michele fraccaroli | Università degli Studi di Ferrara (original) (raw)

Uploads

Papers by michele fraccaroli

Medical & Biological Engineering & Computing

Recently, Artificial Intelligence (AI) and Machine Learning (ML) have been successfully applied t... more Recently, Artificial Intelligence (AI) and Machine Learning (ML) have been successfully applied to many domains of interest including medical diagnosis. Due to the availability of a large quantity of data, it is possible to build reliable AI systems that assist humans in making decisions. The recent Covid-19 pandemic quickly spread over the world causing serious health problems and severe economic and social damage. Computer scientists are actively working together with doctors on different ML models to diagnose Covid-19 patients using Computed Tomography (CT) scans and clinical data. In this work, we propose a neural-symbolic system that predicts if a Covid-19 patient arriving at the hospital will end in a critical condition. The proposed system relies on Deep 3D Convolutional Neural Networks (3D-CNNs) for analyzing lung CT scans of Covid-19 patients, Decision Trees (DTs) for predicting if a Covid-19 patient will eventually pass away by analyzing its clinical data, and a neural sys...

Electronic Proceedings in Theoretical Computer Science

Recent advances in neural-symbolic learning, such as Deep-ProbLog, extend probabilistic logic pro... more Recent advances in neural-symbolic learning, such as Deep-ProbLog, extend probabilistic logic programs with neural predicates. Like graphical models, these probabilistic logic programs define a probability distribution over possible worlds, for which inference is computationally hard. We propose Deep-StochLog, an alternative neural-symbolic framework based on stochastic definite clause grammars, a kind of stochastic logic program. More specifically, we introduce neural grammar rules into stochastic definite clause grammars to create a framework that can be trained end-to-end. We show that inference and learning in neural stochastic logic programming scale much better than for neural probabilistic logic programs. Furthermore, the experimental evaluation shows that DeepStochLog achieves state-of-the-art results on challenging neural-symbolic learning tasks.

2021 IEEE Symposium on Computers and Communications (ISCC), 2021

The role of Machine Learning (ML) in healthcare is based on the ability of a machine to analyse t... more The role of Machine Learning (ML) in healthcare is based on the ability of a machine to analyse the huge amounts of data available for each patient, like age, medical history, overall health status, test results, etc. With ML algorithms it is possible to learn models from data for the early identification of pathologies and their severity. Early identification is crucial to proceed as soon as possible with the necessary therapeutic actions. This work applies modern ML techniques to clinical data of either COVID-19 positive and COVID-19 negative patients with pulmonary complications, to learn mortality prediction models for both groups of patients, and compare results. We have focused on symbolic methods for building classifiers able to extract patterns from clinical data. This approach leads to predictive Artificial Intelligence (AI) systems working on medical data, and able to explain the reasons that lead the systems themselves to reach a certain conclusion.

Deep learning techniques play an increasingly important role in industrial and research environme... more Deep learning techniques play an increasingly important role in industrial and research environments due to their outstanding results. However, the large number of hyper-parameters to be set may lead to errors if they are set manually. The state-of-the-art hyper-parameters tuning methods are grid search, random search, and Bayesian Optimization. The first two methods are expensive because they try, respectively, all possible combinations and random combinations of hyper-parameters. Bayesian Optimization, instead, builds a surrogate model of the objective function, quantifies the uncertainty in the surrogate using Gaussian Process Regression and uses an acquisition function to decide where to sample the new set of hyper-parameters. This work faces the field of Hyper-Parameters Optimization (HPO). The aim is to improve Bayesian Optimization applied to Deep Neural Networks. For this goal, we build a new algorithm for evaluating and analyzing the results of the network on the training a...

Medical & Biological Engineering & Computing

Recently, Artificial Intelligence (AI) and Machine Learning (ML) have been successfully applied t... more Recently, Artificial Intelligence (AI) and Machine Learning (ML) have been successfully applied to many domains of interest including medical diagnosis. Due to the availability of a large quantity of data, it is possible to build reliable AI systems that assist humans in making decisions. The recent Covid-19 pandemic quickly spread over the world causing serious health problems and severe economic and social damage. Computer scientists are actively working together with doctors on different ML models to diagnose Covid-19 patients using Computed Tomography (CT) scans and clinical data. In this work, we propose a neural-symbolic system that predicts if a Covid-19 patient arriving at the hospital will end in a critical condition. The proposed system relies on Deep 3D Convolutional Neural Networks (3D-CNNs) for analyzing lung CT scans of Covid-19 patients, Decision Trees (DTs) for predicting if a Covid-19 patient will eventually pass away by analyzing its clinical data, and a neural sys...

Electronic Proceedings in Theoretical Computer Science

Recent advances in neural-symbolic learning, such as Deep-ProbLog, extend probabilistic logic pro... more Recent advances in neural-symbolic learning, such as Deep-ProbLog, extend probabilistic logic programs with neural predicates. Like graphical models, these probabilistic logic programs define a probability distribution over possible worlds, for which inference is computationally hard. We propose Deep-StochLog, an alternative neural-symbolic framework based on stochastic definite clause grammars, a kind of stochastic logic program. More specifically, we introduce neural grammar rules into stochastic definite clause grammars to create a framework that can be trained end-to-end. We show that inference and learning in neural stochastic logic programming scale much better than for neural probabilistic logic programs. Furthermore, the experimental evaluation shows that DeepStochLog achieves state-of-the-art results on challenging neural-symbolic learning tasks.

2021 IEEE Symposium on Computers and Communications (ISCC), 2021

The role of Machine Learning (ML) in healthcare is based on the ability of a machine to analyse t... more The role of Machine Learning (ML) in healthcare is based on the ability of a machine to analyse the huge amounts of data available for each patient, like age, medical history, overall health status, test results, etc. With ML algorithms it is possible to learn models from data for the early identification of pathologies and their severity. Early identification is crucial to proceed as soon as possible with the necessary therapeutic actions. This work applies modern ML techniques to clinical data of either COVID-19 positive and COVID-19 negative patients with pulmonary complications, to learn mortality prediction models for both groups of patients, and compare results. We have focused on symbolic methods for building classifiers able to extract patterns from clinical data. This approach leads to predictive Artificial Intelligence (AI) systems working on medical data, and able to explain the reasons that lead the systems themselves to reach a certain conclusion.

Deep learning techniques play an increasingly important role in industrial and research environme... more Deep learning techniques play an increasingly important role in industrial and research environments due to their outstanding results. However, the large number of hyper-parameters to be set may lead to errors if they are set manually. The state-of-the-art hyper-parameters tuning methods are grid search, random search, and Bayesian Optimization. The first two methods are expensive because they try, respectively, all possible combinations and random combinations of hyper-parameters. Bayesian Optimization, instead, builds a surrogate model of the objective function, quantifies the uncertainty in the surrogate using Gaussian Process Regression and uses an acquisition function to decide where to sample the new set of hyper-parameters. This work faces the field of Hyper-Parameters Optimization (HPO). The aim is to improve Bayesian Optimization applied to Deep Neural Networks. For this goal, we build a new algorithm for evaluating and analyzing the results of the network on the training a...