Blessing Itoro Afolayan



Cinque Terre

Blessing Itoro Afolayan
bbassey@aimsammi.org

I am a versatile scientist with a strong background in Artificial Intelligence, combining technical expertise with extensive research experience. My passion lies in advancing AI technologies to create innovative solutions that positively impact society. Currently, I am exploring the vast potential of AI in the transportation sector, focusing on optimizing systems and processes. At Deustotech, the engineering faculty of the University of Deusto, Spain, I am dedicated to discovering new opportunities to leverage AI for transformative advancements.


Cinque Terre

PhD. Engineering
Oct 2023 - Till date

A Phd student at the University of Deusto as well as a research assistance with Deustotech.
Cinque Terre

Msc. Mathematical Sciences.
Sep 2018 - July 2019

My first masters was in Mathematical Sciences, at the African Institute for Mathematical Sciences(AIMS). A pan-African network of centres of excellence for post-graduate training, research and public engagement in mathematics with a mission to lead the transformation of Africa through innovative scientific training, technological advances, breakthrough discoveries, strategic foresight, and innovative policy design. Find here the school curriculum.
Cinque Terre

Bsc. Mathematics.
Sept 2012 - June 2016

A Bachelors degree in Mathematics, at the University of Ilorin, kwara state, Nigeria.

game

Cassava Disease Classification.
The project involved classifying pictures of cassava leaves into 1 of 4 disease categories (or healthy). The disease categories were: Cassava Mosaic Disease(CMD), Cassava Brown Streak Disease(CBSD), Cassava Bacterial Blight(CBB), and Cassava Green Mite(CGM). My team TAB-Next got the first position on the kaggle competition.


game

Object Tracking in Images or Videos.
This project was about detection in time series data. The idea was to track objects in a video, by comparing the detected instances in two consecutive frames within a series of frames that make the video. My approach was to use color coding to track the number of detected objects.


game

Object Detection, Segmentation and Human Pose Estimation.
This project involved reproducing the Mask RCNN paper. The technigues used were instance segmentation and object detection. The implementations was done with Detecron2 instance segmentation pretrained model as well as pose estimation whose backbone was Resnet50.


game

EDA and Topic Modelling on Tweet Data
Due to Covid 19, one of the measures put in place by the Word Health Oragnisation to curb the spread of the disease was reduce physical contact i.e maintaining social distancing. In lue of that, most employers had resolved to working remotely. This project is a study of internet-collected tweets from January through June of 2020. Utilizing the concept of “Topic Modeling” to categorize tweets by topic.


game

Statistical Methods for Predicting Prisons Population
In order to explore some statistical modelling techniques like regression, time series analysis as well as the stock flow model. The study aim to identify the need for future rehabilation places. Using the data collected fron England and Whales as a case study, the skills and techniques can be higly transferable to solving other task.


AN EDA and Inferential Statistics of Osteoprious Disease in Saudi Arabia
This is a primary data analysis of a survey that was carried out among the adult population of Saudi Arabia. The study aim to evaluate the impact of knowledge, attitude and management of Osteoprious disease among the adult population.


Predicting student final grade using Machine Learning models
Exploring 3 different machine learning models (Decision Tree, Multivariate Regression and Random Forest) to predict the final grade score of Mathematics course in Portuguese, as well as some explaratory data analysis to explore who performs best in class, male or female.


A predictive analysis using the Pareto (80/20) principle
In order to assist marketing team look into their businesses by analyzing customer dataset to determine customer trends and behavior, I adopted the Pareto (80/20) principle along side some other machine learning classification algorithms to classify customers that brings 80% of the profit to the organization. These are the customers worth targeting. Details can be found in the presentation below.


game

Neural Machine Translation
In order to help address the one of the challenges of low resourse language in NLP, I was involved in a open source project were I implemented a machine translation. Translating the English Bible to Efik and vice versa. Details can be found bellow.


game

A reinforcement learning approach for optimal placement of sensors in protected cultivation systems
With the objective of determining the optimal locations of sensors in a greenhouse, a multi-arm bandit problem was formulated using the Beta distribution and solved by the Thompson Sampling algorithm. This study aided in identifying optimal sensor locations for monitoring and controlling temperature and relative humidity in a greenhouse.




Computer Programming





game

International Conference on Learning Representations (ICLR).
ICLR is globally renowned for presenting and publishing cutting-edge research on all aspects of deep learning used in the fields of artificial intelligence, statistics and data science, as well as important application areas such as machine vision, computational biology, speech recognition, text understanding, gaming, and robotics.


game

International Conference on Learning Representations (ICLR).
The Institute for Artificial Intelligence and Fundamental Interactions (IAIFI) is enabling physics discoveries and advancing foundational AI through the development of novel AI approaches that incorporate first principles, best practices, and domain knowledge from fundamental physics.


game

Womentech Network
The virtual conference connecting women in tech, minorities and their allies in tech through an interactive platform featuring keynotes, engaging panels, a tech job fair with face-to-face networking sessions and a product expo.


game

The Machine Learning Summer School (MLSS)
Machine learning summer schools present topics which are at the core of modern Machine Learning, from fundamentals to state-of-the-art practice. The speakers are leading experts in their field who talk with enthusiasm about their subjects.


game

International Conference on Machine Learning (ICML)
The International Conference on Machine Learning (ICML) is the premier gathering of professionals dedicated to the advancement of the branch of artificial intelligence known as machine learning.