Skip to main content

Building Ojumi


I would like to show a great appreciation to MBB grant for sponsoring this project. For me, it is a great gesture of believe and support for innovators in Africa. We live in a world where it is hard to be trusted to build anything of substance without too much bureaucracy and noise. After the award of the grant (#700,000) in December 2024, I kickstarted the project. The project was divided into 4 key parts which are the Overview Research, Prototype Development, AI Model Development and Project Testing.

Each of these processes is a series of back-and-forth interactions that served as a critical milestone for the project and taught me some great lessons. The project research involves one-on-one meetings, sharing questionnaires, and talking to potential users about the idea, both physically and on social media. The feedback was great, and I got the validation that ojumi is a needed solution that people are willing to pay for. This process took about a month and really got me excited.



For a prototype, I developed an android app with the concept of identity at its core. I focused on data collection, security and data privacy as I built the app. The app has critical features with ready-made use cases for testing. I wanted it to be practical, functional, scalable and secure for each process. This process took about 5 months after which the first Ojumi user interface video was created.

After the android app, I needed to be able to use it on my system so I developed the Ojumi desktop app. I realized the hardware limitations of the android app and often times the need for me to have a localized interface to test features and see further integrations. Furthermore, off-the-shelf solutions are too expensive so I made the effort to build and test locally because of the huge cost implication of cloud services for the ai modules. I only test on cloud services when and where necessary. To truly verify an identity, you need a combination of an array of information in various formats (could be documents, live video, pictures and input text) which needs to be crunched for proper identity detection. Hence, I decided to setup individual pipelines to test and improve each of these aspects.

For the prototype, I focused on the data collection, storage and formatting, user onboarding and ease of use. I also created quick use cases that can provide values to the app users and document the process along the way. At the core, ojumi relies on two cores processes, prior enrollment and efficient matching. In our testing process, I realized the efficiency of identification is directly influenced by the efficiency and cost of detection based on past enrolled data points.

Ojumi is a great project and MBB grant have made it transform from just an idea to something that is tangible and currently under scaling.

Currently, Ojumi is undergoing testing. I am also working on more ways to improve the efficiency of the software and do more demos. Next will be more advance ai detection, cloud scalability and portability features.

For more of this, follow [at]ojumiai on social media.


Related article

Lochav

Our locust harvesting technology is called locharv. It is simply a  drone driven, lightweight, origami deployable structure for locust fishing. At the core is our ai driven technology for locust tracking, capturing  and  notification system. Our solution is designed to capture the maximum obtainable locust per flight with its capturing net. This net is a specially designed origami net specifically for locust capturing.  Visit our website for more locharv website

Becoming a MATLAB Student Ambassador

It is indeed an honor to share that I am now the MATLAB student ambassador for the University of Lagos. My role is to organise programs and events that helps grow the adoption of the MATLAB software on campus. I will also be undergoing some inhouse training under the tootalage of the engineers at MathWorks.  MATLAB student ambassadors are important links between MathWorks and the University of Lagos. Ambassadors inform students about the availability of MATLAB and Simulink on campus and showcase the products’ functionality—all while earning money. Millions of engineers and scientists rely on MATLAB and Simulink in a wide range of applications and industries. I am now part of the global MATLAB community and will gain essential professional experience by working with a leading technical computing software company while still in school.  

Temperature and Pressure Control Simulation

 We considered an interacting loop and process fermentation. Models the fermentation tank temperature and pressure dynamics. Uses PID control for both temperature and pressure. Simulates the system's response to heat (yeast) and CO₂ disturbances. Plots real-time regulation toward setpoints.

Marshalling University of Lagos MATLAB Community

I recently gave a talk to other MATLAB Ambassadors in the UK and Ireland about our community. This one page slide introduces my work and captures the  progress so far. I plan to have a physical event on campus by January 2026 when most people are around.
Ibrahim is a multi-award winning innovator whose expertise interconnects hardware, software and AI development in Africa. Ibrahim is an AI expert with over half a decade experience in the African tech space. He is all about growth and greatness with innovation in Africa.  He works as the Chief AI Scientist at Gamol Studio.

Checkoja

Checkoja is a reliable platform to check the current prices of goods in local markets across Africa. Powered by remote data routing and real-time data analytics. The goal is to create the heartbeat of the African e-commerce ecosystem that allows people to track prices at their convenience while also providing a databank for old prices and connecting millions of local markets to the internet. As a son of a farmer who has viewed this ecosystem for decades, the economic analysis of the market can be checked in terms of prices and the tech must be deployed locally. As a Yoruba boy, I call this innovation check oja which means, view market. It is debatable that price availability might not be novel enough as Jumia and other e-commerce platforms have done so for accessories especially in Nigeria. The lacuna lies in foodstuffs and local farmers who belong to the poor class of which uniquely using data analytics and AI will transform their lives. This beckons for a layer of local penetration ...

Building for Africa

That is why I focus on building AI solutions for Africa, irrespective of whether the Western version already exists. It is a fact that Western tools often don't perform well with local feature detection or deployment realities in Africa. In Africa, however, we like to talk and watch others do things for us. With my AI works, I hope it inspires more innovators to build for Africa and iterate till it fits our local contexts. Individually, this will give us confidence that we are not spectators and allow us to contribute significantly to the league of AI research. Africa should not just be a deployment zone. It can also be the building zone that prevents AI solutions from being biased in Africa. No GPT of the future can guarantee that without us. I believe that the key contribution is our work to do. 

Research 2025

Everything on my plate is machine learning research. To march means to move so I will be moving with wisdom into the realm of research for coming months. I hope to convert some of my works into publications and have fun in the process. I revisited my statement of purpose and also conceptualised some research proposals for my postgraduate work. I also learnt how to use latex and how to draft research proposals. The goal is to rekindle my dream to become a world class researcher.

Conveyor Belt Simulation Control

 In this simulation, I showed how the conveyor belt for Dangote Cement Factory can be modelled for effective control using matlab and simulink.