Software
OpenFL-XAI is an extension to the open-source OpenFL framework for providing user-friendly support to Federated Learning (FL) of Fuzzy Rule-Based Systems (FRBS) as explainable-by-design models.
As an extension to OpenFL, OpenFL-XAI enables several data owners, possibly dislocated across different sites, to collaboratively train an eXplainable Artificial Intelligence (XAI) model while preserving the privacy of their raw data.
SKMoefs is a Python module for Multi-Objective Evolutionary Fuzzy Systems, built upon Platypus. It is developed in Scikit-Learn fashion, resulting in a user friendly interface.
Reference publication:
- Gallo, G., Ferrari, V., Marcelloni, F., Ducange, P. (2020). SK-MOEFS: A Library in Python for Designing Accurate and Explainable Fuzzy Models. In: Information Processing and Management of Uncertainty in Knowledge-Based Systems. IPMU 2020. Communications in Computer and Information Science, vol 1239. Springer, Cham.
Fuzzy Machine Learning Python Library (FuzzyML) implements several fuzzy ML algorithms in Python.
The current version contains:
- Fuzzy Binary Decision Tree (FBDT)
- Fuzzy Multi-way Decision Tree (FMDT)
- Fuzzy Minimum Description Length Principle Discretizer (FMDLP)
- Crisp Minimum Description Length Principle Discretizer (MDLP)
Reference publication:
A. Segatori, F. Marcelloni, W. Pedrycz, “On Distributed Fuzzy Decision Trees for Big Data“, IEEE Transactions on Fuzzy Systems
BitBucket: https://bitbucket.org/mbarsacchi/fuzzyml/src/master/
Demonstration Activities
Fed-XAI Demo
This demonstration activity has been carried out in the framework of Hexa-X – the EU Flagship Project for 6G.
The next generation of mobile networks is poised to rely extensively on Artificial Intelligence (AI) to deliver innovative services. However, it is crucial for AI systems to fulfill key requirements such as trustworthiness, inclusiveness, and sustainability.
Starting from these requirements, we proposed Federated Learning of eXplainable AI (Fed-XAI) models. Together with our colleagues at DII, TIM and Intel, we implemented a real-time testbed, serving as a proof of concept for the Fed-XAI paradigm. The testbed utilizes genuine applications and real devices that interact with a mobile network, emulated using the Simu5G simulator. Its primary objective is to provide explainable predictions regarding video-streaming quality in an automotive scenario.
Want to know more?! Watch this short video and read out more here and here.
PPE Detection Demo
A smart system for personal protective equipment detection in industrial environments based on deep learning at the edge
The Demo has been developed under the framework of the Crosslab activities.
The objective of the designed smart system is to improve the safety of workers by monitoring the correct use of Personal Protective Equipment (PPE) in dangerous areas. The PPE detection is carried out in real time based on video streaming analysis and Deep Neural Network (DNN).
We adopt the edge computing model in which the application for image analysis and classification is deployed on an embedded system installed in proximity of the camera and directly connected to it. The system does not require continuous image transmission towards a cloud system, thus ensuring bandwidth efficiency, reliability, and workers’ privacy.
A prototype of the proposed system was developed exploiting a low-cost commercial embedded system, i.e. a Raspberry PI, equipped with an Intel Neural Compute Stick 2.