Development of a novel standardized framework for automated gait partitioning

Aditya, Aditya (2022) Development of a novel standardized framework for automated gait partitioning. Master's Thesis / Essay, Biomedical Engineering.

Preview	Text mBME_2022_ARamesh.pdf Download (1MB) | Preview
	Text toestemming.pdf Restricted to Registered users only Download (155kB)

Abstract

Conventional means of characterization, analysis, and diagnosis of gait pathology rely on large and expensive motion capture technology, which demands an elaborate laboratory set-up. Although the said means has established itself as the gold standard for gait analysis, the concomitant resources, accessibility to the patient, and the required expertise has deemed this solution non-scalable. New market solutions such as wearable sensor technology with machine learning-driven algorithmic diagnostics have paved the way for cost-effective alternatives. These novel market solutions see an advantage over the gold standard in terms of the scalability of deployment and accessibility to the end user, without the pre-requisite technical expertise at the users’ end to engender an objective basis for gait analyses. This research project was aimed at providing a framework for the development of a novel machine learning-based algorithm for automated gait analyses by exploring and investigating trends in muscle activation and the resultant gait kinematics. Through this framework, a standardized method for partitioning the gait phases under investigation, and the subsequent analyses through feature extraction has been implemented. This standardized method was used to assess the scalability and flexibility of the novel ML-powered wearable sensor technology for unified gait analysis. Furthermore, this project forms a gold standard for the validation of the tool by comparing the data acquired from the conventional motion capture system and the ML-powered wearable-sensor technology.

Item Type:	Thesis (Master's Thesis / Essay)
Supervisor name:	Greve, C.
Degree programme:	Biomedical Engineering
Thesis type:	Master's Thesis / Essay
Language:	English
Date Deposited:	01 Sep 2022 10:16
Last Modified:	23 Sep 2022 10:23
URI:	https://fse.studenttheses.ub.rug.nl/id/eprint/28605

Actions (login required)

View Item