From: Animal-borne acoustic data alone can provide high accuracy classification of activity budgets
Devices | N studies | Species | Devices weight (g) | Sampling frequency (Hz) | Number of activities | Algorithm | Global accuracy (%) | Additional information | |||||||||||||
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
Terr | Aqua | Fly | Range | N | Range | N | Range | N | RF | DT | SVM | DA | NN | KNN | MM | Mix | Range | N | |||
Accelerometer alone | 34 | 25 | 8 | 1 | [2.0–371] | 16 | [0.007–100] | 33 | [2–12] | 34 | 9 | 5 | 5 | 4 | 3 | 2 | 1 | 4 | [73.3–100.0] | 34 | Energy expenditure |
Accelerometer + other(s) | 16 | 10 | 4 | 2 | [15.5–160] | 7 | [0.02–100] | 16 | [2–8] | 16 | 4 | 5 | 2 | 2 | 1 | 1 | 0 | 1 | [71.8–99.0] | 15 | Energy expenditure + potentially others |
GPS | 7 | 4 | 0 | 3 | [4.6–5500] | 4 | [0.003–1] | 7 | [2, 3] | 7 | 3 | 2 | 0 | 1 | 0 | 0 | 1 | 0 | [65.0–94.4] | 7 | Geographical position |
Acoustic recorder | 3 | 1 | 0 | 2 | [16.2–41] | 2 | [16,000–22,050] | 3 | [3–19] | 3 | 1 | 1 | 0 | 0 | 0 | 1 | 0 | 0 | [94.1–98.5] | 2 | Biophony, geophony, anthropophony |
Pressure sensor (depth) | 1 | 0 | 1 | 0 | – | 0 | 0.011 | 1 | 3 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 94.0 | 1 | Diving profile |