Gianvito Pio

Modeling spatio-temporal locality in multi-step forecasting of geo-referenced time series

Annunziata D’Aversa, Gianvito Pio, Michelangelo Ceci

Forecasting future measurements from geographically distributed sensors is essential across many domains. However, the spatial distribution of these sensors raises multiple challenges, primarily due to spatial autocorrelation phenomena, that introduce inter-dependencies among nearby locations, that cannot therefore be treated independently. While some …

IMMENSE: Inductive Multi-perspective User Classification in Social Networks

Francesco Benedetti, Antonio Pellicani, Gianvito Pio, Michelangelo Ceci

Online social networks increasingly expose people to users who propagate discriminatory, hateful, and violent content. Young users, in particular, are vulnerable to exposure to such content, which can have harmful psychological and social repercussions. Given the massive scale of today's social networks, …

Similarity-Guided Forecasting of Multiple Sequences from Mechanical Testing Data of Additively Manufactured Components

Antonio Pellicani, Gianvito Pio, Donato Malerba, Michelangelo Ceci

it, si (code pays fourni par la source)

Dynamic instance weighting for online learning in multi-cryptocurrency price and trend forecasting

Antonio Pellicani, Gianvito Pio, Sašo Džeroski, Michelangelo Ceci

Abstract The cryptocurrency market represents a significant innovation in the financial ecosystem, built upon cryptographic principles to ensure secure and transparent transactions. Cryptocurrencies experienced a global adoption, driven by their decentralized nature that enables borderless transactions without third-party intermediaries. The price of …

Leveraging textual content, citational aspects and dissenting opinions through a multi-view contrastive learning methodology for legal precedent analysis

Graziella De Martino, Piero Marra, Annunziata D’Aversa, Lorenzo Pulito et autres

Artificial Intelligence is transforming the digital justice field by introducing technologies to automate document review, predict case outcomes, and perform legal research tasks. While offering significant benefits, these systems appear to prioritize decision-making patterns that are simply repeated over time, thus neglecting …

it, si (code pays fourni par la source)

Handling complex backgrounds and light perturbations for enhancing learning tasks from images of vegetables

Stefano Polimena, Gianvito Pio, Giovanni Attolico, Michelangelo Ceci

Abstract The quality assessment of fruits and vegetables is crucial in the agroalimentary supply chain, as it directly affects consumer satisfaction, market value and overall food security. Traditional approaches rely on visual inspections or destructive techniques, which are labor-intensive and time-consuming. On …

it, si (code pays fourni par la source)

Modeling spatio-temporal locality in multi-step forecasting of geo-referenced time series

Annunziata D’Aversa, Gianvito Pio, Michelangelo Ceci

Abstract Forecasting future measurements from geographically distributed sensors is essential across many application domains. However, the spatial distribution of these sensors raises multiple challenges, primarily due to spatial autocorrelation phenomena, that introduce inter-dependencies among nearby locations, that cannot therefore be treated independently …

it, si (code pays fourni par la source)

Robust Human Activity Prediction Through Multi-View Sensor Data Integration

Niccolò Petti, Antonio Pellicani, Fabio Frustaci, Francesco Porreca et autres

Human Activity Prediction (HAP) systems play a crucial role in assisting caregivers by enabling timely assistance and preventive interventions for the elderly. In this work, we present a multi-view approach to HAP that leverages data from multiple sensor sources to enhance system …

it (code pays fourni par la source)

COCOWEARS: A framework for COntinuum COmputing WEARable Systems

Gianluca Aloi, Fabio Frustaci, Raffaele Gravina, Antonio Guerrieri et autres

The amount and diversity of data generated by the sensors available on current Wearable Computing Systems (WCS) impose the adoption of advanced, efficient (and often customized) data analysis methods, including Machine Learning (ML) / Artificial Intelligence (AI) and multi-sensor information fusion. With …

it (code pays fourni par la source)

Correction to: Real-Time Anomaly Prediction from Cryptocurrency Time Series

Antonio Pellicani, Gianvito Pio, Sašo Džeroski, Michelangelo Ceci

it, si (code pays fourni par la source)

Discovery Science

Sašo Džeroski, Jurica Levatić, Gianvito Pio, Nikola Simidjievski

A Novel AI Approach for the Diagnosis of Alzheimer’s Disease from Multi-modal Incomplete Data

Veronica Buttaro, Giuseppe Lamanna, Claudio Basilio Caporusso, Gianvito Pio et autres

it (code pays fourni par la source)