LSTM for Human Activity Recognition
Human Activity Recognition using TensorFlow and LSTM RNNs on smartphone sensor data to classify six movement types.
What is LSTM for Human Activity Recognition?
LSTM-Human-Activity-Recognition is an open-source project that implements a Long Short-Term Memory (LSTM) Recurrent Neural Network (RNN) for classifying human activities based on smartphone sensor data. It uses accelerometer and gyroscope readings to recognize six types of movements—such as walking, sitting, and standing—demonstrating how deep learning can automate feature extraction for time-series classification.
Machine learning practitioners, data scientists, and students interested in applying deep learning to time-series data, particularly those working on sensor-based activity recognition or sequence modeling with TensorFlow.
It provides a complete, well-documented implementation that achieves high accuracy with minimal feature engineering, serving as an educational example and practical baseline for HAR tasks using LSTMs.
Overview
Human Activity Recognition example using TensorFlow on smartphone sensors dataset and an LSTM RNN. Classifying the type of movement amongst six activity categories - Guillaume Chevalier
Use Cases
Best For
- Learning how to implement LSTM networks for sequence classification
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.
