PopularMajor Project
Artificial Intelligence
Face Recognition Attendance System
Camera-based attendance with liveness detection and analytics
- Python
- OpenCV
- FaceNet
- Flask
- +2
₹4,900₹5,999
4.8/301 reviews
Artificial Intelligence · Major Project
Synthetic Tabular Data with GANs
Generates privacy-preserving synthetic tables and scores their quality
3-4 weeks build
Overview
Trains CTGAN on the UCI Adult census dataset to produce synthetic rows that keep the statistics of the original without copying real people. Quality is checked three ways: column and correlation similarity, a train-on-synthetic, test-on-real model comparison, and distance-to-closest-record checks that flag rows too close to a real one.
What makes it stand up
- 01CTGAN with mode-specific normalisation for mixed columns
- 02Gaussian copula baseline for comparison
- 03Train-on-synthetic, test-on-real utility evaluation
- 04Distance-to-closest-record privacy check
- 05Upload any CSV and generate a synthetic copy
Module breakdown
- 01
Data profiling
Column typing, missing values and category handling.
- 02
Generators
CTGAN and Gaussian copula models via SDV.
- 03
Fidelity
Distribution and correlation similarity reports.
- 04
Utility
Classifiers trained on synthetic data, tested on real.
- 05
Privacy
Nearest-record distances and a re-identification risk note.
After this, you will be able to
- Explain why tabular data needs a different GAN from images
- Defend the three-part fidelity, utility and privacy evaluation
- Demo generating a synthetic copy of an uploaded CSV
Technology stack
- Python
- PyTorch
- SDV
- Pandas
- scikit-learn
- Streamlit
- Level
- Major Project
- Domain
- Artificial Intelligence
- Build time
- 3-4 weeks
- Difficulty
You receive
- Complete, commented source code
- 60-90 page project report (IEEE format)
- Editable presentation deck
- Architecture, ER and UML diagrams
- Local setup and deployment guide
- Sample dataset or seed data
- Viva question bank with answers
- One 45-minute walkthrough call
- 30 days of doubt-clearing support