Communication Systems

Anyone exploring technological advances in artificial intelligence (AI) will inevitably encounter spiking neural networks (SNNs) — the next step toward energy‑efficient real‑time AI. The difference from conventional neural networks is striking: while standard artificial neurons continuously output values, SNN neurons fire only when critical thresholds are exceeded, sending electrical impulses (spikes) through the network. This event‑driven mode of operation saves both energy and computation time, making it a compelling option for certain use cases. Yet few companies are willing to discard their painstakingly trained deep neural networks (DNNs) and start from scratch. The pressing question, therefore, is: How can the proven knowledge embedded in DNNs be transferred into SNNs? This is precisely where current research comes in.

Read more

Wireless technologies can make production halls more efficient and more dynamic, but this involves a huge challenge: All data must arrive in the right place at the right time. Could Time-Sensitive Networking provide a breakthrough in this area?

Read more

A problem with many AI networks is that they’re good — really good — but sometimes a little big and overly precise. That means a lot of energy, memory, and computing time are spent on complex calculations, even though simpler models could solve the task at hand more efficiently. But how do you turn an overly complicated neural network into a compact artificial intelligence (AI) that also runs reliably on small devices, for example, in a headset for sleep monitoring? This is where neural architecture search comes into play.

Read more

The energy consumption of 5G and 6G networks could increase dramatically in the future. Therefore, a team at Fraunhofer IIS is researching how to give mobile communication networks their own sleep rhythm. It’s called “network energy savings”. But what exactly does that mean.

Read more

Satellites are the shooting stars in the 5G universe. This is because with their extensive geographic coverage, they have the potential to bring 5G – and one day 6G – to every corner of the planet and thus pave the way for global connectivity. At Fraunhofer IIS, we’re working on enhanced satellite coverage, cellular base stations on satellites, and handover procedures that in the future will enable our smartphones to communicate seamlessly via satellite.

Read more

Dr. Elke Roth-Mandutz leverages her creativity and experience in standardization to improve the security and energy efficiency of this mobile communications standard.

Read More

For 15 years, Rainer Wansch and his team have been researching the idea of an on-board processor that can be controlled from Earth when it’s aboard a satellite orbiting the globe. Now the Fraunhofer On-Board Processor has arrived in space. A story of patience and perseverance.

Zum Beitrag

About 19 years ago, Fraunhofer IIS and the Chair of Information Technology (LIKE) at the Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU) founded a digital campus radio station. It was a research project aimed at testing technical innovations and digital broadcasting systems and working with FAU students on developing innovative, content-related concepts. The campus radio station has long since outgrown its status as a research project, and in 2022, the broadcasting studio moved from Erlangen’s E-Werk cultural center to the “Blue House” on the Europa Canal in Erlangen. On the occasion of this move, we take a look back at 19 years of fruitful collaboration.

Read the interview

Located in the town of Ilmenau in the German state of Thuringia, the InSignA High-Performance Center aims to harness synergy effects at a local level and to assist small and medium-sized enterprises (SMEs) with digitalization and other projects. Jörg Robert, Deputy Head of the Electronic Measurements and Signal Processing (EMS) department and professor at TU Ilmenau, explains: “Part of our mission as a research organization is to successfully transfer the Fraunhofer-Gesellschaft’s research and technologies and apply them to serve industry and society. High-Performance Centers are incubators of innovation with a regional focus.”

Read More

Dr. Marco Breiling (51) wants to assist in shaping the future of Germany. The electrical engineer from Erlangen helps get successful high-tech products made in Germany. Inspired by the energy efficiency of a bee’s brain, his team develops clever microchips that process very large data volumes in an energy-saving manner. This achievement impressed the jury of the pilot innovation competition “Energy-Efficient AI System” organized by the German Federal Ministry of Education and Research (BMBF). Here, Marco Breiling gives fascinating insights into his field of research.

Read the article

The SEC-Learn (Sensor Edge Cloud for Federated Learning) project, involving eleven Fraunhofer Institutes, promises a major technological leap in the field of neuromorphic hardware: for the first time, a chip is being developed to accelerate spiking neural networks (SNN) in conjunction with what is known as federated learning. This would offer practical benefits for companies and individuals.

Read the article

Bottlenecks are not exactly popular – after all, they bring entire processes to a standstill. Artificial intelligence has a bottleneck of its own to contend with. To be precise, it is impossible to speed up artificial intelligence indefinitely on classical computers. The hardware needs time to “think”.  Read here how we solve this problem.

Read the article

Computer architecture inspired by the human brain – to most people, this sounds rather abstract and removed from everyday life. Far from it: a research team from Fraunhofer IIS and Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU) has developed neuromorphic hardware capable of detecting early signs of atrial fibrillation and considerably reducing the risk of stroke. In other words, this application has an entirely practical place in everyday life.

Read the article

Bringing intelligence to devices is an essential prerequisite for autonomous driving. After all, real-life traffic situations demand fast responses and leave no time to transmit sensor data to a cloud for intelligent analysis. In the KI-FLEX project, researchers are developing neuromorphic hardware that allows artificial intelligence (AI) to be integrated directly into a car – in the form of a flexible platform. Project coordinator Michael Rothe from the Fraunhofer Institute for Integrated Circuits IIS offers his insights into the project.

To the article

Analog or digital – two terms that will be quite familiar to most people. But when it comes to artificial intelligence, only the experts know that there’s something “in between.” They call this “in between” the spiking neural network (SNN). One of the main hopes for the SNN approach is that it will resolve how to integrate “intelligence” directly into devices. Cognitive scientist Johannes Leugering explains what’s involved.

To the article

The purpose of Edge AI is to relocate artificial intelligence to where it is needed: end devices. For this to work, however, processing operations cannot be too energy-intensive. In the ECSEL projects ANDANTE and TEMPO, researchers at Fraunhofer IIS are paving the way for this emerging technology with the development of suitable chips, algorithms, and tools.

To the article

Some challenges are best faced shoulder to shoulder – like developing the chips, algorithms, and the hardware needed to integrate artificial intelligence directly into end devices, a paradigm also known as “Edge AI”. Marco Breiling, chief scientist at the Fraunhofer IIS Communication Systems division and Dr. Loreto Mateu, group manager at the Fraunhofer IIS Smart Sensing and Electronics division, talk about why their collaboration on Edge AI is so fruitful, and the benefits of working in an international team.

To the article

Satellites can be used to transmit data all around the globe. They gather data for the Internet of Things (IoT) and relay them to well-connected ground stations, from where the data ultimately make their way to the user. To make things even easier, we are developing efficient transmission methods for IoT transmitters that send signals directly to the satellite from any location on Earth.

To the article