Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
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
| Date | Stars |
|---|---|
| 2026-07-24 | 3487 |
| 2026-07-25 | 3487 |
| 2026-07-28 | 3487 |
| 2026-07-30 | 3487 |
| 2026-08-06 | 3487 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
# <a title="Activity Recognition" href="https://github.com/guillaume-chevalier/LSTM-Human-Activity-Recognition" > LSTMs for Human Activity Recognition</a> Human Activity Recognition (HAR) using smartphones dataset and an LSTM RNN. Classifying the type of movement amongst six categories: - WALKING, - WALKING_UPSTAIRS, - WALKING_DOWNSTAIRS, - SITTING, - STANDING, - LAYING. Compared to a classical approach, using a Recurrent Neural Networks (RNN) with Long Short-Term Memory cells (LSTMs) require no or almost no feature engineering. Data can be fed directly into the neural network who acts like a black box, modeling the problem correctly. [Other research](https://archive.ics.uci.edu/ml/machine-learning-databases/00240/UCI%20HAR%20Dataset.names) on the activity recognition dataset can use a big amount of feature engineering, which is rather a signal processing approach combined with classical data science techniques. The approach here is rather very simple in terms of how much was the data preprocessed. Let's use Google's neat Deep Learning library, TensorFlow, demonstrating the usage of an LSTM, a type of Artificial Neural Network that can process sequential data / time series. ## Video dataset overview Follow this link to see a video of the 6 activities recorded in the experiment with one of the participants: <p align="center"> <a href="http://www.youtube.com/watch?feature=player_embedded&v=XOEN9W05_4A " target="_blank"><img src="http://img.youtube.com/vi/XOEN9W05_4A/0.jpg" alt="Video of the experiment" width="400" height="300" border="10" /></a> <a href="https://youtu.be/XOEN9W05_4A"><center>[Watch video]</center></a> </p> ## Details about the input data I will be using an LSTM on the data to learn (as a cellphone attached on the waist) to recognise the type of activity that the user is doing. The dataset's description goes like this: > The sensor signals (accelerometer and gyroscope) were pre-processed by applying noise filters and then sampled in fixed-width sliding windows of 2.56 sec and 50% overlap (128 readings/window). The sensor acceleration signal, which has gravitational and body motion components, was separated using a Butterworth low-pass filter into body acceleration and gravity. The gravitational force is assumed to have only low frequency components, therefore a filter with 0.3 Hz cutoff frequency was used. That said, I will use the almost raw data: only the gravity effect has been filtered out of the accelerometer as a preprocessing step for another 3D feature as an input to help learning. If you'd ever want to extract the gravity by yourself, you could fork my code on using a [Butterworth Low-Pass Filter (LPF) in Python](https://github.com/guillaume-chevalier/filtering-stft-and-laplace-transform) and edit it to have the right cutoff frequency of 0.3 Hz which is a good frequency for activity recognition from body sensors. ## What is an RNN? As explained in [this article](http://karpathy.github.io/2015/05/21/rnn-effectiveness/), an RNN takes many input vectors to process them and output other vectors. It can be roughly pictured like in the image below, imagining each rectangle has a vectorial depth and other special hidden quirks in the image below. **In our case, the "many to one" architecture is used**: we accept time series of [feature vectors](https://www.quora.com/What-do-samples-features-time-steps-mean-in-LSTM/answer/Guillaume-Chevalier-2) (one vector per [time step](https://www.quora.com/What-do-samples-features-time-steps-mean-in-LSTM/answer/Guillaume-Chevalier-2)) to convert them to a probability vector at the output for classification. Note that a "one to one" architecture would be a standard feedforward neural network. > [](https://www.dl-rnn-course.neuraxio.com/start?utm_source=github_lstm) > [Learn more on RNNs](https://www.dl-rnn-course.neuraxio.com/start?utm_sourc
Excerpt of 30,640 characters
Read on GitHub
Guillaume Chevalier · Canada
27
Zhaoyu
1
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:2988086613f404aa, topic:deep-learning, topic:neural-network, topic:tensorflow