OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
AI Models

Lstm Human Activity Recognition

Lstm Human Activity Recognition is an open-source TensorFlow and Jupyter Notebook example that uses an LSTM recurrent neural network to classify smartphone accelerometer and gyroscope data into six activities.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Lstm Human Activity Recognition — OpenViST project profile in AI Models.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use it when you want a concrete notebook example of classifying smartphone sensor time series into everyday movement categories.

Who it is for

  • Learners exploring recurrent neural networks and time-series classification.
  • Developers studying smartphone-sensor activity recognition.
  • Researchers or prototypers seeking a starting example for activity classification.

Documented uses

  • Examine how sequential sensor measurements can be mapped to an activity label.
  • Explore a six-class LSTM activity-recognition example using the UCI HAR dataset.
  • Use the documented notebook workflow to prepare the example dataset.
Before you choose

Requirements & limits

The public GitHub repository identifies the project as MIT-licensed.

  • The example distinguishes six activities: walking, walking upstairs, walking downstairs, sitting, standing and laying.
  • Its README describes 2.56-second sensor windows with 50% overlap and 128 readings per window.
  • The notebook imports TensorFlow, NumPy, Matplotlib and scikit-learn metrics; its code comments reference TensorFlow 1.0.0 and earlier-version use in past commits.
  • The described input uses nine normalized features covering body acceleration, body gyroscope and total acceleration across three axes.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Prepare the UCI HAR dataset for the notebook

Download and extract the dataset used by the activity-recognition example.

Before you start

  • The project repository, including its data directory and download_dataset.py script.
  • A notebook environment capable of running the documented shell and Python steps.

Steps

  1. Change into the repository's data directory.

  2. Run the documented command: python download_dataset.py.

  3. Return to the repository root and use the dataset path data/UCI HAR Dataset/.

Expected outcome

The dataset is downloaded and extracted at the location used by the notebook.

Guide limitations

  • This guide covers dataset preparation only, not running or training the model.
  • The README's recorded download output is an example from its own environment, not a guarantee of current access or successful execution.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
15 October 2026
Original website title
guillaume-chevalier/LSTM-Human-Activity-Recognition · Official homepage title · retained in its source language
How we review sourcesSuggest a correction