arXiv subjects

Flavio Bertini

Publications and source records attributed to Flavio Bertini.

6 recordsLinked to original sources

arXiv2026

Segment-Level Mandarin Chinese Speech-Based Cognitive Impairment Detection via an Autoencoder with Contrastive Learning

\noindent\textbf{Background and Objective:} Speech has emerged as a low-cost and non-invasive digital biomarker with considerable potential for cognitive impairment detection. However, limited labeled data and cross-dataset variability remain major challenges for robust speech-based screening systems. \par\noindent\textbf{Methods:} We developed a segment-level representation learning framework for speech-based cognitive impairment detection. Speech recordings were divided into short segments and converted into spectrogram representations. To improve robustness under limited-data conditions, offline and online augmentation strategies were combined with autoencoder-based representation learning and contrastive objectives to enhance discriminative latent representations. \par\noindent\textbf{Results:} Experiments conducted on four independent Mandarin Chinese speech datasets demonstrated stable and competitive performance in both binary and three-class classification tasks, with particularly notable improvements in the clinically challenging three-class setting. Ablation studies further supported the effectiveness of the proposed framework. \par\noindent\textbf{Conclusions:} The findings suggest that segment-level speech representation learning may provide a scalable and practical approach for cognitive impairment screening in resource-constrained clinical settings.

cs.SD↗

arXiv2025

Data2Concept2Text: An Explainable Multilingual Framework for Data Analysis Narration

This paper presents a complete explainable system that interprets a set of data, abstracts the underlying features and describes them in a natural language of choice. The system relies on two crucial stages: (i) identifying emerging properties from data and transforming them into abstract concepts, and (ii) converting these concepts into natural language. Despite the impressive natural language generation capabilities demonstrated by Large Language Models, their statistical nature and the intricacy of their internal mechanism still force us to employ these techniques as black boxes, forgoing trustworthiness. Developing an explainable pipeline for data interpretation would allow facilitating its use in safety-critical environments like processing medical information and allowing non-experts and visually impaired people to access narrated information. To this end, we believe that the fields of knowledge representation and automated reasoning research could present a valid alternative. Expanding on prior research that tackled the first stage (i), we focus on the second stage, named Concept2Text. Being explainable, data translation is easily modeled through logic-based rules, once again emphasizing the role of declarative programming in achieving AI explainability. This paper explores a Prolog/CLP-based rewriting system to interpret concepts-articulated in terms of classes and relations, plus common knowledge-derived from a generic ontology, generating natural language text. Its main features include hierarchical tree rewritings, modular multilingual generation, support for equivalent variants across semantic, grammar, and lexical levels, and a transparent rule-based system. We outline the architecture and demonstrate its flexibility through some examples capable of generating numerous diverse and equivalent rewritings based on the input concept.

cs.LO↗

arXiv2024

Survey on Abstractive Text Summarization: Dataset, Models, and Metrics

The advancements in deep learning, particularly the introduction of transformers, have been pivotal in enhancing various natural language processing (NLP) tasks. These include text-to-text applications such as machine translation, text classification, and text summarization, as well as data-to-text tasks like response generation and image-to-text tasks such as captioning. Transformer models are distinguished by their attention mechanisms, pretraining on general knowledge, and fine-tuning for downstream tasks. This has led to significant improvements, particularly in abstractive summarization, where sections of a source document are paraphrased to produce summaries that closely resemble human expression. The effectiveness of these models is assessed using diverse metrics, encompassing techniques like semantic overlap and factual correctness. This survey examines the state of the art in text summarization models, with a specific focus on the abstractive summarization approach. It reviews various datasets and evaluation metrics used to measure model performance. Additionally, it includes the results of test cases using abstractive summarization models to underscore the advantages and limitations of contemporary transformer-based models. The source codes and the data are available at https://github.com/gospelnnadi/Text-Summarization-SOTA-Experiment.

cs.AI↗

arXiv2021

Understanding Cycling Mobility: Bologna Case Study

Understanding human mobility in urban environments is of the utmost importance to manage traffic and for deploying new resources and services. In recent years, the problem is exacerbated due to rapid urbanization and climate changes. In an urban context, human mobility has many facets, and cycling represents one of the most eco-friendly and efficient/effective ways to move in touristic and historical cities. The main objective of this work is to study the cycling mobility within the city of Bologna, Italy. We used six months dataset that consists of 320,118 self-reported bike trips. In particular, we performed several descriptive analysis to understand spatial and temporal patterns of bike users for understanding popular roads, and most favorite points within the city. This analysis involved several other public datasets in order to explore variables that can possibly affect the cycling activity, such as weather, pollution, and events. The main results of this study indicate that bike usage is more correlated to temperature, and precipitation and has no correlation to wind speed and pollution. In addition, we also exploited various machine learning and deep learning approaches for predicting short-term trips in the near future (that is for the following 30, and 60 minutes), that could help local governmental agencies for urban planning. Our best model achieved an R square of 0.91, a Mean Absolute Error of 5.38 and a Root Mean Squared Error of 8.12 for the 30-minutes time interval.

cs.CY↗

arXiv2021

Universal properties of multimodal human mobility: a statistical physics point of view

The statistical properties of human mobility have been studied in the framework of complex systems physics. Taking advantage from the new datasets made available by the information and communication technologies, the distributions of mobility path lengths and of trip duration have been considered to discover the fingerprints of complexity characters, but the role of the different transportation means on the statistical properties of urban mobility has not been studied in deep. In this paper we cope with the problem of pointing out the existence of universal features for different type of individual mobility: pedestrian, cycling and vehicular urban mobility. In particular, we propose the use of travel time as universal 'energy' for the mobility and we define a simple survival model that explains the travel time distribution of the different types of mobility. the analysis is performed in the metropolitan area of Bologna (Italy), where GPS datasets were available on individual trips using different transport means. Our results could suggest how to plan the different transportation networks to realize a multimodal mobility compatibly with the citizens propensities to use the different transport means.

physics.soc-ph↗

arXiv2020

Are Social Networks Watermarking Us or Are We (Unawarely) Watermarking Ourself?

In the last decade, Social Networks (SNs) have deeply changed many aspects of society, and one of the most widespread behaviours is the sharing of pictures. However, malicious users often exploit shared pictures to create fake profiles leading to the growth of cybercrime. Thus, keeping in mind this scenario, authorship attribution and verification through image watermarking techniques are becoming more and more important. In this paper, firstly, we investigate how 13 most popular SNs treat the uploaded pictures, in order to identify a possible implementation of image watermarking techniques by respective SNs. Secondly, on these 13 SNs, we test the robustness of several image watermarking algorithms. Finally, we verify whether a method based on the Photo-Response Non-Uniformity (PRNU) technique can be successfully used as a watermarking approach for authorship attribution and verification of pictures on SNs. The proposed method is robust enough in spite of the fact that the pictures get downgraded during the uploading process by SNs. The results of our analysis on a real dataset of 8,400 pictures show that the proposed method is more effective than other watermarking techniques and can help to address serious questions about privacy and security on SNs.

cs.MM↗