Hi!
I am Usman Yaqoob
Artficial Intellignece Engineer
Contact
![](assets/img/image3.png)
About Me
![](assets\css\img\usman2.png)
WHO AM I?
As a Computer Engineering graduate, my passion lies in the realms of Artificial Intelligence, Machine Learning, and Data Science. I derive immense satisfaction from meticulously cleansing datasets, ensuring their optimal utilization. My expertise extends to conducting insightful Data Analysis on real-world datasets and presenting findings through compelling visualizations. I take delight in the process of training Machine Learning and Deep Learning models, instilling programs with the intelligence to make informed decisions. Beyond development, I relish showcasing my work to the world by deploying models on web or app platforms. It's not just about coding; it's about crafting intelligent solutions that resonate with real-world challenges.
Skills
Python
Conditional Programming in Python
Data Structures in Python
OOP in Python
Machine Learning
Supervised Learning Algorithms
Unsupervised Learning Algorithms
Scikit Learn
Recommendation Systems
Web Scraping
Beautiful Soap
Selenium
Octaparse
Data Analysis and Visualization
Numpy
Pandas
Matplotlib
Seaborn
Plotly
Power BI
Deep Learning
Neural Networks
Natural Language Processing
Computer Vision
Tensorflow
Pytorch
Keras
Generative AI
OpenAI API
LangChain
Prompt Chaining
Others
Flask
Dash
Data Structures and Algorithms
C++
C
MATLAB
SQL
Problem Solving
Projects
Sakura (FYP)
Trained a model with an accuracy of 96% for four emotions detection using BERT and Deep
Neural Networks.
Collected Data about different Exercises that can Enhance a particular emotion.
Made a Recommendation System for recommendation of the Exercises to do mood enhancement.
Deployed all these models/features on a Web App via Streamlit.
ScrapeInflateForecast
Used Beautiful Soap to Scrap the Latest Inflation Rate Data from the official Web Site.
Performed detailed Time Series Analysis to know about Stationarity, Seasonality, Trend, AutoCorrelation, Partial AutoCorrelation and Distribution.
Optimized ARIMA to Mean Square error of 2.88 and also Trained SARIMA and Facebook Prophet on the Data.
Heart Attack Risk Prediction Web Application
Made a Web Application using Dash.
User can select the Machine Learning model and that specific model will be trained on the data and accuracy will be shown to user.
User can enter data of any person (features data) and selected model will do prediction on that and will return prediction to user.
Scratch NN
This Project has got Bronze Madel in Kaggle Notebooks.
Scratch coded complete Neural Network for the Prediction of a number, specifically coded Linear Function for Forward Propagation and Gradients for Backward Propagation.
Also Trained a Keras Neural in Keras to Compare the Results.
EDA of Pakistan Suicide Bombing Attacks Dataset
This Project has got Bronze Madel in Kaggle Notebooks.
In this project I did a detailed EDA on the Data set of Zeeshan Usmani which has Data about Suicide Bombing Attacks till 2017.
Found Valueable Insights from EDA.
Sentence Sentiment Analysis Using Bert
In this project I used BERT which is a Natural Language Processing model and Logistic Regression to classify a sentence/text into positive or negative sentiments.
Achieved Accuracy of 84% for Classifying the Unseen Sentences into Positive and Negative Sentiments.
Hate Speech Detection
Did data cleaning on 150,000 comments that included Toxic, Severe Toxic, Insulting, Identity hate comments.
Then I made an ML model with the High Accuracy using Logistic Regression to predict, either the comment is Toxic, severe toxic etc. or not.
Petrol/Gasoline Prices Worldwide Dataset EDA
Detailed Data Analysis and Visualization on the dataset to know about the Insights about the Oil and Gas Consumption in the whole world and also Comapred the different Countries on the Basis of the Oil and Gas Consumtion and Production.
Experience
- Artificial Intelligence Engineer
- JMM TECHNOLOGY
- 09/2023 - Present
Key Responsibilities:
- -Contributed in end to end integrated system for US Company, by applying the Regression Algorithms for Prediction of Football Scores of the Team after Cleaning the Dirty Data from the API Provided.
- -Trained and finetuned Yolov8 and Yolov5 for the American Sign Language Detection(at MVP Stage) System for Sauidi Airpot Assistance, improving accuracy and FPS Lag.
- -Trained and finetuned YoloV8 and Yolov5 for the American Sign Language Detection(at MVP Stage) system for Sauidi Airpot Assistance, improving accuracy and FPS Lag.
- -Developed an End to End project using LangChain and OpenAI API to get Answers from the Document, uploaded by the User.
- -Contributed in Project for 'Urban E Recycling Company' by doing Data Cleaning and Analysis for the Valuable Insights
- Machine Learning Engineer (Internship)
- LAB-D TECH LTD
- 07/2023 - 08/2023
Key Responsibilities:
- -Developed and Optimized Human Face Recognition System for a School by Using MTCNN and RESNET, that can Recognize Authorize Person and Send Request to Admin whenever Unauthorized Person is recognized to make him Authorized by Entering Name.
- -Optimized the Overall Recognition System by Imporving the Accuracy of Recognition and FPS Lag.