Chilufya Mutale

Hard-working Student with experience supporting building teams. Versatile employee helping out where needed. Safety-minded worker minimizing risk with awareness and deliberation. I am seeking to maintain a full-time position that offers professional challenges utilizing interpersonal skills, excellent time management and problem-solving skills.

Love’s Cup Undergraduate Semifinalist

Participated in the Love's cup start-up entrepreneurship competition which lasted for 6 weeks of the summer of 2021. During this time, my team and I were able to build the foundational fundamentals in our start-up by developing and writing out a business plan, interviewing our customers from around the world, as well as setting up initial funding and public interest in our company.

Graph-based storage engine for MariaDB

For my school project, I researched and helped develop a graph-based storage engine for MariaDB, a relational database system, that would be ran on a Unix-based High-Performance Computing platform. I was tasked with optimizing and ensuring data handling was efficient and accurate in the system. The toughest task was implementing multi-threading techniques into the code base so that the system could be used in parallel between different user's while still maintaining the speed and efficiency stipulated by the benchmarks. The project was implemented with C and C++.

Fatigue/ Drowsiness detection for drivers

Using machine learning and Artificial Intelligence concepts, to develop a system and framework for detecting driver fatigue with facial recognition only. Using this model, drivers should be able to detect presence of fatigue while driving in a non-intrusive manner, from which, upon flagging, appropriate action can be taken. The project should be able to detect levels of fatigue over a period of time but fast enough to avoid crashes.

XSEDE Tulsa rental evictions

The City of Tulsa has challenged the ORU Data Science Team to analyze several years of utility bills and eviction actions, and develop predictive models for residential eviction likelihood in order to trigger a potential intervention in order to avoid actual eviction if possible. Existing attempts to address this problem have not resulted in satisfactory predictability. (http://www.computationalscience.org/xsede-empower/positions/383)