Table 4 Results of CBR and DT RBR on the WISDM smartphone and smartwatch activity and biometrics dataset
From: Building an enhanced case-based reasoning and rule-based systems for medical diagnosis
Approach | Accuracy | Precision | Recall | F1-Score |
|---|---|---|---|---|
Cosine similarity | 43.98% | 32% | 32% | 32% |
Euclidean distance | 48.43% | 34% | 34% | 34% |
Manhattan distance | 50.86% | 38% | 37% | 37% |
Hamming distance | 25.28% | 15% | 12% | 13% |
Pearson correlation coefficient | 43.88% | 32% | 32% | 32% |
Jaccard similarity | 54.19% | 50% | 46% | 45% |
Dice coefficient | 54.19% | 50% | 46% | 45% |
Logistic regression similarity | 73.21% | 55% | 49% | 47% |
Random forest similarity | 89.48% | 88% | 85% | 86% |
GaussianNB similarity | 75.83% | 70% | 69% | 68% |
DT RBR | 86% | 84% | 83% | 84% |
CNN [19] | N/A | 86.8% | N/A | 70.25% |
ConvLSTM [19] | N/A | 83.8% | N/A | 69.6% |