Tshiamo Motaung

I developed a comprehensive course centered on coding with a solution-oriented methodology.

This program emphasizes cultivating a strong foundation in solution-driven thinking and systems design through the utilization of the Qt cross-platform framework. Participants are equipped with the skills to conceptualize and develop systems, progressing from ideation to the creation of installable applications on mobile devices with interactive capabilities.

LapTime offers the functionality to schedule titled sets segmented into repeatable intervals with designated rest periods. Its versatility extends to timing various activities such as workouts, stretching routines, meditation practices, study sessions, and more.

Designed for individuals who prefer strict time management, this application caters to users who seek discipline in adhering to specific workout regimens or routines for predetermined durations. It ensures uniform training by meticulously timing each aspect of the exercise, promoting balanced development of strength across both sides of the body.

Developed an in-vehicle, hands-free, and speech-controlled personalized banking system, which interacts with one from the comfort of their car seat as they drive, putting to good use idle traffic time.

The system extends the current mobile banking infrastructure to banking hands-free behind the wheel. It incorporates machine learning algorithms on statement transactional information for trend analysis, budgeting and financial planning, and integrated financial advisory.

The system was developed for Grindrod Bank's "RE-IMAGINE a Fintech Future" hackathon and took first place.

Published a paper that explored the use of principal component analysis (PCA) techniques to develop classification systems for synthetic-aperture radar (SAR) images.

The concept of PCA is centered on feature extraction and dimensionality reduction. By exploiting spatial differences and variances between data points of a specific data domain, PCA techniques reduce datasets to representations consisting of principal components only. Henceforth, the effect is the reduction of dataset sizes, which translates to a decrease in processing time on these datasets for almost any application of the mathematical technique.