FlowAR

Description

A modular, data-driven operational experimental framework designed to support reproducibility and scientific rigor in the development and evaluation of activity recognition systems. Realized as part of PhD research.

How To Run

1. Create and activate a virtual environment.

python3 -m venv .venv
source .venv/bin/activate

2. Install required packages.

pip install -r requirements.txt

3. Run the Streamlit app.

streamlit run gui/main.py

Cite Papers

Please cite the following papers if you use or refer to FlowAR (code, data) in your research:

FlowAR: A Framework for Data-Driven Development of Human Activity Recognition Systems using Binary Sensors

Ali Ncibi, Luc Bouganim, Philippe Pucheral
21st International Conference on Distributed Computing in Smart Systems and the Internet of Things (DCOSS-IoT), 2025.

• https://hal.science/hal-05213603v1

FlowAR: une plateforme uniformisee pour la reconnaissance des activites humaines a partir de capteurs binaires

Ali Ncibi, Luc Bouganim, Philippe Pucheral
25eme conference francophone Extraction et Gestion des Connaissances (EGC), 2025.
Paper links:

• https://hal.science/hal-04944889v1