Skip to main content
Advertisement
Browse Subject Areas
?

Click through the PLOS taxonomy to find articles in your field.

For more information about PLOS Subject Areas, click here.

< Back to Article

Table 1.

Comparison of different state-of-the-art machine learning studies on Parkinson’s disease.

More »

Table 1 Expand

Fig 1.

Experimental framework proposed for the development of this work.

* SVM 1, SVM 2, and SVM 3 classify between PD and Healthy Control (HC).

More »

Fig 1 Expand

Table 2.

Demographic and clinical information of the participants included in the FacePark-GITA database.

More »

Table 2 Expand

Fig 2.

Facial expression stages according to the elicited valence measured with the Affectiva tool.

(left) Healthy woman, 63 years old; (right) Woman with Parkinson’s disease, 67 years old, FE item = 2.

More »

Fig 2 Expand

Table 3.

Results of classification using a single image from the extracted image sequence.

More »

Table 3 Expand

Table 4.

Results of the classification using different combinations of the extracted frames sequences.

More »

Table 4 Expand

Fig 3.

Action Units defined for the Experiment 2.

More »

Fig 3 Expand

Table 5.

FAU detection results of the VGGFace2 model after retraining with the EmotioNet database.

More »

Table 5 Expand

Table 6.

PD classification results using the Freeze 75 model.

More »

Table 6 Expand

Table 7.

PD classification results using the Freeze 50 model.

More »

Table 7 Expand

Fig 4.

PD classification ROC curves obtained from the different input sequences in the retrained Freeze models.

More »

Fig 4 Expand

Table 8.

FAU detection results of the VGG-8 and ResNet-7 training with EmotioNet database.

More »

Table 8 Expand

Table 9.

PD classification results using the VGG-8 model.

More »

Table 9 Expand

Table 10.

PD classification results using the ResNet-7 model.

More »

Table 10 Expand

Fig 5.

Comparison between PD classification ROC curves obtained using the NOnAOffN sequence in the Freeze 75, ResNet-7 and VGG-8.

More »

Fig 5 Expand

Table 11.

Classification results using a CNN architecture trained from scratch with the NOnAOffN sequences.

More »

Table 11 Expand

Table 12.

PD classification results of classification with the Triplet 75 model.

More »

Table 12 Expand

Table 13.

PD classification results of classification with the Triplet 50 model.

More »

Table 13 Expand

Table 14.

PD classification results using the Triplet-VGG8 model.

More »

Table 14 Expand

Table 15.

PD classification results using the Triplet-ResNet7 model.

More »

Table 15 Expand

Fig 6.

(Up) Principal components spaces generated from the features of the different models and (Bottom) score distributions of PD patients and Healthy Control (HC) subjects obtained by the SVM classifier.

More »

Fig 6 Expand

Table 16.

Pairwise comparison results with Mann-Whitney U test and Bonferroni correction for the classification models.

More »

Table 16 Expand

Fig 7.

Heatmaps representations in two different tasks over the three domains studied: (a) Right wink task and (b) Smile task.

More »

Fig 7 Expand