Pubblicazioni scientifiche

La ricerca accademica che diventa vantaggio competitivo per la tua azienda

Pubblicazioni scientifiche

La ricerca accademica
che diventa vantaggio competitivo per la tua azienda

Pubblicazioni scientifiche

La ricerca accademica che diventa vantaggio competitivo per la tua azienda

Renewable energy

Leggi il paper→

A Review of the Enabling Methodologies for Knowledge Discovery from Smart Grids Data

Marzo 14, 2026

A KDD-driven pipeline turns smart meter streams into multi-step load forecasts, benchmarking feature reduction and models.

F. De Caro, A. Andreotti, R. Araneo, M. Panella, A. Rosato, A. Vaccaro, D. Villaci

Biomedical

Leggi il paper→

Enhancing Autism Detection Through Gaze Analysis Using Eye Tracking Sensors and Data Attribution with Distillation in Deep Neural Networks

Dicembre 5, 2024

A deep learning model enhances early autism diagnosis by analyzing visual patterns with eye tracking.

F. Colonnese, F. Di Luzio, A. Rosato, M. Panella

Quantum computing

Leggi il paper→

Quantum Generative Modeling via Straightforward State Preparation

Novembre 30, 2024

A lightweight quantum generative model creates high-fidelity data samples with minimal parameters and efficient state preparation.

L. Lavagna, F. De Falco, S. Piperno, A. Ceschini, A. Rosato, M. Panella

Quantum computing

Leggi il paper→

Enhancing QAOA Ansatz via Multi-Parameterized Layer and Blockwise Optimization

Novembre 29, 2024

A novel quantum-classical algorithm boosts QAOA performance with fewer layers, enabling real-world optimization on NISQ devices.

F. De Falco, S. Piperno, L. Lavagna, A. Ceschini, A. Rosato, M. Panella

Renewable energy

Leggi il paper→

A Deep Learning-based Approach for Battery Life Classification

Novembre 20, 2024

A deep learning-based LSTM network accurately classifies battery health, optimizing energy storage and predictive maintenance.

F. Succetti, A. Dell’Era, A. Rosato, A. Fioravanti, R. Araneo, M. Panella

Biomedical

Leggi il paper→

An explainable fast deep neural network for emotion recognition

Novembre 14, 2024

A fast, explainable deep neural network enhances emotion recognition by optimizing facial landmark analysis.

F. Di Luzio, A. Rosato, M. Panella

Renewable energy

Leggi il paper→

Multi-label classification with imbalanced classes by fuzzy deep neural networks

Ottobre 18, 2024

A fuzzy deep neural network accurately classifies household appliances in real time using symbolic data and multi-label AI.

F. Succetti, A. Rosato, M. Panella

Quantum computing

Leggi il paper→

Quantum enhanced knowledge distillation

Ottobre 11, 2024

Classical-to-quantum knowledge distillation boosts hybrid AI performance using efficient quantum circuits and reduced model sizes.

S. Piperno, L. Lavagna, F. De Falco, A. Ceschini, A. Rosato, D. Windridge, M. Panella

Quantum computing

Leggi il paper→

A variational approach to quantum gated recurrent units

Agosto 21, 2024

A faster and efficient Quantum Gated Recurrent Unit (QGRU) improves time series forecasting.

A. Ceschini, A. Rosato, M. Panella

Aerospace

Leggi il paper→

A Neural Network Symbolic Approach to Structural Health Monitoring in Aerospace Applications

Agosto 8, 2024

A symbolic deep learning approach enhances structural health monitoring in aerospace achieving near-perfect damage classification.

F. Angeletti, F. Succetti, M. Panella, A. Rosato

Advanced AI Methods

Leggi il paper→

An adaptive embedding procedure for time series forecasting with deep neural networks

Settembre 9, 2023

A novel deep learning model that integrates adaptive embedding with bidirectional LSTMs to enhance time series forecasting.

F. Succetti, A. Rosato, M. Panella

Cybersecurity

Leggi il paper→

Modular quantum circuits for secure communication

Agosto 2, 2023

Quantum modular circuits enable ultra-secure communication for fast, parallel encryption and decryption.

A. Ceschini, A. Rosato, M. Panella

Advanced AI Methods

Leggi il paper→

Perceptron Theory Can Predict the Accuracy of Neural Networks

Febbraio 6, 2023

A perceptron-based theory predicts neural network accuracy using output statistics, fast, data-free, and surprisingly precise.

D. Kleyko, A. Rosato, E. Paxon Frady, M. Panella, F. T. Sommer

Renewable energy

Leggi il paper→

Challenges and perspectives of smart grid systems in islands: a real case study

Gennaio 4, 2023

Integrating renewables with AI tools offers sustainable solutions, especially in isolated contexts.

