In this work, we introduce Ducho 2.0, the latest stable version of our framework. Differently from Ducho, Ducho 2.0 offers a more personalized user experience with the definition and import of custom extraction models fine-tuned on specific tasks and datasets. Moreover, the new version is capable of extracting and processing features through multimodal-by-design large models. Notably, all these new features are supported by optimized data loading and storing to the local memory. To showcase the capabilities of Ducho 2.0, we demonstrate a complete multimodal recommendation pipeline, from the extraction/processing to the final recommendation. The idea is to provide practitioners and experienced scholars with a ready-to-use tool that, put on top of any multimodal recommendation framework, may permit them to run extensive benchmarking analyses. All materials are accessible at: https://github.com/sisinflab/Ducho/
Emotion recognition is crucial in affective computing, aiming to bridge the gap between human emotional states and computer understanding. This study presents NeuroSense, a novel electroencephalography (EEG) dataset utilizing low-cost, sparse electrode devices for emotion exploration. Our dataset comprises EEG signals collected with the portable 4-electrodes device Muse 2 from 30 participants who, thanks to a neurofeedback setting, watch 40 music videos and assess their emotional responses. These assessments use standardized scales gauging arousal, valence, and dominance. Additionally, participants rate their liking for and familiarity with the videos.We develop a comprehensive preprocessing pipeline and employ machine learning algorithms to translate EEG data into meaningful insights about emotional states. We verify the performance of machine learning (ML) models using the NeuroSense dataset. Despite utilizing just 4 electrodes, our models achieve an average accuracy ranging from 75% to 80% across the four quadrants of the dimensional model of emotions. We perform statistical analyses to assess the reliability of the self-reported labels and the classification performance for each participant, identifying potential discrepancies and their implications. We also compare our results with those obtained using other public EEG datasets, highlighting the advantages and limitations of sparse electrode setups in emotion recognition. Our results demonstrate the potential of low-cost EEG devices in emotion recognition, highlighting the effectiveness of ML models in capturing the dynamic nature of emotions. The NeuroSense dataset is publicly available, inviting further research and application in human-computer interaction, mental health monitoring, and beyond.
29 December 2025 in Expert Systems with Applications
Generative modeling for 3D brain MRI is challenged by a trade-off between anatomical fidelity, sample diversity, and computational efficiency. Diffusion-based approaches achieve strong visual quality but typically require hundreds to thousands of sampling steps, while latent-space compression can introduce reconstruction artifacts and degrade fine-grained anatomy. We introduce FlowLet, a conditional generative framework that performs Flow Matching in an invertible 3D wavelet domain. This representation enables multi-scale generation without learned latent compression, while deterministic ODE sampling allows fast inference. Age conditioning is modeled through complementary feature-wise modulation and spatially adaptive cross-attention, enabling explicit control over age-related morphological variation. Across multi-site neuroimaging datasets, FlowLet achieves competitive and, in several settings, superior global fidelity compared to diffusion-based baselines using as few as 10 sampling steps. Region-based evaluation across 95 cortical and subcortical brain regions demonstrates improved local anatomical plausibility beyond what is captured by global similarity metrics alone. In a downstream brain age prediction study, models augmented with FlowLet-generated data consistently reduce prediction error relative to real-only training and other generative baselines. Rather than focusing on a single dominant metric improvement, these results highlight a consistent trade-off between efficiency, controllability, and anatomically meaningful 3D brain MRI generation. The proposed framework is released as open-source to support reproducibility.