The future of fall prevention: integrating OpenPose with cutting-edge ML models

Shina Samuel Kolawole; Gautam Siddharth Kashyap; Olamide Emmanuel Kolawole; Miao Yu

doi:10.4108/eetpht.11.9013

The future of fall prevention: integrating OpenPose with cutting-edge ML models

Shina Samuel Kolawole, Gautam Siddharth Kashyap^*, Olamide Emmanuel Kolawole, Miao Yu

^*Corresponding author for this work

Research output: Contribution to journal › Article › peer-review

2 Citations (Scopus)

17 Downloads (Pure)

Abstract

The research paper aims to assess ML models for video-recorded gaits with an aim of classifying people into high or low risks to fall groups. Several ML algorithms were tried employing OpenPose for CV, with RF showing the best outcomes: 93% accuracy along with F1-score as well as balanced sensitivity (93.50%) as well as specificity (92.50%). Some important determining factors were speed per unit distance, angle among other statistical measures. In comparison to wearables-based DL approaches plus traditional fall detection methods, this study’s approach showed higher accuracy and adaptability within health care settings.

Original language	English
Pages (from-to)	1-9
Number of pages	9
Journal	EAI Endorsed Transactions on Pervasive Health and Technology
Volume	11
DOIs	https://doi.org/10.4108/eetpht.11.9013
Publication status	Published - 2025
Externally published	Yes

Bibliographical note

Copyright the Author(s) 2025. Version archived for private and non-commercial use with the permission of the author/s and according to publisher conditions. For further rights please contact the publisher.

Keywords

Deep Learning
Fall
Healthcare
Machine Learning
OpenPose

Access to Document

10.4108/eetpht.11.9013Licence: CC BY-NC-SA

Publisher version (open access)Final published version, 1.22 MBLicence: CC BY-NC-SA

Cite this

@article{552d7477565741ab8095ef4a170ebbe4,

title = "The future of fall prevention: integrating OpenPose with cutting-edge ML models",

abstract = "The research paper aims to assess ML models for video-recorded gaits with an aim of classifying people into high or low risks to fall groups. Several ML algorithms were tried employing OpenPose for CV, with RF showing the best outcomes: 93\% accuracy along with F1-score as well as balanced sensitivity (93.50\%) as well as specificity (92.50\%). Some important determining factors were speed per unit distance, angle among other statistical measures. In comparison to wearables-based DL approaches plus traditional fall detection methods, this study{\textquoteright}s approach showed higher accuracy and adaptability within health care settings.",

keywords = "Deep Learning, Fall, Healthcare, Machine Learning, OpenPose",

author = "Kolawole, \{Shina Samuel\} and Kashyap, \{Gautam Siddharth\} and Kolawole, \{Olamide Emmanuel\} and Miao Yu",

note = "Copyright the Author(s) 2025. Version archived for private and non-commercial use with the permission of the author/s and according to publisher conditions. For further rights please contact the publisher.",

year = "2025",

doi = "10.4108/eetpht.11.9013",

language = "English",

volume = "11",

pages = "1--9",

journal = "EAI Endorsed Transactions on Pervasive Health and Technology",

issn = "2411-7145",

publisher = "European Alliance for Innovation",

}

TY - JOUR

T1 - The future of fall prevention

T2 - integrating OpenPose with cutting-edge ML models

AU - Kolawole, Shina Samuel

AU - Kashyap, Gautam Siddharth

AU - Kolawole, Olamide Emmanuel

AU - Yu, Miao

N1 - Copyright the Author(s) 2025. Version archived for private and non-commercial use with the permission of the author/s and according to publisher conditions. For further rights please contact the publisher.

PY - 2025

Y1 - 2025

N2 - The research paper aims to assess ML models for video-recorded gaits with an aim of classifying people into high or low risks to fall groups. Several ML algorithms were tried employing OpenPose for CV, with RF showing the best outcomes: 93% accuracy along with F1-score as well as balanced sensitivity (93.50%) as well as specificity (92.50%). Some important determining factors were speed per unit distance, angle among other statistical measures. In comparison to wearables-based DL approaches plus traditional fall detection methods, this study’s approach showed higher accuracy and adaptability within health care settings.

AB - The research paper aims to assess ML models for video-recorded gaits with an aim of classifying people into high or low risks to fall groups. Several ML algorithms were tried employing OpenPose for CV, with RF showing the best outcomes: 93% accuracy along with F1-score as well as balanced sensitivity (93.50%) as well as specificity (92.50%). Some important determining factors were speed per unit distance, angle among other statistical measures. In comparison to wearables-based DL approaches plus traditional fall detection methods, this study’s approach showed higher accuracy and adaptability within health care settings.

KW - Deep Learning

KW - Fall

KW - Healthcare

KW - Machine Learning

KW - OpenPose

UR - https://www.scopus.com/pages/publications/105002443050

U2 - 10.4108/eetpht.11.9013

DO - 10.4108/eetpht.11.9013

M3 - Article

AN - SCOPUS:105002443050

SN - 2411-7145

VL - 11

SP - 1

EP - 9

JO - EAI Endorsed Transactions on Pervasive Health and Technology

JF - EAI Endorsed Transactions on Pervasive Health and Technology

ER -

The future of fall prevention: integrating OpenPose with cutting-edge ML models

Abstract

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Cite this