MobiSpaces delivers an end-to-end mobility-aware and mobility optimised data governance platform covering data acquisition, in-situ processing and all security- and privacy-related operations.
MobiSpaces has envisioned a set of toolboxes, suites, and tools to bring this concept to life. The project has defined an AI-based Data Operations Toolbox, which includes tools such as a Declarative querying tool, a Decentralized Data Management tool and an Online Data Aggregator. Additionally the Edge Analytics Suite, comprises tools for XAI Prediction Modelling, Edge-driven Federated Learning, and Visual Analytics.
The MobiSpaces platform is surrounded by a Green & Environmental Dimensioning Workbench for monitoring and advising processing behaviors, ensuring its infrastructure is in line with zero-carbon footprint legislation and the “do no significant harm” principle. Read on to learn more about the set of toolboxes, suites, and tools MobiSpaces has delivered.
AI-based Data Operations Toolbox
MobiSpaces empowers data management systems and enhances their capabilities by integrating AI-based data operations in a toolbox that can be applied in mobility settings. This toolbox includes a set of tools which are integrated into the AI-based data operations toolbox, while also being able to perform autonomously.
Declarative Querying
MobiSpaces follows an approach that defines abstract data operations with clear semantics, which are fundamental for expressing more complex queries.
Decentralized Data Management
MobiSpaces adopts a massively distributed and adaptive infrastructure that makes use of large numbers of edge computing nodes to collect, cache, manage, aggregate, analyze, model and present huge amounts of data from a large number of objects and heterogeneous sources
Online Data Aggregator
MobiSpaces has developed a tool that computes and aggregates statistics from multiple, distributed data streams in an online and incremental way. To reduce the memory footprint, appropriate data sketches have been applied on the streaming data, while approximate query processing techniques have been used to compute results with high accuracy.
Edge Analytics Suite
MobiSpaces delivers a suite of decentralized, edge analytics algorithms, based on techniques for Machine Learning over mobility data that go beyond the state-of-the-art.
XAI Prediction Modelling
MobiSpaces goes one step further in building robust and accurate mobility models from data by focusing on model interpretability which is focal in operational environments. A tool equipped with XAI techniques focusing on the explainability of deep neural networks has been delivered.
Edge-driven Federated Learning
MobiSpaces will design and implement a Federated Learning architecture to address the challenges associated with mobility datasets that are massively distributed. Under this setting, data is stored locally at the edge, while a primary model is stored in a centralised location.
Visual Analytics
This tool aims to develop interactive and scalable methodologies, which can efficiently handle both historical and streaming spatiotemporal data originating from different sources, with varying levels of resolution and quality.