Searcharxiv⌕ Search

arXiv subjects

Tommaso Colafiglio

Publications and source records attributed to Tommaso Colafiglio.

2 recordsLinked to original sources

EE-Motion: An EEG-based Web Architecture for Live Affective Music Recommendation

Music listening is intrinsically tied to emotion, which drifts continuously within a single session. Although modern browsers interface with wearable brain-computer interfaces, recommendation systems remain structured around discrete logs and lack the infrastructure to integrate continuous physiological signals. Furthermore, existing affect-aware models rely on static user profiles and offline training, failing to serve anonymous newcomers without model retraining. We present a web platform that resolves both challenges. Pairing with a consumer electroencephalogram (EEG) headband over Web Bluetooth, the system captures live EEG, mapping frontal alpha asymmetry and arousal index to normalized valence-arousal proxy coordinates on Russell's circumplex plane. Driven by these coordinates, an affective adapter unifies structurally diverse recommendation backbones under a shared live scoring mechanism. By parameterizing anonymous visitors through a few favorite tracks, the module recommends tracks conditioned on live proxy coordinates. This demonstrates that real-time EEG-derived control signals can steer recommendations without persistent user tables or model retraining.

cs.IR↗

MAFUS: a Framework to predict mortality risk in MAFLD subjects

Metabolic (dysfunction) associated fatty liver disease (MAFLD) establishes new criteria for diagnosing fatty liver disease independent of alcohol consumption and concurrent viral hepatitis infection. However, the long-term outcome of MAFLD subjects is sparse. Few articles are focused on mortality in MAFLD subjects, and none investigate how to predict a fatal outcome. In this paper, we propose an artificial intelligence-based framework named MAFUS that physicians can use for predicting mortality in MAFLD subjects. The framework uses data from various anthropometric and biochemical sources based on Machine Learning (ML) algorithms. The framework has been tested on a state-of-the-art dataset on which five ML algorithms are trained. Support Vector Machines resulted in being the best model. Furthermore, an Explainable Artificial Intelligence (XAI) analysis has been performed to understand the SVM diagnostic reasoning and the contribution of each feature to the prediction. The MAFUS framework is easy to apply, and the required parameters are readily available in the dataset.

stat.ML↗