Mercy Mawia Mulwa

footer strip
An Image of Mercy Mawia Mulwa
Kenya

“Explainable Machine Learning Approach on Sensor Based Human Gait Analysis for Assistive Device Model Prediction and 3-D Design”

Country of Study
Kenya

Institution
Jomo Kenyatta University of Agriculture and Technology

Expected Year of Completion
2024

Thematic Area
Information and Technology

Education
Mercy is a Computing and Information Technology r PhD student  at Jomo Kenyatta University of Agriculture and Technology (JKUAT) in Kenya. She is also the Deputy Principal at Mahanaim Educational Institute. She holds an MSc in ICT Policy and Regulations from JKUAT and is expected to complete her studies in 2024.

Research Summary
Mercy’s research addresses the speed, affordability and disuse challenges of affordable individualised ortho prosthetic devices (ADs) with explainable Machine learning and 3D image reconstruction models. The demand for ADs is growing due to a corresponding need for improved quality of life among People Living with Disability (PLWD). Despite the effort by various key players to avail such devices to those who need them, out of the current one billion people in need, only 10 percent have access to such devices. This is because of limited availability of the ADs, their affordability and lack of access to the devices among other reasons. At the same time, there is disuse among those using the ADs because most of those devices do not  perfectly match their body types. Through the use of Machine Learning models and 3D image reconstruction incorporated in 3D printing, this could be achieved. However, due to the black box nature of the existing Machine Learning (ML) models, orthopaedists still manually design and hand-craft the ADs. With adequate collection of human gait using Internet of Things (IOT) and sensor technology, it is possible to design affordable individualised prosthetics and orthotics devices very fast. Mercy’s use of Machine Learning and 3D image reconstruction models incorporated with sensor technology captures gait data from the user, classifying the data and generating the design features.

Publications:
1. Effects of Network Infrastructure on Universal Access: A Survey of ICT Access in Kenya

Subscribe to our Newsletter

Follow our newsletter to be the first to know when we add a new resource!

Donate

You can support Mawazo’s work by making a charitable donation by credit or debit card, or through PayPal.  We are a registered 501(c)(3) non-profit in the US, and all donations are tax deductible for US donors.