Hemisphere Classification on Mona Lisa
100ROC-AUCRandom Forest
Evaluation results
| Method | Links | ||||||||
|---|---|---|---|---|---|---|---|---|---|
| Random ForestFrequency Band=Delta2025.09 | 100 | 96 | 100 | 90 | 95 | 100 | 90 | 0.91 | |
| Random ForestFrequency Band=Theta2025.09 | 100 | 100 | 100 | 100 | 100 | 100 | 100 | 1 | |
| Random ForestFrequency Band=Alpha2025.09 | 100 | 100 | 100 | 100 | 100 | 100 | 100 | 1 | |
| Random ForestFrequency Band=Beta2025.09 | 100 | 100 | 100 | 100 | 100 | 100 | 100 | 1 | |
| Random ForestFrequency Band=Gamma2025.09 | 100 | 98 | 95 | 100 | 98 | 96 | 100 | 0.96 | |
| SVM (RBF)Frequency Band=Delta2025.09 | 100 | 94 | 95 | 90 | 93 | 96 | 90 | 0.87 | |
| SVM (RBF)Frequency Band=Theta2025.09 | 100 | 96 | 100 | 90 | 95 | 100 | 90 | 0.91 | |
| SVM (RBF)Frequency Band=Alpha2025.09 | 100 | 100 | 100 | 100 | 100 | 100 | 100 | 1 | |
| SVM (RBF)Frequency Band=Beta2025.09 | 100 | 100 | 100 | 100 | 100 | 100 | 100 | 1 | |
| SVM (RBF)Frequency Band=Gamma2025.09 | 100 | 98 | 95 | 100 | 98 | 96 | 100 | 0.96 | |
| SVM (Linear)Frequency Band=Delta2025.09 | 100 | 100 | 100 | 100 | 100 | 100 | 100 | 1 | |
| SVM (Linear)Frequency Band=Theta2025.09 | 100 | 100 | 100 | 100 | 100 | 100 | 100 | 1 | |
| SVM (Linear)Frequency Band=Alpha2025.09 | 100 | 100 | 100 | 100 | 100 | 100 | 100 | 1 | |
| SVM (Linear)Frequency Band=Beta2025.09 | 100 | 100 | 100 | 100 | 100 | 100 | 100 | 1 | |
| SVM (Linear)Frequency Band=Gamma2025.09 | 100 | 100 | 100 | 100 | 100 | 100 | 100 | 1 | |
| Deep Neural Network (RMSprop)Frequency Band=Delta2025.09 | 100 | 98 | 100 | 95 | 98 | 100 | 95 | 0.96 | |
| Deep Neural Network (RMSprop)Frequency Band=Theta2025.09 | 100 | 100 | 100 | 100 | 100 | 100 | 100 | 1 | |
| Deep Neural Network (RMSprop)Frequency Band=Alpha2025.09 | 100 | 100 | 100 | 100 | 100 | 100 | 100 | 1 | |
| Deep Neural Network (RMSprop)Frequency Band=Beta2025.09 | 100 | 100 | 100 | 100 | 100 | 100 | 100 | 1 | |
| Deep Neural Network (RMSprop)Frequency Band=Gamma2025.09 | 100 | 98 | 100 | 95 | 98 | 100 | 95 | 0.96 | |
| Small machine learning modelFrequency=β, Optimizer=RMSprop2025.09 | 99.15 | — | — | — | — | — | — | — | |
| Big machine learning modelFrequency=γ, Optimizer=Adadelta2025.09 | 98.76 | — | — | — | — | — | — | — | |
| Big machine learning modelFrequency=β, Optimizer=Adadelta2025.09 | 98.72 | — | — | — | — | — | — | — | |
| Small machine learning modelFrequency=γ, Optimizer=NAdam2025.09 | 98.64 | — | — | — | — | — | — | — | |
| Small machine learning modelFrequency=δ, Optimizer=RMSprop | Adam2025.09 | 97.9 | — | — | — | — | — | — | — | |
| Small machine learning modelFrequency=θ, Optimizer=Adam2025.09 | 97.09 | — | — | — | — | — | — | — | |
| Convolutional Neural Network (CNN)Frequency=β, Optimizer=Adamax2025.09 | 96.72 | — | — | — | — | — | — | — | |
| Small machine learning modelFrequency=α, Optimizer=RMSprop2025.09 | 96.6 | — | — | — | — | — | — | — | |
| Big machine learning modelFrequency=θ, Optimizer=Adadelta2025.09 | 96.53 | — | — | — | — | — | — | — | |
| Big machine learning modelFrequency=α, Optimizer=Adadelta2025.09 | 95.29 | — | — | — | — | — | — | — | |
| Big machine learning modelFrequency=δ, Optimizer=Adadelta2025.09 | 94.39 | — | — | — | — | — | — | — | |
| Convolutional Neural Network (CNN)Frequency=θ, Optimizer=Adadelta | SGD2025.09 | 93.69 | — | — | — | — | — | — | — | |
| Convolutional Neural Network (CNN)Frequency=δ2025.09 | 89.72 | — | — | — | — | — | — | — | |
| Convolutional Neural Network (CNN)Frequency=γ2025.09 | 89.6 | — | — | — | — | — | — | — | |
| Convolutional Neural Network (CNN)Frequency=α, Optimizer=SGD2025.09 | 88.91 | — | — | — | — | — | — | — |