It's this time of the year when most people have come back from their holiday breaks, they are recharged and full of creativity! Here at MARVEL, we have one more reason to feel energized and inspired: We recently had our M23 plenary meeting and our live demo presentation! Thanks to the hard work of the whole consortium and the good collaboration among the partners, the feedback was both rewarding for all the progress achieved so far, and constructive for what is further expected.

With this Newsletter, we would like to proudly share what happened in the last 4 months as well as what is coming up! Enjoy and don't forget to follow us online (if you are not doing it already), for more immediate updates!

The 2nd Info Day for the MARVEL project was hosted by Greenroads in Valletta, Malta on November 28, 2022. Public authorities, Traffic Managers, Law Enforcement Agencies, data scientists, engineers, architects, technical project managers, and other people who are interested in smart city technologies, products, and services were invited and attended the event.

Visit our zenodo community and get access to a great number of scientific papers, presentations and well as deliverable reports. The outcomes of our latest research include:

• Engineering Resource-Efficient Data Management for Smart Cities with Apache Kafka,
• Non-linear Gradient Mappings and Stochastic Optimization: a General Framework with Applications to Heavy-Tail Noise,
• Large deviations rates for stochastic gradient descent with strongly convex functions,
• One-Shot Federated Learning for Model Clustering and Learning in Heterogeneous Environments
  
• Low-Complexity Acoustic Scene Classification in DCASE 2022 Challenge
• ConfMix: Unsupervised Domain Adaptation for Object Detection via Confidence-based Mixing
• Cluster-level pseudo-labelling for source-free cross-domain facial expression recognition
• FaaS execution models for edge applications
• In-Network Computing With Function as a Service at the Edge
• Stateful Function as a Service at the Edge

At the end of February, our consortium prepared deliverable D5.2: Technical evaluation and progress against benchmarks – initial version. You can access it by visiting our zenodo community here. Click on the button below and view all our deliverables!

Find out more about the technologies used in MARVEL