Sara Narteni

Sara Narteni

See Latest Publications
See Most Cited Publications
SciProfiles
ORCID Profile
Google Scholar

Research Subjects

Sara Narteni has a total of 42 co-authors. Here are the top co-authors by number of shared publications:

Latest Publications

  • Website
    Google Scholar
    Open Access

    A Consensus Clustering Approach to Amyotrophic Lateral Sclerosis Phenotyping

    by Pilar M. Ferraro, Sara Narteni, Marta Lenatti, Francesca Oliveri, Chiara Gemelli, Corrado Cabona, Antonio Uccelli, Alessia Paglialonga, Maurizio Mongelli, Angelo Schenone

    Amyotrophic Lateral Sclerosis (ALS) phenotyping is a challenging task due to its heterogeneous nature and low prevalence. In this paper, we introduce a data-driven approach to support the characterization of ALS phenotypes based on clinical data from a battery of examinations. A consensus clustering method is proposed to identify stable clusters across multiple random data sub-samples, with the objective of discovering whether the retrieved patients’ groups and related features align with clinical phenotypes and medical knowledge. Results suggest consistent profiles for bulbar onset ALS patients, driven by onset characteristics, whereas spinal onset ALS patients exhibit greater within-phenotype heterogeneity.

  • Website
    Google Scholar
    Open Access

    Safe and Efficient Social Navigation Through Explainable Safety Regions Based on Topological Features

    by Victor Toscano-Duran, Sara Narteni, Alberto Carlevaro, Jérôme Guzzi, Rocio Gonzalez-Diaz, Maurizio Mongelli

    The recent adoption of artificial intelligence (AI) in robotics has driven the development of algorithms that enable autonomous systems to adapt to complex social environments. In particular, safe and efficient social navigation is a key challenge, requiring AI not only to avoid collisions and deadlocks but also to interact intuitively and predictably with its surroundings. To date, methods based on probabilistic models and the generation of conformal safety regions have shown promising results in defining safety regions with a controlled margin of error, primarily relying on classification approaches and explicit rules to describe collision-free navigation conditions. This work extends the existing perspective by investigating how topological features can contribute to the creation of explainable safety regions in social navigation scenarios, enabling the classification and characterization of different simulation behaviors. Rather than relying on behaviors parameters to generate safety regions, we leverage topological features through topological data analysis. We first utilize global rule-based classification to provide interpretable characterizations of different simulation behaviors, distinguishing between safe (free of collisions) and unsafe scenarios based on topological properties. Next, we define safety regions, $$S_\varepsilon $$ S ε , representing zones in the topological feature space where collisions are avoided with a maximum classification error of $$\varepsilon $$ ε . These regions are constructed using adjustable SVM classifiers and order statistics, ensuring a robust and scalable decision boundary. To enhance interpretability, we extract local rules from these safety regions, ensuring that the decision-making process remains transparent and comprehensible. Initially, we generate safety regions that separate simulations with and without collisions, achieving higher accuracy than methods that do not incorporate topological features. This approach also provides a deeper and more intuitive understanding of robot interactions within a navigable space. We then extend our methodology to design safety regions that ensure efficient simulations (i.e., free of deadlocks). Finally, we integrate both aspects to obtain comprehensive safety regions that guarantee both collision-free and deadlock-free simulations, defining an overall compliant simulation space.

    Cited by 2
  • Website
    Google Scholar
    Open Access

    Uniform Manifold Approximation and Projection Filtering and Explainable Artificial Intelligence to Detect Adversarial Machine Learning

    by Achmed Samuel Koroma, Sara Narteni, Enrico Cambiaso, Maurizio Mongelli

    Adversarial machine learning exploits the vulnerabilities of artificial intelligence (AI) models by inducing malicious distortion in input data. Starting with the effect of adversarial methods on well-known MNIST and CIFAR-10 open datasets, this paper investigates the ability of Uniform Manifold Approximation and Projection (UMAP) in providing useful representations of both legitimate and malicious images and analyzes the attacks’ behavior under various conditions. By enabling the extraction of decision rules and the ranking of important features from classifiers such as decision trees, eXplainable AI (XAI) achieves zero false positives and negatives in detection through very simple if-then rules over UMAP variables. Several examples are reported in order to highlight attacks behaviour. The data availability statement details all code and data which is publicly available to offer support to reproducibility.

