[Not Actively Maintained] Whitebox is an open source E2E ML monitoring platform with edge capabilities that plays nicely with kubernetes

BEST SCORE ON KAGGLE SO FAR , EVEN BETTER THAN THE KAGGLE TEAM MEMBER WHO DID BEST SO FAR. The project is about diagnosing pneumonia from XRay images of lungs of a person using self laid convolutional neural network and tranfer learning via inceptionV3. The images were of size greater than 1000 pixels per dimension and the total dataset was tagged large and had a space of 1GB+ . My work includes self laid neural network which was repeatedly tuned for one of the best hyperparameters and used variety of utility function of keras like callbacks for learning rate and checkpointing. Could have augmented the image data for even better modelling but was short of RAM on kaggle kernel. Other metrics like precision , recall and f1 score using confusion matrix were taken off special care. The other part included a brief introduction of transfer learning via InceptionV3 and was tuned entirely rather than partially after loading the inceptionv3 weights for the maximum achieved accuracy on kaggle till date. This achieved even a higher precision than before.

This clustering based anomaly detection project implements unsupervised clustering algorithms on the NSL-KDD and IDS 2017 datasets

A repository of resources for understanding the concepts of machine learning/deep learning. 

Corpus and a baseline neural network system for Named Entity Recognition in Hindi-English Code-Mixed social media text.

Boundary F1 Score - Python Implementation

Image key points Extraction, Description, Feature Matching

Extremely fast evaluation of the extrinsic clustering measures: various (mean) F1 measures and Omega Index (Fuzzy Adjusted Rand Index) for the multi-resolution clustering with overlaps/covers, standard NMI, clusters labeling

Verifying suitability of dysphonia measurements for diagnosis of Parkinson’s Disease using multiple supervised learning algorithms.

The project provides a complete end-to-end workflow for building a binary classifier in Python to recognize the risk of housing loan default. It includes methods like automated feature engineering for connecting relational databases, comparison of different classifiers on imbalanced data, and hyperparameter tuning using Bayesian optimization.

📚 Use Google BERT on fake_or_real news dataset with best f1 score: 0.986

67% accuracy on test set of CIFAR-100 by CNN in Keras without transfer learning

Detecting drug-drug interaction (DDI) has become a vital part of public health safety. This project is an implementation of NLP based approach for such relation extraction between entities.

Advancing Cybersecurity with AI: This project fortifies phishing defense using cutting-edge models, trained on a diverse dataset of 737,000 URLs. It was the final project for the AI for Cybersecurity course in my Master's at uOttawa in 2023.

Automatic method for the recognition of hand gestures for the categorization of vowels and numbers in Colombian sign language based on Neural Networks (Perceptrons), Support Vector Machine and K-Nearest Neighbor for classifier /// Método automático para el reconocimiento de gestos de mano para la categorización de vocales y números en lenguaje de señas colombiano basado en redes neuronales (perceptrones), soporte de máquina vectorial y K-vecino más cercano para clasificador

This is a simple python example to recreate classification metrics like F1 Score, Accuracy

Report various statistics stemming from a confusion matrix in a tidy fashion. 🎯

I aim in this project to analyze the sentiment of tweets provided from the Sentiment140 dataset by developing a machine learning sentiment analysis model involving the use of classifiers. The performance of these classifiers is then evaluated using accuracy and F1 scores.

With some projects to develop "TOOLs" for better Modeling

Script for calculating the optimal cut-off for max. F1-score, etc.

LSTM based model for Named Entity Recognition Task using pytorch and GloVe embeddings

Link prediction in a directed social graph.

This is the code for predicting football (soccer) results by Amir Mirbagheri

Plant disease detection on PlantVillage dataset using EfficientNetV2-B0

Contributed to a vision-driven accessibility tool translating sign language into text

This project aims to predict liver disease in Indian patients

Classifying Forest Cover type

An interactive web application that allows Formula 1 fans to create and share their predictions for the latest F1 season. Users can drag and drop drivers into grid positions for each race, track points, and share their predictions with others.

The aim is to find an optimal ML model (Decision Tree, Random Forest, Bagging or Boosting Classifiers with Hyper-parameter Tuning) to predict visa statuses for work visa applicants to US. This will help decrease the time spent processing applications (currently increasing at a rate of >9% annually) while formulating suitable profile of candidates more likely to have the visa certified.

Python framework to evaluate Named Entity Recognition (NER) models. Creates entity-level confusion matrix and classification report.