Going through directional changes: evolving human movement classifiers using an event based encoding

Directional changes (DC) is an event based encoding for time series data that has become popular in financial 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.

[1]  Andrew M. Tyrrell,et al.  Positional Independence and Recombination in Cartesian Genetic Programming , 2006, EuroGP.

[2]  Fernando E. B. Otero,et al.  Generating Directional Change Based Trading Strategies with Genetic Programming , 2015, EvoApplications.

[3]  Julian Francis Miller Cartesian Genetic Programming , 2011, Cartesian Genetic Programming.

[4]  Edward Tsang,et al.  A Directional-Change Events Approach for Studying Financial Time Series , 2011 .

[5]  Joan Cabestany,et al.  Dopaminergic-induced dyskinesia assessment based on a single belt-worn accelerometer , 2016, Artif. Intell. Medicine.

[6]  A. Crossman Functional anatomy of movement disorders , 2000, Journal of anatomy.

[7]  J. Nutt,et al.  The Unified Dyskinesia Rating Scale: Presentation and clinimetric profile , 2008, Movement disorders : official journal of the Movement Disorder Society.

[8]  Tom Robinson,et al.  Levodopa-induced dyskinesia in Parkinson’s disease: clinical features, pathogenesis, prevention and treatment , 2007, Postgraduate Medical Journal.

[9]  Thomas G. Dietterich Machine Learning for Sequential Data: A Review , 2002, SSPR/SPR.

[10]  Julian Francis Miller,et al.  Cartesian genetic programming , 2000, GECCO '10.

[11]  Andrew M. Tyrrell,et al.  Evolving Classifiers to Recognize the Movement Characteristics of Parkinson's Disease Patients , 2014, IEEE Transactions on Evolutionary Computation.

[12]  James B. Glattfelder,et al.  Patterns in high-frequency FX data: discovery of 12 empirical scaling laws , 2008, 0809.1040.

[13]  Stephen L. Smith,et al.  Classification and characterisation of movement patterns during levodopa therapy for parkinson's disease , 2014, GECCO.

[14]  Mukesh Dhamala,et al.  Is the Brain's Inertia for Motor Movements Different for Acceleration and Deceleration? , 2009, PloS one.

[15]  Edward Tsang,et al.  Profiling high-frequency equity price movements in directional changes , 2017 .

[16]  Fernando E. B. Otero,et al.  Evolving trading strategies using directional changes , 2017, Expert Syst. Appl..