Human-Activity-Recognition
A machine learning project comparing topological and statistical feature extraction for classifying human activities from smartphone and smartwatch sensor data.
What is Human-Activity-Recognition?
Human Activity Recognition is a machine learning research project that classifies human activities using accelerometer and gyroscope data from smartphones and smartwatches. It compares topological data analysis against statistical feature extraction methods to preprocess sensor data, then evaluates multiple classifiers including Decision Trees, Random Forest, SVM, and CNN. The project aims to determine which preprocessing approach yields better activity recognition accuracy.
Machine learning researchers and data scientists working on human activity recognition, time-series classification, or sensor data analysis. Particularly relevant for those exploring topological data analysis applications or comparing preprocessing techniques for HAR systems.
Provides a comprehensive comparison of topological versus statistical preprocessing methods for HAR using real-world sensor data. The project offers reproducible experiments with multiple classifiers and sensor types, helping researchers understand which approaches work best for different activity recognition scenarios.
Overview
This project aims to classify human activities using data obtained from accelerometer and gyroscope sensors from phone and watch.
Use Cases
Best For
Related Projects
Found a gem we're missing?
Open-Awesome is built by the community, for the community. Submit a project, suggest an awesome list, or help improve the catalog on GitHub.
