In this paper, we propose a novel model-free technique for differentiating both Parkinson’s Disease (PD) patients from healthy subjects and mild PD patients from moderate ones by using a handwriting analysis tool. The tool is based on the analysis of biometric signals and the application of Artificial Neural Network (ANN)-based classifier. Experimental tests have been carried on with both healthy and PD subjects to identify the most representative features and to assess the accuracy and repeatability of classification performances achieved through optimal topology ANNs. Finally, the obtained results are reported and discussed to infer some important properties on classification approaches and the role of muscular activities on the handwriting analysis applied to neurodegenerative disease research.
|Titolo:||A Model-Free Computer-Assisted Handwriting Analysis Exploiting Optimal Topology ANNs on Biometric Signals in Parkinson’s Disease Research|
|Data di pubblicazione:||2018|
|Nome del convegno:||14th International Conference on Intelligent Computing, ICIC 2018|
|Digital Object Identifier (DOI):||http://dx.doi.org/10.1007/978-3-319-95933-7_74|
|Appare nelle tipologie:||4.1 Contributo in Atti di convegno|