F. Succetti, A. Rosato, R. Araneo, G. Di Lorenzo, M. Panella

Aerospace

Leggi il paper→

A Study on structural health monitoring of a large space antenna via distributed sensors and deep learning

Dicembre 29, 2022

AI-powered Bi-LSTM detect structural damage in flexible satellite antennas with over 99% accuracy using onboard sensor data.

F. Angeletti, P. Iannelli, P. Gasbarri, M. Panella, A. Rosato

Biomedical

Leggi il paper→

A randomized deep neural network for emotion recognition with landmarks detection

Dicembre 6, 2022

Novel randomized DNN uses facial landmarks for fast emotion recognition.

F. Di Luzio, A. Rosato, M. Panella

Renewable energy

Leggi il paper→

Hybrid Quantum-Classical Recurrent Neural Networks for Time Series Prediction

Settembre 30, 2022

A hybrid quantum-classical recurrent network improves solar power forecasting by combining LSTM memory with quantum layers.

A. Ceschini, A. Rosato, M. Panella

Hyperdimensional Computing

Leggi il paper→

Few-shot Federated Learning in Randomized Neural Networks via Hyperdimensional Computing

Agosto 30, 2022

Fast, private AI learning from few examples using hyperdimensional computing and randomized networks across distributed devices.

A. Rosato, M. Panella, E. Osipov, D. Kleyko

Renewable energy

Leggi il paper→

Multivariate Time Series Analysis for Electrical Power Theft Detection in the Distribution Grid

Agosto 19, 2022

A convolutional neural network analyzes multivariate time series to detect energy theft in distribution grids effectively.

A. Ceschini, A. Rosato, F. Succetti, R. Araneo, M. Panella

Biomedical

Leggi il paper→

A Fast Deep Learning Technique for Wi-Fi-Based Human Activity Recognition

Luglio 5, 2022

A fast AI-based approach for Wi-Fi-based human activity recognition achieves real-time, non-invasive monitoring.

F. Succetti, A. Rosato, F. Di Luzio, A. Ceschini, M. Panella

Quantum computing

Leggi il paper→

Quasi-Chaotic Oscillators Based on Modular Quantum Circuits

Aprile 18, 2022

Quantum modular circuits generate quasi-chaotic signals for future secure, parallel encryption schemes.

A. Ceschini, A. Rosato, M. Panella

Quantum computing

Leggi il paper→

Design of an LSTM Cell on a Quantum Hardware

Novembre 8, 2021

A quantum circuit design translates LSTM memory gates into qubit-based operations for future quantum recurrent networks

A. Ceschini, A. Rosato, M. Panella

Renewable energy

Leggi il paper→

Multivariate Prediction of Energy Time Series by Autoencoded LSTM Networks

Novembre 3, 2021

An autoencoded LSTM learns hidden structure in multivariate energy signals to forecast solar power more accurately.

F. Succetti, F. Di Luzio, A. Ceschini, A. Rosato, R. Araneo, M. Panella

Renewable energy

Leggi il paper→

Deep Neural Networks for Electric Energy Theft and Anomaly Detection in the Distribution Grid

Novembre 3, 2021

A deep Bi-LSTM detects daily energy theft and grid anomalies directly from smart meter time series.

A. Ceschini, A. Rosato, F. Succetti, F. Di Luzio, M. Mitolo, R. Araneo, M. Panella

Hyperdimensional Computing

Leggi il paper→

Hyperdimensional Computing for Efficient Distributed Classification with Randomized Neural Networks

Settembre 20, 2021

A hyperdimensional compression scheme lets distributed neural agents share classifiers efficiently without sharing raw data.

A. Rosato, M. Panella, D. Kleyko

Renewable energy

Leggi il paper→

A Blockwise Embedding for Multi-Day-Ahead Prediction of Energy Time Series by Randomized Deep Neural Networks

Settembre 20, 2021

A randomized CNN-LSTM learns energy data in daily blocks to forecast entire future days with high efficiency.

F. Di Luzio, A. Rosato, F. Succetti, M. Panella

Hyperdimensional Computing

Leggi il paper→

On Effects of Compression with Hyperdimensional Computing in Distributed Randomized Neural Networks

Agosto 21, 2021

An HDC-based compression method makes distributed classifiers lighter to share while preserving predictive power.

A. Rosato, M. Panella, E. Osipov, D. Kleyko

Aerospace

Leggi il paper→

Deep learning-based Structural Health Monitoring for damage detection on a large space antenna

Agosto 5, 2021

LSTM networks detect and localize structural damage in large space platforms by learning vibration patterns from sensor data.

P. Iannelli, F. Angeletti, P. Gasbarri, M. Panella, A. Rosato

Distributed Learning

Leggi il paper→

A decentralized algorithm for distributed ensemble clustering

Luglio 27, 2021

Agents cluster local data and reach global consensus by sharing prototypes, not data, enabling private distributed learning.

