Portfolio

Machine Learning and Deep Learning

Deep Learning based drone detection - YOLOv4

Description: Developed deep learning based drone detection system that able to detect any flying drone in live. I have used You only look once (YOLOv4) object detection framework to implement this project. I have trained 6000 imgaes (4000 was manually labelled by labelimg tools) to traine this model and tested in live environment.

Flower Classifier with pretrained VGG16 and CIFAR10 by ResNET20

Description

VGGNET16: Developed a flower classifier using VGG16. Other tools I used keras and some machine learning concept such as Activation, MaxPooling2D, BatchNormalization, Flattening, EarlyStopping etc.
ResNET20: Implemented CIFAR10 classifier using ResNet20 including machine leanring tools/ technology such as TensorFlow, optimizers, BatchNormalization, AveragePooling2D, ZeroPadding2D etc.

Basic Neural Networks (Convolutional neural network) with MNIST

Description: Developed basic hand digit recognition classifier and trained on MNIST data.

Data Science

Data Analysis and visualisation in Tableau

View on Tableau public

Performed data analysis and visualization using BI tools Tableau, created multiple dashboard and organised in a Tableau story to tell the story for stackholders.

Brain Tumor Classification using Keras and Pre-tranined Efficientnet Model

Performed data visualization, data preprocessing, data augmentation, Created train, validation and test sets using image Data Generator in Keras. Trained an Efficient Net Model in Keras to perform Image Classification.

Credit Risk Prediction Web App

After my team preprocessed a dataset of 10K credit applications and built machine learning models to predict credit default risk, I built an interactive user interface with Streamlit and hosted the web app on Heroku server.

Kaggle Competition: Predict Ames House Price using Lasso, Ridge, XGBoost and LightGBM

I performed comprehensive EDA to understand important variables, handled missing values, outliers, performed feature engineering, and ensembled machine learning models to predict house prices. My best model had Mean Absolute Error (MAE) of 12293.919, ranking 95/15502, approximately top 0.6% in the Kaggle leaderboard.

Predict Breast Cancer with RF, PCA and SVM using Python

In this project I am going to perform comprehensive EDA on the breast cancer dataset, then transform the data using Principal Components Analysis (PCA) and use Support Vector Machine (SVM) model to predict whether a patient has breast cancer.

Business Analytics Conference 2018: How is NYC’s Government Using Money?

In three-month research and a two-day hackathon, I led a team of four students to discover insights from 6 million records of NYC and Boston government spending data sets and won runner-up prize for the best research poster out of 18 participating colleges.

Natural Language Processing

Word Representation and Text Classification with Neural Networks

Description: This is NLP project divided into 4 parts includes Word Embeddings with Word2Vec, Basic Text Classification, Using LSTMs for Text Classification and Text classification using BERT.

Neural Machine Translation: An NMT system which translates texts from Spanish to English using a Bidirectional LSTM encoder for the source sentence and a Unidirectional LSTM Decoder with multiplicative attention for the target sentence (GitHub).

Dependency Parsing: A Neural Transition-Based Dependency Parsing system with one-layer MLP (GitHub).