On the Use of <i>t</i>-Distributed Stochastic Neighbor Embedding for Data Visualization and Classification of Individuals with Parkinson’s Disease

<div>Receiver operating characteristic (ROC) curves of SVM classifier for the training and test sets of <i>S</i><sub>PD</sub> group. The orange, green, and blue lines show the ROC curves for <i>t</i>-SNE, Sammon’s mapping, and PCA DR methods, respectively. AUC is the area under the curve. (a) Mean ROC curves for data from the training set and its 95% confidence bounds computed by means of Bootstrap, with 1000 replicas. (b) Mean ROC curves for data from the test set.</div>

Computational and Mathematical Methods in Medicine

fig12

Figure 12

Figure 12: On the Use of <i>t</i>-Distributed Stochastic Neighbor Embedding for Data Visualization and Classification of Individuals with Parkinson’s Disease 

Figure 12 | On the Use of t-Distributed Stochastic Neighbor Embedding for Data Visualization and Classification of Individuals with Parkinson’s Disease 