Gait Dynamics Classification with Criticality Analysis and Support Vector Machines

Eltanani, Shadi; Scheper, Tjeerd V. olde; Collett, Johnny; Dawes, Helen; Esser, Patrick

doi:10.3390/math14010177

This is an early access version, the complete PDF, HTML, and XML versions will be available soon.

Open AccessArticle

Gait Dynamics Classification with Criticality Analysis and Support Vector Machines

by

Shadi Eltanani

^1,*

,

Tjeerd V. olde Scheper

¹

,

Johnny Collett

²

,

Helen Dawes

³

and

Patrick Esser

²

¹

School of Engineering, Computing and Mathematics, Faculty of Health, Science and Technology, Oxford Brookes University, Headington Hill Campus, Headington, Oxford OX3 0BP, UK

²

Faculty of Health and Life Sciences, Oxford Brookes University, Headington Campus, Headington, Oxford OX3 0BP, UK

³

NIHR Exeter BRC, Medical School, University of Exeter, St Luke’s Campus, Exeter EX1 2LU, UK

^*

Author to whom correspondence should be addressed.

Mathematics 2026, 14(1), 177; https://doi.org/10.3390/math14010177

Submission received: 20 October 2025 / Revised: 18 December 2025 / Accepted: 30 December 2025 / Published: 2 January 2026

(This article belongs to the Special Issue Mathematical Modelling of Nonlinear Dynamical Systems)

Download Versions Notes

Abstract

Classifying demographic groups of humans from gait patterns is desirable from several long-standing diagnostic and monitoring perspectives. IMU recorded gait patterns are mapped into a nonlinear dynamic representation space using criticality analysis and subsequently classified using standard Support Vector Machines. Inertial-only gait recordings were found to readily classify in the CA representations. Accuracies across age categories for female versus male were 72.77%, 78.95%, and 80.11% for

σ = 0.1

, 1, and 10, respectively; within the female group, accuracies were 73.36%, 76.70%, and 78.90%; and within the male group, 77.65%, 81.48%, and 81.05%. These results show that dynamic biological data are easily classifiable when projected into the nonlinear space, while classifying the data without this is not nearly as effective.

Keywords: criticality analysis; support vector machine; gait pattern detection; chaotic mathematical model; rate control of chaos; demographic analysis

Share and Cite

MDPI and ACS Style

Eltanani, S.; Scheper, T.V.o.; Collett, J.; Dawes, H.; Esser, P. Gait Dynamics Classification with Criticality Analysis and Support Vector Machines. Mathematics 2026, 14, 177. https://doi.org/10.3390/math14010177

AMA Style

Eltanani S, Scheper TVo, Collett J, Dawes H, Esser P. Gait Dynamics Classification with Criticality Analysis and Support Vector Machines. Mathematics. 2026; 14(1):177. https://doi.org/10.3390/math14010177

Chicago/Turabian Style

Eltanani, Shadi, Tjeerd V. olde Scheper, Johnny Collett, Helen Dawes, and Patrick Esser. 2026. "Gait Dynamics Classification with Criticality Analysis and Support Vector Machines" Mathematics 14, no. 1: 177. https://doi.org/10.3390/math14010177

APA Style

Eltanani, S., Scheper, T. V. o., Collett, J., Dawes, H., & Esser, P. (2026). Gait Dynamics Classification with Criticality Analysis and Support Vector Machines. Mathematics, 14(1), 177. https://doi.org/10.3390/math14010177

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Metrics

Article metric data becomes available approximately 24 hours after publication online.

Article Menu

Gait Dynamics Classification with Criticality Analysis and Support Vector Machines

Abstract

Share and Cite

Article Metrics

Further Information

Guidelines

MDPI Initiatives

Follow MDPI