Research Article
An Energy Efficient Wearable Smart IoT System to Predict Cardiac Arrest
Table 2
Quantitative comparison of existing work based on different features.
| Approach | Average Max HR | Approximate Accuracy | Average Max Sampling Rate | Number of Device (s) Used | Power Consumption in Watts |
| PatientsL-ikeMe [27] | 160 | 90% | 120 | 1 | ~ 500 mWatt |
| Daily Strength [28] | 156 | 85% | 110 | 1 | N/A |
| Om-nio [29] | 140 | 80% | 100 | 1 | N/A |
| Everyday Health [30] | 144 | 85% | 80 | 1 | N/A |
| SEHMS [31] | 155 | 78% | 90 | 2 | N/A |
| RMHM [32] | 162 | 82% | 140 | 2 | N/A |
| PHM [33] | 145 | 70% | 150 | 1 | N/A |
| Qardiocore [34] | 135 | 78% | 110 | 1 | N/A |
| Maksimović [35] | 155 | 85% | 105 | 2 | N/A |
| Stecker [36] | 167 | 77% | 130 | 1 | N/A |
| Mancini [37] | 151 | 87% | 135 | 2 | ~ 600 mWatt |
| Sun [38] | 160 | 75% | 95 | 1 | N/A |
| Communicore [39] | 148 | 72% | 150 | 1 | N/A |
| Kavitha1 [40] | 156 | 68% | 155 | 1 | N/A |
| Jagtap [41] | 148 | 72% | 145 | 2 | N/A |
| Our Approach | 135 | 95% | 160 | 1 | ~ 444 mWatt |
|
|