ThinKIsense
Resource-efficient thin-edge systems through integrated AI and neuromorphic electronics in sensors
Start: 07/2022
End: 12/2025
The increasing number of networked devices and sensors, the “Internet of Things” (IoT), enables a wide range of new applications. However, it also results in a rapidly growing amount of data. Processing data at its point of origin (edge computing) helps to deal with this efficiently. Edge computing enhances the functionality, sustainability, reliability, and cost-effectiveness of electronic applications through the use of artificial intelligence and networking.
As part of the ThinKIsense project, a predictive maintenance application will be used to shift data processing from the cloud directly to the sensor. Specialized data preprocessing in the sensor reduces communication frequency, which increases energy efficiency and thus the service life of the batteries in the sensor. The preprocessing primarily uses neural networks. To achieve acceleration two techniques are being tested: one involves special instructions for artificial neural networks on a customized RISC-V system, and the other involves the use of spiking neural networks and a specially designed neuromorphic accelerator.
In the ThinKIsense project, FZI is researching energy-saving neuromorphic accelerators for spiking neural networks, which can be coupled with an ARM or RISC-V processor to perform predictive maintenance tasks directly in a sensor. In addition to the hardware architecture, we also design and train suitable spiking neural networks in a co-design process.
Applied Artificial Intelligence
In this research focus, the FZI concentrates on practical research into the key technology of Artificial Intelligence (AI). Innovative AI solutions are developed and transferred to application areas such as mobility, robotics, healthcare technology, logistics, production, and supply and disposal on behalf of our partners and customers.
Sustainable Engineering and Energy
This research focus includes the research and design of sustainable IT innovations in the cross-sectional areas of energy, mobility, production, water management, and logistics. This involves developing systems that promote the ecologically, socially, and economically sustainable use of resources, and providing strategic consultancy services to companies, particularly SMEs, on their path to greater sustainability.
