Implementing the PER  system and creating a Multi-Agent Reinforcement Learning (MARL) model requires a preliminary phase that simulates the possible movements of people in an emergency situation to properly train the model.. A true-to-life simulator offers a safe and controlled platform for testing learning strategies in different situations.

On 2 February 2024, fifty retired policemen and women were called on to participate in a simulation activity that feeds into the project’s Personalised Evacuation Route use case. These volunteers met on San Servola island to help visually represent the change in crowd speed stemming from different obstacles put in their path.

By:SIXSQ Efficiently managing data is one of the main challenges faced by complex computing systems, including AI. The rapid increase of Internet of Things (IoT) sensors and the vast amounts of raw data they generate have made it essential to effectively store and...

Elli Kartsakli and Alba Cañete from the BSC presented at the Barcelona Beat Agora, hosted by the Barcelona City Council on 26 February. Their presentation focused on smart city applications of the key enabling technologies that facilitate extreme data mining. It also included an introduction into the Venice Personalised Evacuation Route crisis management use case.

The third EXTRACT face-to-face meeting took place in Paris and Nançay France from 13-15 February 2024. Partner Observatoire de Paris hosted this three day event that provided key insights into the requirements of the Transient Astrophysics with a Square Kilometer...

On February 11, we celebrate the Women in Science who help make research and development possible. Get to know the responsabilities of the women driving the EXTRACT project.

Figure 1: Xavier Palomo, from partner BSC, shares EXTRACT use cases to demonstrate potential crisis management applications of an efficient compute continuum The half day workshop, "CompContinuum: Computing Continuum of Cloud, Edge, and IoT Technologies” held on the...

A machine-learning (ML) model recommends where each individual should go in case of a disaster, taking into account the person’s characteristics and capabilities (age, disability, etc) and the limited capacity and labyrinthian streets and alleys of ancient Venice. To allow people’s devices to access this model, it needs to be served, i.e., be available as a remote service.

On 13 December 2023, BSC partner Universitat Rovira i Virgili (URV) presented its paper, “Glider: Serverless Ephemeral Stateful Near-Data Computation” at the 25th ACM/IFIP International Middleware Conference (11-15 December 2023). This conference is a major forum for...

EXTRACT partner, LOGOS RI, participated in the networking event “Connect & Create,”. Dr. Emanuele Bellini (LOGOS RI) took this opportunity to give a short presentation introducing LOGOS’ project portfolio and the EXTRACT project.