Table 3.
Summary of vision- and environmental-based literature.
| Ref. | #Sen. | Method | #Sub | System Accuracy/ Precision (%) |
Drinking Detection Accuracy (%) |
Null Class |
|---|---|---|---|---|---|---|
| [101] | 1 | ANN 1 | 33 | 98.3 | - | × |
| [104] | 1 | 3D CNN 2, 13 classes | 1950 videos | 96.4 | 92 | √ |
| [102] | 4 | Fuzzy vector quantization, LDA 3 3 class |
4 | 93.3 | 100 | √ |
| [105] * | 2 | kNN 4 4 class | 2 | 89.13 | 100 | √ |
| kNN 4 6 class | 95.4 | 93.1 | ||||
| kNN 4 5 class | 98.7 | 96.88 |
* This paper only reported the precision values and the accuracy values were not reported by the authors. 1 Artificial Neural Network, 2 Convolutional Neural Network, 3 Linear Discriminant Analysis, 4 k-Nearest Neighbours. Where #Sen. corresponds to the number of sensors used and #Sub. corresponds to the number of subjects in the study.