Table 2 Accuracy comparison on STM32F207ZG
From: Detecting unregistered users through semi-supervised anomaly detection with similarity datasets
Algorithm | Threshold | Train accuracy (%) | Validation accuracy (%) | Test accuracy (%) | TFLM accuracy(%) | Model size (Kb) | Used memory (Kb) | Inference speed (Ms) |
|---|---|---|---|---|---|---|---|---|
MLP-based Auto-Encoder | 1.13 | 77 | 73.9 | 58.9 | 58.7 | 304.1953125 | 2.3125 | 198 |
CNN-based Auto-Encoder | 1.09 | 77.6 | 75 | 56.7 | 56.2 | 78.1953125 | 90 | 66415 |
ReNet-5 based Multi-Image | 78 | 97.7 | 92.7 | 89.2 | 85.7 | 206.390625 | 16.875 | 2742 |