profile picture

CTO @ Aidia | CEO @ Sphera - Founder, Machine Learning Engineer, Big Data and Software Architect.

About

I am a Computer Engineer, Founder and Researcher. I love to work with challenging problems, especially in the field of Machine Learning or Signal Processing. I also love Music, Photography and travelling.

Work

Sphera SRL
CEO & Founder

Sphera is a company that offers high-tech, disruptive software products, integrated with AI and BI. The main product is a modular software suite to manage businesses, workflows and Industry 4.0. I manage the company and I supervise the development of the products making strategic decisions and tracing the growing direction of the company

Apr 2022 - Now
Florence, Italy

AIDIA SRL
CTO & Founder

I design and supervise the development of the technological solutions the company offers, selecting the right tools, frameworks and methods and managing the development engineering team. The fields of application include: AI and ML, Microservices architecture and platforms, Big Data. My responsibilities and duties are: Company Management, Project management, Technological and Strategical decision making and Team building.

Jun 2020 - Now
Florence, Italy

Education

UNIVERSITY OF FLORENCE
Doctor of Philosophy - PhD in Smart Computing
AI Lab
Advisor: Prof. Paolo Frasconi

From Nov 2019
Florence, Italy

UNIVERSITY OF FLORENCE
MEng in Computer Engineering
Vote: 110/110 Magna Cum Laude

Thesis title: "RFMLS: Radio Frequency Machine Learning System"
Thesis supervisors: Stratis Ioannidis, Paolo Frasconi, Andrew D. Bagdanov.

Apr 2019
Florence, Italy

UNIVERSITY OF FLORENCE
BS in Computer Engineering
Vote: 102/110

Thesis title: "Recognition techniques and their application to the control of moving systems through embedded platforms"
Thesis supervisor: Fabrizio Argenti.

Nov 2016
Florence, Italy

Research

UNIVERSITY OF FLORENCE
Researcher

I collaborate with Prof. Paolo Frasconi and Dr. Valentijn Borghuis in the design, training, and evaluation of innovative generative models and algorithms to generate music genre interpolations and other forms of autonomous music production. Generative models are unsupervised learning techniques that allow one to sample data points from a distribution inferred from a training set. Prominent exampes that have received significant attention in recent years include generative adversarial networks and various kinds of autoencoders. The goal of this research project is the application of Wasserstein autoencoders to the generation of MIDI musical patterns starting from proprietary data made available by the contractor Borgflocken B.V.

May 2019 - Oct 2019
Florence, Italy

NORTHEASTERN UNIVERSITY - SPIRAL LAB
Researcher

Worked with Machine Learning and Signal Processing on a DARPA project called RFMLS (Radio Frequency Machine Learning System), in order to identify wireless devices based only on raw RF transmissions with thousands of devices. Designed the Neural Network Architecture used for the identification task and helped develop the signal processing system needed to extract the right features.

Sep 2018 - Jan 2019
Boston, MA, USA

UNIVERSITY OF FLORENCE
Researcher (Research Scholarship)

Worked on the ”Development of compression and denoising algorithms for images from AS-OCT” project, financed by C.S.O. S.r.l. Designed a custom and efficient compression and denoising algorithm specifically for AS-OCT images and implemented it (C++ No Libraries).

Jul 2017 - Mar 2018
Florence, Italy

Publications

Conlon: a Pseudo-song Generator Based on a New Pianoroll, Wasserstein Autoencoders, and Optimal Interpolations

Luca Angioloni, Valentijn Borghuis, Lorenzo Brusci, Paolo Frasconi

Proceedings of the 21st International Society for Music Information Retrieval Conference

2020

Pattern-Based Music Generation with Wasserstein Autoencoders and PRC Descriptions

Valentijn Borghuis, Luca Angioloni, Lorenzo Brusci, Paolo Frasconi

29th International Joint Conference on Artificial Intelligence

2020

DeepRadioID: Real-Time Channel-Resilient Optimization of Deep Learning-based Radio Fingerprinting Algorithms

Restuccia, Francesco and D'Oro, Salvatore and Al-Shawabka, Amani and Belgiovine, Mauro and Angioloni, Luca and Ioannidis, Stratis and Chowdhury, Kaushik and Melodia, Tommaso

Proceedings of the Twentieth ACM International Symposium on Mobile Ad Hoc Networking and Computing

2019

No Radio Left Behind: Radio Fingerprinting Through Deep Learning of Physical-Layer Hardware Impairments

Sankhe, Kunal and Belgiovine, Mauro and Zhou, Fan and Angioloni, Luca and Restuccia, Francesco and D'Oro, Salvatore and Melodia, Tommaso and Ioannidis, Stratis and Chowdhury, Kaushik

IEEE Transactions on Cognitive Communications and Networking

2019