Brain Tumor Classification on Kaggle Brain Tumor
99.85AccuracyKNN, SVM, ResNet50, Xception, CNN-MRI, DenseNet121, ResNet101 (Proposed Method)
Evaluation results
| Method | Links | |
|---|---|---|
| KNN, SVM, ResNet50, Xception, CNN-MRI, DenseNet121, ResNet101 (Proposed Method)Classifier Type=Ensemble System, Ensemble Logic=Optimized Weighted Voting System2026.03 | 99.85 | |
| GoogleNet, ShuffleNet, NasNet-Mobile, LDA, SVM, KNN (Ali et al.)Classifier Type=Ensemble System2026.03 | 98.4 | |
| CNN (Rasheed et al. [5])Classifier Type=Single Classifiers2026.03 | 98.33 | |
| SVM, Random Forest, eXtreme Gradient Boosting (Roy et al.)Classifier Type=Ensemble System2026.03 | 98.15 | |
| EfficientNet (Ramakrishna et al.)Classifier Type=Single Classifiers2026.03 | 98 | |
| CNN and SVM (Bansal et al.)Classifier Type=Ensemble System2026.03 | 98 | |
| CNN (Rasheed et al. [4])Classifier Type=Single Classifiers2026.03 | 97.85 | |
| EfficientNet (Ishaq et al.)Classifier Type=Single Classifiers2026.03 | 97.4 | |
| ResNet50, InceptionV3, InceptionResNetV2, Xception, MobileNetV2, EfficientNetB0 (Guzman et al.)Classifier Type=Ensemble System2026.03 | 97.12 | |
| CNN (Asiri et al.)Classifier Type=Single Classifiers2026.03 | 94.58 |