | 97.36 | 94.01 | 92.66 | 93.78 | 94.71 | 94.02 | Thyroid | 97.67 | 97.09 | 96.71 | 96.09 | 95.92 | 93.08 | 94.42 | Banana | 94.67 | 94.08 | 93.35 | 93.08 | 93.91 | 93.28 | 93.16 | Image | 99.04 | 98.56 | 98.21 | 98.24 | 97.80 | 97.52 | 97.87 | Ringnorm | 92.83 | 76.87 | 74.81 | 74.74 | 74.21 | 73.82 | 73.56 | Splice | 93.51 | 91.91 | 93.39 | 93.36 | 92.68 | 93.00 | 95.46 |
| Human activity data | 3 | 4 | 5 | 6 | 7 | 8 | 9 |
| HAPT | 85.93 | 88.32 | 90.51 | 91.60 | 90.32 | 86.62 | 84.34 | Smartphone | 88.60 | 89.23 | 91.28 | 92.67 | 87.83 | 87.98 | 85.39 |
|
|