Project Funding Agency: Horizon 2020

Smart Parts Detector in Manufacturing using Deep Learning

We are designing and implementing SmartPartsDetector, a new component for the SHOP4CF EU project, that enables manufacturing SMEs of small parts to optically identify their parts by leveraging state-of-the-art convolutional neural networks (CNN). This fundamental capability can then be used to assist and empower humans by devising a wide range of digital tools, e.g. production quality control software, staff training applications, etc.

ARES: A Next-Generation, Erasure Coded, Shared Distributed Storage System

Distributed shared storage services (DSS), is the building block to yield complex, decentralized, cloud applications in emerging technologies (e.g., IoT, VR/AR), as they may offer a transparent cloud storage space where distributed applications can store, retrieve, and coordinate over shared data.The popularity of distributed shared storage services has increased recently, due to the emergence of powerful mobile devices and the need for immediate and reliable access to user data from multiple devices.

In this project, the EU- US team plans to run thorough experimental evaluations on the performance of a novel protocol ARES [1] , which implements an Atomic Distributed Shared Storage (ADSS) space over asynchronous, fail prone, message passing network nodes. Such services usually keep copies of the data in multiple network locations, we refer to as replica hosts or servers , to ensure data availability and survivability.


As the Digital Transformation of Europe, and the rest of the world, is rapidly picking up pace, the underlying physical infrastructure is similarly expanding to keep up with demand generated by over 2 billion connected computers and more than 30 billion smartphones, wearables and IoT devices. Nevertheless, Internet applications and services remain prone to inevitable hardware failures, that lead to data losses and increased maintenance costs. The primary problem lies with the cost of implementing data redundancy by constantly adding expensive hardware to cater to the needs of traditional data replication approaches (e.g. by always keeping copies of a file on multiple servers).

With the assistance of an Innovation Associate specializing in Machine Learning, Algolysis Ltd aspires to extend its cloud-based storage device monitoring service (DriveNest – with a robust state-of-the-art failure prediction engine. Reliably identifying soon-to-fail storage devices can be a transformative capability across the ICT sector, as a range of proactive data management and mitigation services can be built on top.