A. Rosato, R. Altilio, M. Panella

Renewable energy

Leggi il paper→

2-D Convolutional Deep Neural Network for the Multivariate Prediction of Photovoltaic Time Series

Aprile 23, 2021

A 2D CNN-LSTM model turns weather and PV data into sharper multivariate solar power forecasts.

A. Rosato, R. Araneo, A. Andreotti, F. Succetti, M. Panella

Renewable energy

Leggi il paper→

Two-stage dynamic management in energy communities using a decision system based on elastic net regularization

Marzo 31, 2021

A two-stage forecasting-optimization system for efficient management of energy communities.

A. Rosato, M. Panella, A. Andreotti, Osama A. Mohammed, R. Araneo,

Renewable energy

Leggi il paper→

Two-stage dynamic management in energy communities using a decision system based on elastic net regularization

Marzo 31, 2021

A CNN–LSTM model turns multivariate time series into 2D maps to improve solar power forecasting from weather and sensor data.

A. Rosato, M. Panella, A. Andreotti, Osama A. Mohammed, R. Araneo

Renewable energy

Leggi il paper→

Deep Neural Networks for Multivariate Prediction of Photovoltaic Power Time Series

Novembre 20, 2020

Deep neural networks enhance photovoltaic power forecasting by leveraging multivariate time-series modelling.

F. Succetti, A. Rosato, R. Araneo, M. Panella,

Efficient Edge AI

Leggi il paper→

A Parallel Hardware Implementation for 2-D Hierarchical Clustering Based on Fuzzy Logic

Ottobre 21, 2020

Energy-aware FPGA architecture enables parallel fuzzy hierarchical clustering for real-time embedded intelligence.

G. C. Cardarilli, L. Di Nunzio, R. Fazzolari, M. Panella, M. Re, A. Rosato

Renewable energy

Leggi il paper→

Prediction of Photovoltaic Time Series by Recurrent Neural Networks and Genetic Embedding

Settembre 3, 2020

Genetic optimization of time-delay embedding boosts recurrent neural network accuracy for photovoltaic time series forecasting.

A. Rosato, R. Araneo, M. Panella

Efficient Edge AI

Leggi il paper→

An Energy-Aware Hardware Implementation of 2D Hierarchical Clustering

Agosto 6, 2020

Energy-aware hardware optimizations make 2D hierarchical clustering fast and practical for low-power embedded and edge devices.

G. C. Cardarilli, R. Fazzolari, M. Matta, M. Panella, A. Rosato, S. Spanò

Renewable energy

Leggi il paper→

A Fuzzy Neural Network Approach to Quality Assessment of Water Reservoirs

Marzo 2, 2020

Satellite imagery and fuzzy neural networks enable accurate estimation of key water quality indicators in large reservoirs.

H. A. N. Silva, A. Rosato, M. Panella

Aerospace

Leggi il paper→

Retrieving Chlorophyll-a Levels, Transparency and TSS Concentration from Multispectral Satellite Data by Using Artificial Neural Networks

Febbraio 19, 2018

AI and satellite data join forces to estimate water quality in Amazon reservoirs with high accuracy and minimal fieldwork.

H. A. Nascimento Silva, G. Laneve, A. Rosato, M. Panella

Efficient Edge AI

Leggi il paper→

Finite precision implementation of random vector functional-link networks

Novembre 7, 2017

Optimized RVFL neural networks enable accurate AI on low-power hardware using finite precision and genetic algorithms.

A. Rosato, R. Altilio, M. Panella

Efficient Edge AI

Leggi il paper→

A nonuniform quantizer for hardware implementation of neural networks

Novembre 2, 2017

Nonuniform quantization and genetic algorithms optimize neural networks for efficient implementation on low-precision hardware.

R. Altilio, A. Rosato, M. Panella

Distributed Learning

Leggi il paper→

Distributed Learning of Random Weights Fuzzy Neural Networks

Novembre 10, 2016

Self-organizing distributed AI systems enable scalable, resilient learning across networks without centralized control.

R. Fierimonte, M. Barbato, A. Rosato, M. Panella

Renewable energy

Leggi il paper→

Embedding of time series for the prediction in photovoltaic power plants

Settembre 1, 2016

AI models forecast solar power output with high accuracy using time series embedding from real photovoltaic plant data.

A. Rosato, R. Altilio, R. Araneo, M. Panella

Distributed Learning

Leggi il paper→

Recent Advances on Distributed Unsupervised Learning

Giugno 19, 2016

Distributed clustering enables intelligent, resilient data analysis across sensor networks without centralized supervision.

A. Rosato, R. Altilio, M. Panella