wisdal / deep-learning-for-sensor-based-human-activity-recognition

Application of Deep Learning to Human Activity Recognition using accelerometer and gyroscope sensors data

Deep Learning for sensor-based Human Activity Recognition.

With advances in Machine Intelligence in recent years, our smartwatches and smartphones can now use apps empowered with Artificial Intelligence to predict human activity, based on raw accelerometer and gyroscope sensor signals. This problem is commonly referred to as Sensor-based Human Activity Recognition (HAR).

This repository contains the source code of my solution to the HAR problem. A detailed analysis of the approach can be found on my blog post (address below).

Original Blog Post: here

Contact: [email protected]

UPDATE: currently revamping my source code to adapt it to the latest TensorFlow releases; things have changed a lot since version 1.1. I will update this repository when the new code is ready.

deep-learning-for-sensor-based-human-activity-recognition's Issues

Model Information

Wisdom,

Can you share the model you used for training and testing? I don't need the code but it would be useful to know the layers and the number of parameters used.

Thanks