Rochester Institute of Technology
Tensor decomposition of multi-channel wearable sensors for Parkinson’s disease assessment
Abstract
dc:description.abstractThe cure for Parkinson’s disease is considered as one of the greatest challenges in chronic neurological disorder therapy, motivating efforts to provide information to guide therapy adjustments. This disease affects the patients day to day tasks which may vary from drinking water to a more complex task like folding laundry. Postural instability and rigidity of motion can be defined as some of the main symptoms for Parkinson’s disease. In order to better understand and analyze the patients suffering from this disease, the patients were asked to maintain records in a diary of times when they felt an unusual behavior while doing a particular task. Due to the difficulty in maintaining such records, each patient is asked to wear inertial sensors that monitor various movements of the patient. With the help of mathematical tools like Tensors, data fusion is carried out on the signal received from the sensors in order to determine the severity of Parkinson’s Disease. Using machine learning algorithms, it is possible to determine the accuracy with which the developed algorithm manages to determine the extent by which each patient is affected by the Parkinson’s disease.
Degree
thesis:*- Name thesis:degree_name
- Electrical Engineering (MS)
- Level thesis:degree_level
- Thesis
- Discipline thesis:degree_discipline
- Electrical Engineering (KGCOE)
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Ramji, Vignesh
- Contributors dc:contributor
-
- Behnaz Ghoraani
Subjects
dc:subject × 3Identifiers
dc:identifier.*- Repository record dc:identifier
- https://repository.rit.edu/theses/9312