# guillaume-chevalier/LSTM-Human-Activity-Recognition

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

Repository: https://github.com/guillaume-chevalier/LSTM-Human-Activity-Recognition
Canonical: https://ross.abutalabs.com/products/lstm-human-activity-recognition
Language: Jupyter Notebook
License: MIT
License Family: permissive
Topics: machine-learning, deep-learning, lstm, human-activity-recognition, neural-network, rnn, recurrent-neural-networks, tensorflow, activity-recognition
Last push: 2022-11-06T17:53:06+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 3760, "days_push": 1396, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 3482, forks 935 (observed 2026-08-28T04:08:06.919732+00:00)

## What it is
A Jupyter Notebook tutorial demonstrating Human Activity Recognition using an LSTM recurrent neural network in TensorFlow on the UCI smartphone sensor dataset. It classifies six movement activities (walking, stairs, sitting, standing, laying) from accelerometer and gyroscope time-series data.

## Use cases
- learn how to build an LSTM in TensorFlow for time-series classification
- classify smartphone sensor data into human activities
- example of RNN applied to wearable sensor signals
- tutorial on human activity recognition with deep learning
- starter code for sequence classification with LSTMs

## When to choose
- you want a worked, educational example of LSTM-based sequence classification
- you are working with the UCI HAR smartphone sensor dataset
- you want to learn TensorFlow RNN APIs through a hands-on notebook

## When to avoid
- you need a production-ready activity recognition system
- you need support for modern TensorFlow 2.x or PyTorch out of the box
- you need a maintained library with an API rather than a tutorial notebook

## Facets
- artifact type: learning-resource
- maturity: maintenance
- function: machine-learning, deep-learning
- domain: machine-learning, deep-learning
- platform: python
- tags: lstm, rnn, tensorflow, human-activity-recognition, tutorial, jupyter-notebook, time-series, sensors

## Member repositories
- guillaume-chevalier/LSTM-Human-Activity-Recognition (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:08:06.919732+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T18:36:26.490053+00:00, confidence not recorded.
  - readme: https://github.com/guillaume-chevalier/LSTM-Human-Activity-Recognition (fetched 2026-08-28T04:08:06.919732+00:00, sha 8c5b8f6a773c)
- Data as of 2026-08-30T08:39:29.467469+00:00.