On-demand Webinar: Machine Learning on STM32 with Cartesiam: for equipment monitoring and more
In this session, we introduce condition monitoring at the edge and explain how ST’s offer combined with Cartesiam’s solution, allows you to easily, quickly and affordably run on-device learning and anomaly detection in your own solutions on compact and low power devices.
Why you should watch
Predictive maintenance (PdM) is based on condition monitoring, abnormality detection and classification algorithms and is widely implemented in industrial and consumer markets. AI has the potential to make it more accurate then ever.
Today, ST and Cartesiam give you the keys to easily build your AI-based PdM application without having to invest in resources on data science or needing to deeply understand machine learning techniques. You will learn the steps required to set up predictive maintenance in your system and quickly put theory into practice thanks to ST’s and Cartesiam’s joint solutions. Watch this on-demand webinar and discover how we can help you develop your AI application and bring it to market across a wide variety of innovative use cases.
Agenda
- Condition monitoring at the edge
- How to easily build ML algorithm (Cartesiam)
- And embed it at the edge (ST)
- Use cases and application example
- Interconnectivity between ST's AI solutions and Cartesiam's offer
- Expanding device connectivity features
Speakers
![]() | Raphael Apfeldorfer Raphael Apfeldorfer is responsible for Artificial Intelligence Marketing at ST. Focusing on innovation in digital transformations, he has 20 years’ experience in Telecom and IoT industry, from broadband to LPWAN connectivity, security and low-power applications.
|
![]() | Francois de Rochebouet François de Roucheboet computer, electronics and robotics engineer. He has been working for 20 years in the start-up industry. Cartesiam is the fourth start-up he co-founded. He currently leads the R&D team. |