    Cited by 1
  • Website
    Google Scholar
    Open Access

    A novel score function for conformal prediction in rule-based binary classification

    by Sara Narteni, Alberto Carlevaro, Fabrizio Dabbene, Marco Muselli, Maurizio Mongelli

    Cited by 5
  • Website
    Google Scholar
    Open Access

    Explainable evaluation of generative adversarial networks for wearables data augmentation

    by Sara Narteni, Vanessa Orani, Enrico Ferrari, Damiano Verda, Enrico Cambiaso, Maurizio Mongelli

    Cited by 8
  • Website
    Google Scholar

    Ensuring Safe Social Navigation via Explainable Probabilistic and Conformal Safety Regions

    by Sara Narteni, Alberto Carlevaro, Jérôme Guzzi, Maurizio Mongelli

    Cited by 2
  • Website
    Google Scholar

    Application of the Representative Measure Approach to Assess the Reliability of Decision Trees in Dealing with Unseen Vehicle Collision Data

    by Javier Perera-Lago, Victor Toscano-Duran, Eduardo Paluzo-Hidalgo, Sara Narteni, Matteo Rucco

    Cited by 2
  • Website
    Google Scholar
    Open Access

    Application of the representative measure approach to assess the reliability of decision trees in dealing with unseen vehicle collision data

    by Javier Perera-Lago, Víctor Toscano-Durán, Eduardo Paluzo-Hidalgo, Sara Narteni, Matteo Rucco

    Machine learning algorithms are fundamental components of novel data-informed Artificial Intelligence architecture. In this domain, the imperative role of representative datasets is a cornerstone in shaping the trajectory of artificial intelligence (AI) development. Representative datasets are needed to train machine learning components properly. Proper training has multiple impacts: it reduces the final model's complexity, power, and uncertainties. In this paper, we investigate the reliability of the $\varepsilon$-representativeness method to assess the dataset similarity from a theoretical perspective for decision trees. We decided to focus on the family of decision trees because it includes a wide variety of models known to be explainable. Thus, in this paper, we provide a result guaranteeing that if two datasets are related by $\varepsilon$-representativeness, i.e., both of them have points closer than $\varepsilon$, then the predictions by the classic decision tree are similar. Experimentally, we have also tested that $\varepsilon$-representativeness presents a significant correlation with the ordering of the feature importance. Moreover, we extend the results experimentally in the context of unseen vehicle collision data for XGboost, a machine-learning component widely adopted for dealing with tabular data.

  • Website
    Google Scholar
    Open Access

    Explainable artificial intelligence for cough-related quality of life impairment prediction in asthmatic patients

    by Sara Narteni, Ilaria Baiardini, Fulvio Braido, Maurizio Mongelli

    Explainable Artificial Intelligence (XAI) is becoming a disruptive trend in healthcare, allowing for transparency and interpretability of autonomous decision-making. In this study, we present an innovative application of a rule-based classification model to identify the main causes of chronic cough-related quality of life (QoL) impairment in a cohort of asthmatic patients. The proposed approach first involves the design of a suitable symptoms questionnaire and the subsequent analyses via XAI. Specifically, feature ranking, derived from statistically validated decision rules, helped in automatically identifying the main factors influencing an impaired QoL: pharynx/larynx and upper airways when asthma is under control, and asthma itself and digestive trait when asthma is not controlled. Moreover, the obtained if-then rules identified specific thresholds on the symptoms associated to the impaired QoL. These results, by finding priorities among symptoms, may prove helpful in supporting physicians in the choice of the most adequate diagnostic/therapeutic plan.

    Cited by 6
  • Website
    Google Scholar

    Weighted Mutual Information for Out-Of-Distribution Detection

    by Giacomo De Bernardi, Sara Narteni, Enrico Cambiaso, Marco Muselli, Maurizio Mongelli

    Cited by 1
Show all