Table 1 Categorization of the data for training, validation and testing purposes.

From: PHTNet: Characterization and Deep Mining of Involuntary Pathological Hand Tremor using Recurrent Neural Network Models

81 Patients (250 Tremor Assessments)

20% Test Data (16 subjects)

20% Validation Data (16 subjects)

60% Training Data (49 subjects)

• Static tremor was used for quantitative evaluation

• Static tremor was used for validation of the model

• Static tremor was used for training the network

• The action tremor of the three sets was employed to qualitatively monitor the performance of the network.