HARE

Human Activity Recognition Engineering

As the framework is composed of different building blocks, it contains different folders for each task. The code is structured as follows:

• ml-pipeline

Code to reproduce the experiments for a single modality (IMU data)

• multimodal

Code to reproduce the experiments from the two data sources IMU & Pose Estimations

• tflite-export

Code to reproduce the on-device experiments

• xsens_android

Android code for real-time human activity recognition using the Xsens DOT sensors