Data Science Repositories

Explore my data science projects, including notebooks and GitHub repositories.

NeuroMetrics

An AI-driven platform to predict the UPDRS 3 score for Parkinson's disease.

View on GitHub

Film Feedback AI

A sentiment analysis project to classify movie reviews.

View on GitHub

PneumoNet

A deep learning project for pneumonia detection from chest X-rays.

View on GitHub

Cloud Architecture

Explore various projects demonstrating cloud architecture capabilities.

Serverless API Deployment

NeuroMetrics is an AI-driven platform designed to predict the UPDRS 3 score (Motor ability deterioration), a crucial metric in the Unified Parkinson's Disease Rating Scale.

Demo Beta

Multi-Service Application

Use Docker microservices orchestrated with Kubernetes.

Machine Learning Pipeline

Host a model via FastAPI or Flask, exposing it through a REST API.

Dashboard Portfolio

Explore my interactive dashboards created with various tools.

Human Resources Monitoring Dashboard

A comprehensive dashboard to analyze human resources data, providing both summary views for high-level insights and detailed employee records for in-depth analysis

View Demo Beta

Sales Performance Dashboard

Visualize sales data with interactive charts and filters.

Website Analytics Dashboard

Track website traffic and user behavior metrics.

Social Media Analytics Dashboard

Monitor social media engagement and follower growth.

Financial Portfolio Tracker

Visualize investment performance and asset allocation.

Customer Churn Analysis

Analyze customer churn rate and identify contributing factors.

Marketing Campaign Performance

Track the effectiveness of marketing campaigns.

Project Management Dashboard

Visualize project progress and resource allocation.

Sales Forecasting Dashboard

Forecast future sales using historical data and predictive modeling.

Edge Computing

Leveraging the power of edge computing for real-time processing and reduced latency.

Edge computing brings computation and data storage closer to the source of data generation, enabling faster processing, reduced latency, and improved bandwidth efficiency. This is particularly beneficial for applications requiring real-time responses, such as IoT devices, autonomous vehicles, and industrial automation. When combined with cloud computing, edge computing creates a hybrid architecture that leverages the strengths of both environments. Edge devices handle immediate processing needs, while the cloud provides scalable storage and processing for larger datasets and complex tasks.

Image Analysis via WebAssembly

Use a lightweight model (MobileNet) for computer vision, executed locally in the browser.

Demo Beta

Data Processing via Web Workers

Analyze CSV files directly in the browser for efficient multitasking.

Demo Beta

Real-time Video Analytics

Process video streams from security cameras at the edge to detect events and trigger alerts immediately, reducing reliance on cloud bandwidth.

Industrial IoT Monitoring

Monitor sensor data from industrial equipment at the edge to detect anomalies and prevent equipment failures, enabling proactive maintenance.