Introducing AI-SPRINT: bringing artificial intelligence applications to real life
In this blog post we introduce a new and very exciting European project that Beck et al. is participating: AI-SPRINT, short for Artificial Intelligence in Secure PRIvacy-preserving computing coNTinuum. Beck et al. will apply extensive cloud computing knowledge in a consortium consisting of several industry partners, along with several European universities.
For most of its history, artificial intelligence has been used in academia. In recent years it has grown in popularity and slowly made its way into the mainstream public. However, the journey from academic specialization and complexity to accessible tools for businesses is not yet complete.
Academics and companies are vital elements of the economy, yet they don’t always overlap. While the first group focuses on specific and fine-grained solutions, businesses develop scalable tools that others can use.
As an example, in one side, a group of researchers publishes an extremely effective image processing machine learning networks that obtain all-time highs in computer vision metrics. On the other side, a company would like to equip their cameras with technology to detect faulty machines, mistakes in the supply chain or diseases on animals or plants. This company should use the image processing network, but how to bridge the gap? How to connect the abstract and complex machine learning model with a program or tool that the company can use? AI-SPRINT aims to solve this problem.
Why AI-SPRINT
For AI to ubiquitous in the economy, it needs access to the real world applications, and that requires access to devices that businesses use. Currently there is extensive effort to connect AI to edge computing, and AI-SPRINT aims to be a strong voice in this regard.
AI-SPRINT, or Artificial Intelligence in Secure PRIvacy-preserving computing coNTinuum is a a Research and Innovation Action co-funded by the European Commission, H2020 Programme, coordinated by the Politecnico University of Milano, Italy with the collaboration of several other universities, research centers and companies all over Europe. The project has received an European grant and will run until end of 2023.
AI-SPRINT’s contribution can be defined as follows:
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.
The main outputs of the project 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 will meet the digitisation needs of businesses and the public sector proving its competitive edge and replicability in three real-world scenarios, spanning farming 4.0, maintenance and inspection, and personalised healthcare.
Novel framework for design and operation of AI applications
AI-SPRINT will build simplified programming models to reduce the steep learning curves in the development of AI software.
Computing continua
The framework will contain highly specialized building blocks for distributed training, privacy preservation and advanced machine learning models, to shorten time-to-market for AI applications.
The following image shows different layers of the computing continuum: from cloud services, to edge servers and IoT and AI-enabled edge sensors. With AI-SPRINT, these layers are connected to enable a continuous communication for training, deploying and inference.
Design and partition of AI applications among cloud-based solutions
The distributed system will support automated deployment and dynamic reconfiguration to decrease the cost of operating AI software.
Security and privacy guarantees
The proposed system enables a finely-tuned tradeoff between performance (e.g. in terms of end-to-end latency and throughput) and AI model accuracy, while providing security and privacy guarantees.
Participants in AI-SPRINT
Four research partners bring over cutting-edge innovation and expertise to the Consortium; two system integrators provide vision on relevant verticals and technology insights, one cloud provider brings real-world implementation expertise, and two specialists in dissemination ensure impacts and uptake.
Three heterogeneous use cases (farming 4.0, maintenance & inspection, and personalized healthcare) are built by industrial partners and beneficiaries include end-users of AI systems, software developers, system integrators, and cloud providers.
The partners in the project, coordinated by Politecnico di Milano, are the following: Barcelona Supercomputing Center, Technische Universität Dresden, Universitat Politècnica de València, Grégoire, Beck et al., Cloud&Heat, 7bulls.com, AirFusion, Trust-IT Services and IDC. These partners come from 6 European countries: Italy, Spain, Germany, France, Romania and Poland.
Use cases
Farming 4.0
AI-SPRINT drives innovations in farming and agriculture for environmental sustainability with increased efficiency via predictive models.
Maintenance and inspection
The project will bring wind turbines improvements in terms of data analysis and quality assessment.
Personalized healthcare
AI-SPRINT will develop an automated system for personalized stroke risk assessment and prevention using continuous, non-invasive monitoring via AI and wearable devices, while also preserving data protection, privacy and security aspects related to healthcare.
The project doesn’t stop here. A dedicated AI-SPRINT Alliance will be set up to engage with small SW houses and EU cloud providers to support the AI and edge computing ecosystem. Alliance Members will reap tangible benefits from AI-SPRINT with the opportunity to join its planned Acceleration Club (A3C), where they could use the AI-SPRINT design tools and runtime environment to provide advanced design solutions hosted in their platform and extend application deployment and resource management from their internal cloud to edge servers and AI enabled sensors or end-user devices, optimising the seamless execution of applications across the computing continuum while also minimising energy consumption.
For more information and updates, visit:
- Beck et al. website: https://www.becketal.com/
- AI-SPRINT website: https://ai-sprint-project.eu
- Twitter: https://twitter.com/ai_sprint
- Linkedin: https://www.linkedin.com/company/ai-sprint
- Youtube: https://www.youtube.com/channel/UCSBAC5zpf8bWf5w3IXY2hAw
