AI News, guillaume-chevalier/LSTM-Human-Activity-Recognition

guillaume-chevalier/LSTM-Human-Activity-Recognition

Other research on the activity recognition dataset used mostly use a big amount of feature engineering, which is rather a signal processing approach combined with classical data science techniques.

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.

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.

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 (one vector per time step) to convert them to a probability vector at the output for classification.

And it can peak to values such as 92.73%, at some moments of luck during the training, depending on how the neural network's weights got initialized at the start of the training, randomly.

In another open-source repository of mine, the accuracy is pushed up to 94% using a special deep LSTM architecture which combines the concepts of bidirectional RNNs, residual connections and stacked cells.

If you want to learn more about deep learning, I have also built a list of the learning ressources for deep learning which have revealed to be the most useful to me here.

Action Detection Using A Deep Recurrent Neural Network

An example of MERL's deep recurrent neural network for action detection working on a test video from the MERL Shopping Dataset. The yellow box in the upper ...

Temporal Activity Detection in Untrimmed Videos with Recurrent Neural Networks (NIPS WS 2016)

This thesis explore different approaches using Convolutional and Recurrent Neural Networks to classify and ..

3D CNN-Action Recognition Part-1

This video explains the implementation of 3D CNN for action recognition. It explains little theory about 2D and 3D Convolution. The implementation of the 3D ...

On Characterizing the Capacity of Neural Networks using Algebraic Topology

The learnability of different neural architectures can be characterized directly by computable measures of data complexity. In this talk, we reframe the problem of ...

Keras Explained

Whats the best way to get started with deep learning? Keras! It's a high level deep learning library that makes it really easy to write deep neural network models ...

How to visualize neural network parameters and activity - Justin Shenk

Description Visualizing neural network parameters and activity using open source software such as Yosinski's Deep Convolutional Toolbox, Karpathy's RNNs, ...

Using artificial neural networks to generate realistic neural activity - AI Grant

Mark Wronkiewicz, Majid Mirbagheri, Nicholas Foti 2-min pitch for AI Grant ( Project title: Using artificial neural networks to generate realistic ..

Quiver: A Tool for Seeing Inside a Neural Network

Quiver: An Interactive Visualization Tool for Convolutional Neural Networks ━━━━━━━━━━━━━━━━━━━━━━━━━ ☆ Rajistics Social Media ...

Neural Networks - Object Detection

Convolutional Neural Networks About this course: This course will teach you how to build convolutional neural networks and apply it to image data. Thanks to ...

Activity recognition using LSTM in tensorflow

detection of human movement(run or work). The model classified correctly with a validation accuracy of greater 99% using LSTM in Tensorflow.