Research Article
Sensor Type, Axis, and Position-Based Fusion and Feature Selection for Multimodal Human Daily Activity Recognition in Wearable Body Sensor Networks
Table 2
Review of the different performance metrics that were used with pertinent techniques in the literature.
| | Study | Accuracy (%) | F1-score | Precision | Recall | CV method | Sensitivity (%) | Specificity (%) |
| | [7] | 96 | — | — | — | Leave-one-out (LOOCV) | — | — | | [8] | 78.2 | — | — | — | 10-fold CV | — | — | | [9] | 93.8 | — | — | — | Leave-one-out (LOOCV) | — | — | | [10] | 81 | — | — | — | Leave-one-out (LOOCV) | — | — | | [11] | 99.8 | — | — | — | 5-fold CV | 100 | 100 | | [12] | 97.4 | — | — | — | — | 95 | 99.7 | | [13] | 71.6 | — | — | — | — | — | — | | [14] | 99.13 | Avg. of all activities 98.86% | Avg. of all activities 98.77% | Avg. of all activities 98.95% | Leave-one-out (LOOCV) | — | — | | [15] | 96.87 | 85.84% | — | — | 10-fold CV | 84.7 | 85.3 | | [16] | 99.22 | Avg. of all activities 99.23% | Avg. of all activities 99.23% | Avg. of all activities 99.23% | 10-fold CV | — | — | | [16] | 95.33 | Avg. of all activities 95.52% | Avg. of all activities 95.52% | Avg. of all activities 95.50% | 10-fold CV | — | — | | [17] | 92.6 | — | — | — | — | — | — | | [18] | 99.9 | 99.4% | 99.4% | 99.4% | Leave-one-out (LOOCV) | — | — | | [19] | 97.2 | 97.2% | 97.2% | 97.2% | — | — | — | | Ours | 99.8 | 99.3% | 99.1% | 99.4% | 10-fold CV | 99.4 | 99.1 |
|
|
