I am a graduate of Embedded Systems Engineering (ESE) from the University of Leeds (UoL), United Kingdom. A course which I decided to study, even though I lived in a continent (Africa) where no tertiary institution offered it as a degree awarding program (as at then).

My leap into the tech world started when I delved into software development in December 2013, while concluding my Bachelors in Information and Communication Engineering (ICE), from Covenant University, Nigeria.

As a result of my ICE background, I've got some experience in IT also. However, my key interest and competency areas can be succinctly highlighted to be in:

1. Software Engineering
2. Artificial Intelligence &
3. Embedded Systems

In the spirit of keeping this brief, I will put an end to this bio here. For more details, you can check me out on LinkedIn or send me a mail through the Contact page.

In the last few months, I have worked on a couple of interesting projects, some of which are listed below.

• An optimized computer vision system for traffic sign recognition and detection in autonomous vehicles; using a convolutional neural network
• An artificial intelligent grade point adviser (i-GPA) to help fresh undergraduate students make viable plans on their grade points early into school.
• A host based intrusion detection system using genetic algorithm for spoofed IP address detection
• A computer controlled embedded home energy management system using C/C++, Java and SQL
• An ARM Cortex-M3 based temperature monitoring and logging device using Embedded C
• A multiplayer Ping Pong Game on ARM Cortex-A9 using Embedded C/C++
• A Junction traffic control simulator on Intel FPGA using Verilog HDL
• A JPEG image compressor using MATLAB

This project implements a mobile phone based traffic sign detection and recognition system assisted by a Convolutional Neural Network (CNN). Adequate effort is made to utilize heterogeneous computing as much as possible through the newly released Android Neural Networks API which intelligently distribute computationally intensive Neural Networks (NN) tasks to any available onboard accelerator (GPU/NN Accelerator).

For more details on the project, please visit the Code Repository & Project Site