Assets

This module provides a placeholder for AL systems i.e., AI systems that can consult an authority (e.g., a human) in the cases where they lack data/information to take proper decisions.

The module implements different strategies in response to various attacks against AI system, notably poisoning and evasion attacks.

It is composed by a safety zone detector and a robot planner. The first module will be used to provide insights on the safe placement of robots in a manufacturing environment.

Distributed Ledger Services for Data Reliability (DLSDR) provides a decentralized data reliability solution for industrial AI algorithms configurations and results. It offers an Analytics Engine Configuration (AEC) Service that supports Analytics by providing the capability for distributing analytics manifest objects across multiple gateways. Additionally, it offers an Analytics Results Publishing (ARP) Service,  that makes it possible for analytics instances to share analytics results on the Distributed Ledger infrastructure, thus contributing to a common data set representing the combined results across the entire distributed system.

This module provides and executes Explainable Artificial Intelligence models and algorithms.

FaMS uses artificial intelligence (AI) models relying on machine learning to estimate fatigue exertion level and mental stress of subjects based on static data (e.g., age, weight, etc.) as well as dynamic data (e.g., HR, EDA, skin temperature).

The feedback module interfaces to some interaction modules (e.g., GUI or NLP) that enable the transfer of user data to the feedback module and vice versa.

The platform supports human in the loop processes provides feedback/results on workers’ safety and performance.

Natural Language Processing related components, proof of concepts and recommendations to facilitate the interaction between humans and machines and to get contextual information enabling efficient collaboration.

This module consolidates domain knowledge about the production processes of the manufacturing environment.

This module is destined to assess risk for assets associated with AI-based systems in manufacturing lines.

RMS is a Data collection framework which provides the specifications and relevant implementation to enable a real time data collection, transformation, filtering, and management service to facilitate data consumers (i.e., analytic algorithms). The framework can be applied in IoT environments supporting solutions in various domains (e.g., Industrial, Cybersecurity, etc.). The design of the framework is driven by configurability, extensibility, dynamic setup and stream handling capabilities.