FlowAR: une plateforme uniformis\'ee pour la reconnaissance des activit\'es humaines \`a partir de capteurs binaires

TL;DR

FlowAR is a versatile platform for human activity recognition using binary sensor data, enabling flexible testing and evaluation of different methods through a modular pipeline.

Contribution

The paper introduces FlowAR, a modular and flexible platform for developing and evaluating human activity recognition systems with binary sensors.

Findings

Effective data cleaning, segmentation, and classification pipeline

Demonstrated flexibility with various datasets and methods

Validated through a concrete use case

Abstract

This demo showcases a platform for developing human activity recognition (AR) systems, focusing on daily activities using sensor data, like binary sensors. With a data-driven approach, this platform, named FlowAR, features a three-step pipeline (flow): data cleaning, segmentation, and personalized classification. Its modularity allows flexibility to test methods, datasets, and ensure rigorous evaluations. A concrete use case demonstrates its effectiveness.