Author

Aishwarya Pai

Date of Award

1-5-2023

Document Type

Thesis - SCU Access Only

Publisher

Santa Clara : Santa Clara University, 2023

Degree Name

Master of Science (MS)

Department

Computer Science and Engineering

First Advisor

Silvia Figueira

Abstract

Children with disabilities may not make up most of the population, but their struggles–especially in getting an appropriate education–should not be minimized. From a 2021 blog on the very first Global Disability Summit held in 2018, it was determined that around 10-15% of children living in Africa have disabilities. The blog further states that less than 10% of children with disabilities are attending school in the continent [6]. Thus, determining the reasons why Ghana, Tunisia, and Zimbabwe are unable to provide access to formal education for its youth who are disabled is imperative; it allows us to understand in which ways the situation can be improved on a national level. To this end, I have employed Machine Learning techniques, with two sets of data: one on education-related rates, and the other on world development indicators for these three countries. I use a basic ANN model to predict out of school (OOS) rates for both female children with functional disabilities and those living in rural regions. I additionally use the ARIMA model for time-series analysis, forecasting the world development indicators. Finally, the ANN is again utilized for determining which of the development indicators influence the aforementioned predictions.

SCU Access Only

To access this paper, please log into or create an account in Scholar Commons using your scu.edu email address.

Share

COinS