Center of pressure electronic platform testing is proposed as an affordable early diagnostic tool for persons at risk of Parkinson's disease. A stiffness measures and crossing time statistic are studied for possible use in such a diagnosis.
Center of pressure electronic platform testing is proposed as an affordable early diagnostic tool for persons at risk of Parkinson's disease. A stiffness measures and crossing time statistic are studied for possible use in such a diagnosis.
We study general algorithmic frameworks for online learning tasks. These include binary classification, regression, multiclass problems and cost-sensitive multiclass classification. The theorems that we present give loss bounds on the behavior of our algorithms which depend on general conditions on the iterative step sizes.
Several measures of balance obtained from quiet stance on an electronic platform are described. These measures were found to discriminate patients with Parkinson disease (PD) from normal control subjects. First degree relatives of patients with PD show greater variability on these measures. A primary goal is to develop sensitive measures that would be capable of identifying impaired balance in early stages of non-clinical PD.