File(s) under permanent embargo
Going through directional changes: evolving human movement classifiers using an event based encoding
conference contribution
posted on 2023-05-23, 14:59 authored by Lones, MA, Jane AltyJane Alty, Duggan-Carter, P, Turner, AJ, Jamieson, DRS, Smith, SLDirectional changes (DC) is an event based encoding for time series data that has become popular in fnancial analysis, particularly within the evolutionary algorithm community. In this paper, we apply DC to a medical analytics problem, using it to identify and summarise the periods of opposing directional trends present within a set of accelerometry time series recordings. The summarised time series data are then used to train classifiers that can discriminate between different kinds of movement. As a case study, we consider the problem of discriminating the movements of Parkinson’s disease patients when they are experiencing a common effect of medication called levodopa-induced dyskinesia. Our results suggest that a DC encoding is competitive against the window-based segmentation and frequency domain encodings that are often used when solving this kind of problem, but offers added benefits in the form of faster training and increased interpretability. CCS CONCEPTS •Computing methodologies → Genetic programming; •Applied computing → Health informatics;
History
Pagination
1365-1371ISBN
978-1-4503-4939-0Department/School
Wicking Dementia Research Education CentrePublisher
Association for Computing MachineryPlace of publication
New York, NY, United StatesEvent title
GECCO '17: Proceedings of the Genetic and Evolutionary Computation Conference CompanionEvent Venue
Berlin, GermanyDate of Event (Start Date)
2017-07-15Date of Event (End Date)
2017-07-19Rights statement
Copyright 2017 ACMRepository Status
- Restricted