Low Cost Artificial Ventilator Embedding Unsupervised Learning for Hardware Failure Detection [Society News]

In this paper, a less than $200 artificial ventilator that can be used against COVID-19 pandemic is presented. Using low-cost easyto-find materials, it has been designed for helping developing countries where supplies building new medical equipments are limited. It complies with requirements, allowing to monitor and adjust ventilation parameters such as tidal volume, maximum intra-lung pressure breath rate. Even if low cost, focus placed on improving its global reliability. recycled materials may lead mechanical failures, potential drawback addressed an intelligent embedded hardware failure detector implemented inside the microcontroller. K-means optimized algorithm, learns in short time normal operation corresponding couple formed by given set-up patient. case of breakdown, alert generated inform staff. First, mechanical, electrical software architectures system presented, then detection algorithm detailed. Finally, test results done at IRBA using lung discussed. The overall project published open source one GitHub: https://github.com/iutgeiitoulon/ArtificialVentilator.