Asset Type
Library
Performance Models
Performance Models support the AI-SPRINT design and runtime components in selecting an appropriate configuration
Header
AI-SPRINT
Artificial Intelligence in Secure PRIvacy-preserving computing coNTinuum
AI-SPRINT defines a novel framework for the design and operation of AI applications in computing continua.
AI-SPRINT goes beyond supporting AI applications development by enabling the seamless design and partition of AI applications among the plethora of cloud-based solutions and AI-based sensor devices, providing security and privacy guarantees.
Funding Call
Business Categories
Duration
-
AI-SPRINT is poised to develop a novel framework for developing and operating AI applications, together with their data, exploiting computing continuum environments. Key outputs include novel tools for AI applications development, secure execution, easy deployment, as well as runtime management and optimisation, which will help to overcome current technological challenges in exploiting resources in the edge-to-cloud continuum in terms of flexibility, scalability of analytics, interoperability, energy efficiency, security and privacy.
AI-SPRINT addresses the technological challenges of designing and efficiently executing AI applications, leveraging resources from the edge to the cloud. Our AI-SPRINT applications are primarily written in Python and heavily utilize AI technologies. These applications consist of multiple components that run across a computing continuum, with some on the cloud, some on edge servers, and some on AI-enabled sensors.
Discover the AI-SPRINT Components
AI-SPRINT has been duly tested and validated in three real-world scenarios:
- Personalised Healthcare - Developing an automated system for personalised stroke risk assessment and prevention.
- Maintenance & Inspection - Creating an infrastructure that reduces downtime and revenue losses caused by degenerative asset performance.
- Farming 4.0 - Delivering edge and intelligent sensors to optimise phytosanitary treatments.
Assets related to AI-SPRINT
Asset Type
Executable
SPACE4AI-D
A Design-time Tool for AI applications Resource Selection in Computing Continua
Asset Type
Executable
Federated Learning
The application contained in this folder creates an AI model using Federeated Learning. Unlike other applications, which have a centralized training dataset, this version pursues training the model using multiple datasets hosted in different institutions ...
Asset Type
Docker container
PyCOMPSs and dislib
Transparent parallelisation of user code and seamless execution of the same code on different backends from the edge to the cloud and HPC clusters.
Asset Type
Library
POPNAS (Models Architecture Search)
Pareto Optimal Progressive Neural Network Architecture Search tool
Asset Type
Library
Privacy Preserving Component
The Privacy Preserving Component offered by AI-SPRINT facilitates the training of image classification neural networks with assured privacy protections. It also tests the robustness of these models against prevalent attacks on deep learning systems. Depen...
Asset Type
Library
Secure Generative Data Exchange (SGDE)
The Secure Generative Data Exchange (SGDE) is a Python application that allows users to train, upload, and download generative models to and from a server.
Asset Type
Library
Scheduling for Accelerated Devices
The GPU Scheduler tool determines the best scheduling and GPU allocation for Deep Learning training jobs, reducing energy and execution costs (in both private or public clouds) while meeting deadline constraints. The tool only requires the list of submit...
Asset Type
Library
IM (Infrastructure Manager)
Service for the complete orchestration of virtual infrastructures and applications deployed on it, including resource provisioning, deployment, configuration, re-configuration, and termination.
Asset Type
Library
AI-SPRINT-STUDIO
This project contains the design environment project structure of an AI-SPRINT application. Furthermore, it contains the initial version of the AI-SPRINT parsers.
Asset Type
Library
SPACE4AI-R
SPACE4AI-R : runtime management tool for aI applications component placement and resource selection in computing continua
Personalised Healthcare
Healthcare represents one of the most promising areas for innovative applications exploiting the computing continuum, and the concept of personalised healthcare is becoming a reality through AI-enabled functionality. The specific focus of this use case wa...
Maintenance and Inspection
This use case was focused on the maintenance and inspection of the large turbines that are used for the (highly renewable) generation of electric power from wind. The inevitable damage to the turbines from the exposure to the elements can lead to expensiv...
Farming 4.0
The agricultural use case involved the cultivation of vineyards, with an end user in France that produces agricultural machinery. The agricultural use case demonstrated how AI can enable an enterprise not only to enhance its business-related activities,...