Lukman, what is your background?
I am a Nigerian and a doctoral researcher at LARIS Laboratory, Polytech Angers, University of Angers, France. I specialize in using machine learning techniques for the automatic recognition of functional brain networks using rs-fMRI images.
I enjoy cross-disciplinary collaborative projects and demonstrate readiness to take on challenging problems through medical imaging, graph theory, predictive modeling, and scalable algorithms.
My experience at Omdena has been highly fulfilling across multiple roles, including
- Lead Machine Learning Engineer
- Project Manager
- Community Manager at Omdena-Paris Chapter.
I’ve had the opportunity to collaborate with a fantastic team of AI experts from around the world on practical and innovative AI projects to provide lasting solutions to a range of everyday problems.
Lukman Enegi Ismaila
Which DataCamp course(s) did you participate in?
I have completed the course Biomedical Image Analysis in Python.
Specifically, it gave me confidence when tackling complex problems in medical imaging.
Fig.1. Biomedical Image Analysis in Python. Source DataCamp
How did participating in Omdena projects help you in your career? Which projects were most important to you? Why?
Working on collaborative projects at Omdena has exposed and inspired me to solve more challenging tasks successfully. It also has improved my AI project management skills to effectively manage a diverse team of machine learning engineers.
Some projects I took part in:
1. Improving Food Security and Crop Yield in Senegal
This challenge was initiated to help farmers know where to add water or fertilizer using data such as soil PH, temperature, and moisture levels, combined with other data sources. The data and predictions revealed where to invest and helped strengthen the understanding of crop losses while maximizing revenues and minimizing losses.
Crop yield prediction – Source: Omdena
In the span of two months, Omdena’s collaborators were able to implement a Deep Learning model that predicts crop yield in Senegal.
2. Detecting the Violence Between Elders and Caregivers Using Computer Vision
The AI for Children Violence project by Omdena utilized various data sources to train and test their AI models. The sources included public datasets such as the Child Vision and Abuse Dataset and the UNICEF Violence Against Children Survey Dataset. Additionally, the team collected their own dataset by manually annotating videos from YouTube and Vimeo. The team also used transfer learning techniques to leverage pre-trained models and further improve their model’s performance.
3. Credit Scoring for Making Food Affordable to the Millions of Underserved in Africa
The Credit Scoring in Africa project by Omdena utilized various AI technologies to provide credit-scoring solutions to the unbanked and underbanked populations in Africa. The team employed machine learning algorithms, natural language processing (NLP) techniques, and deep learning models to predict the creditworthiness of individuals based on non-traditional data sources such as mobile phone usage, social media activity, and utility bill payments. The project involved a team of over 70 data scientists, engineers, and experts from around the world. Our models achieved high accuracy rates in predicting the creditworthiness of individuals based on non-traditional data sources.
Build your portfolio with real-world projects from Omdena
How has Omdena changed your worldview?
Before my experience with Omdena, I had little confidence in my skills and ability with machine learning. Fast forward to now, I have gained confidence and improved my collaborative leadership skills through multiple machine learning projects at Omdena.
During my first Omdena project as a Junior Machine Learning Engineer, I was promoted mid-project based on my performance and contribution. This promotion allowed me to complete the project as a Machine Learning Engineer.
What was the most difficult part of your job? How did you overcome obstacles?
At first, I felt uneasy to jump into machine learning problems from real-world scenarios because it often requires a well-thought-out process and the chance of success can be narrow.
However, as time passed I benefited from the advice of other AI experts from the Omdena community. I was able to take on challenging problems and drive them to success across several projects such as:
- AI-based plant disease detection application
- Detection and localization of different symbols present in a P&ID
- Frame-level entity interaction detection between child-caregiver and elderly caregiver toward violence detection
How did it help your career? Did you get a job, internship, or any other accomplishment you want to share?
As a doctoral researcher in machine learning, my main goal was to familiarize myself with addressing complex problems in this domain. I was able to understand the necessary steps involved in addressing real-life problems and continue to enjoy positive feedback as a project manager and Omdena-Paris Community Lead.
Furthermore, I was recently awarded a Datasphere Research Fellowship by the Datasphere Institute. I regard this as strong evidence that I have improved my self-confidence in applying my skills for real-life problem-solving.
Would you like to add something more?
I firmly believe that the Omdena community has positively impacted my personal growth and I hope to continue on the projected trajectory towards a groundbreaking impact in AI for good.
