PopularMajor Project
Machine Learning
AI Resume Screening System
NLP pipeline that ranks candidates against a job description
- Python
- spaCy
- scikit-learn
- FastAPI
- +2
₹4,499₹7,999
4.9/214 reviews
Machine Learning · Major Project
Human Activity Recognition from Smartphone Sensors
Recognises walking, sitting, stairs and more from phone motion data
3-4 weeks build
Overview
Trained on the UCI Human Activity Recognition dataset, this kit classifies six everyday activities from accelerometer and gyroscope signals. Engineered-feature models are compared with a CNN-LSTM on raw windows, evaluated on held-out subjects, and a small Kotlin Android app streams live phone sensor data to a Flask endpoint for real-time predictions.
What makes it stand up
- 01Engineered-feature SVM compared with a CNN-LSTM on raw signals
- 02Subject-wise splits so the test set contains unseen people
- 03Confusion matrix showing which activities get mixed up
- 04Kotlin Android app streaming live accelerometer and gyroscope data
- 05Real-time prediction view for the viva demo
Module breakdown
- 01
Dataset
Loads UCI HAR windows, features and subject IDs.
- 02
Classic models
SVM and random forest on the 561 features.
- 03
Deep model
CNN-LSTM trained on raw inertial windows.
- 04
Inference API
Flask endpoint that windows and classifies live data.
- 05
Android app
Kotlin app capturing and sending sensor readings.
After this, you will be able to
- Explain how sliding windows turn signals into samples
- Defend subject-wise evaluation over random splits
- Demo live activity detection with a phone in your pocket
Technology stack
- Python
- TensorFlow
- scikit-learn
- Pandas
- Flask
- Kotlin
- Level
- Major Project
- Domain
- Machine Learning
- 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