I am Technology Manager turned Data Scientist, who loves building machine learning models and AI Products. Recently, I have trained the Automatic Speech Recognition (ASR) model on the Wolof language to help illiterate people interact with apps with just their voice, in a language they can already speak. I am currently testing AI Products at PEC-PITC, which later get approved for human trials, eg. Breast Cancer Classifier. My vision is to build an AI product that will help identify students that are struggling with mental illness. Do check my Data Science Portfolio.
|
|
2015-2017
Msc. Technology ManagementAward: Distinction with 3.7 out of 4Taken Courses
Extracurricular Activities
|
||||||||||
|
|
B.Sc. in Electrical (Telecommunication) EngineeringCGPA: 3.09 out of 4Publications
Taken Courses
Extracurricular Activities
|
||||||||||
|
|
2007-2009
A-LevelsGrades: A, B, C out of 3AsExtracurricular Activities
|
||||||||||
|
|
PITC has two main functional streams; Innovation and Testing. It aims to engage diverse stakeholders and provide them a platform to collaborate for the purpose of creating, developing, elaborating, and prototyping products/ solutions to the prevailing challenges for long-term social impact.
Kaggle, a subsidiary of Google LLC, is an online community of data scientists and machine learning practitioners. Kaggle allows users to find and publish data sets, explore and build models in a web-based data-science environment, work with other data scientists and machine learning engineers, and enter competitions to solve data science challenges.
Feb 2019 - July 2020, Online
Worked on multiple frealance platform such as Fiverr and Upwork.
The Center for REsearch and Development of IoT (CREDIT) was established on November 15, 2016. CREDIT aims to provide students and academic staff the opportunities to access IoT-related knowledge and know-how through various activities. It also acts as a hub to support commercialising potential solutions resulting from R&D projects.
Beyond Media is the official media team at APU/APIIT. We are passionate and enthusiastic in expressing the lifestyle of students in APIIT Education Group.
NGO, working for the youth of Pakistan.
Audio preprocessing and finetuning using wav2vec2-large-xlsr model on AI4D Baamtu Datamation - automatic speech recognition in WOLOF data.
SQLLEX is a python library for comfortable and safe working with databases.
I scored 40th rank in this DrivenData competition and my Jounery started with simple LSTM.
Automated System that collect data from web on Vaccine and created Data Analysis Dashboard.
We need to design the model that will predict likely degradation rates at each base of an RNA molecule.
This project is one of my machine learning and data-driven web apps made using Streamlit. The goal of this project is to visualize various sentiment and exploratory analysis on tweets about US airlines.
In this exploratory data analysis, I have used PEC registered Engineers data up till 2019, which is publicly available on the official website. I wanted to use Plotly and in build, function to assist me in interactive and clean visualization for easy interpretations.
Exploratory Data Analysis and Machine learning techniques were used to process the Online book market.
In this project, we will be exploring the hotel reviews and the rating base on customer hotel experience. We will be also looking at feature engineering and designing a deep learning model to predict ratings based on reviews.
The objective of this challenge is to create a machine translation system capable of converting text from French into Fongbe or Ewe.
I have created Dashboard out of simple engineer data set, you can read more here.
The goal of this challenge is to estimate the wind speeds of storms at different points in time using satellite images captured throughout a storm’s life cycle and the temporal memory of the storm.
Build data pipelines, the easy way. Orchest is a tool for building data pipelines that don’t require DAGs and frameworks. The environment is simple to navigate, and you can code Python, R, and Julia.
Discover your reading patterns and recommendations for a new book to read.
build an application programming interface (API) for your machine learning model and then deploy it with simple code.
OmdenaLore is world’s biggest AI4Good library for real-world projects.
Using FastAI.jl library to classify images from the Imagnet dataset.
We will use data analysis tools to figure out trends in digital learning and how it is effective towards improvised communities.
Designing machine learning pipeline with few lines of codes using Orchest. You will learn to preprocess the data, train the machine learning model, and evaluate the results.
Discord bot using DailoGPT pretrained model on Rick& Morty Dataset from Kaggle.
Learn how much Singapore is saving energy per years by recycling plastics, paper, glass, ferrous and non-ferrous metal.
To get certified this candidate had to display that they have the knowledge, skills, and abilities to perform a Data Scientist role. These included but were not limited to Data Management, Exploratory Analysis, Statistical Experimentation, Model Development, Coding for Production Environments, Communication, and Reporting.
This course Helped my understand basics of R languages and taught me some of the basic of Data Analysis, with hand on working with real-life examples.
Learning Basics of SQL and using SQL query to analyze the data. This course has helped me learn more about the database and how to produce effective analysis.
This course was my way to career change, I have learned the basics of Programming, Data analysis, and Data Science which also include Machine Learning.
Learn Geospatial Analysis, Data Analysis, and Data Visualization on public Tableau. I have worked on Multiple real-life projects during my course.
I have learned the Basics of Natural language processing and how to get useful information from text, tokenization, machine learning and eventually using Spacy and NLTK to processes the text data.
I have learned Natural language processing using Deep learning libraries especially Tensor-flow and how to get useful information from text, tokenization, machine learning and eventually using Spacy and NLTK to processes the text data.
Get hold of PostgreSQL and how to optimize database using index, learning new techniques to create database and maintaining the efficiency.
This course has helped me understand how feature engineering improves the overall score of machine learning models and how to process the features.
I have published more than ten notebooks on the Deepnote platform and got MVP for publishing the highest number of notebooks on data analysis, Data Science, and Machine learning.
Top ten spots by weightage ensembling automl, cat boost, lightgbm, and Xgbm. I have also used feature engineering and hyperparameters optimization to get better results.
Became Lifetime Member of PEC.
