Francesca Mangili

• Politecnico di Milano

Federated learning leverages data across institutions to improve clinical discovery while complying with data-sharing restrictions and protecting patient privacy. As the evolution of biobanks in genetics and systems biology has proved, accessing more extensive and varied data pools leads to a faster and more robust exploration and translation of re...

In recent years, the emphasis on computational thinking (CT) has intensified as an effect of accelerated digitalisation. While most researchers are concentrating on defining CT and developing tools for its instruction and assessment, we focus on the characteristics of computational thinking problems (CTPs)- activities requiring CT to be solved-and...

Single-cell sequencing provides rich information; however, its clinical use is limited due to high costs and complex data output. Here, we present a protocol for extracting single-cell-related information from bulk RNA-sequencing (RNA-seq) data using the pathway-level information extractor (PLIER) algorithm. We describe the steps for extracting sin...

This paper addresses the incorporation of problem decomposition skills as an important component of computational thinking (CT) in K-12 computer science (CS) education. Despite the growing integration of CS in schools, there is a lack of consensus on the precise definition of CT in general and decomposition in particular. While decomposition is com...

We present Flotta, a Federated Learning framework designed to train machine learning models on sensitive data distributed across a multi-party consortium conducting research in contexts requiring high levels of security, such as the biomedical field. Flotta is a Python package, inspired in several aspects by Apache Spark, which provides both flexib...

Directed graphical models such as Bayesian nets are often used to implement intelligent tutoring systems able to interact in real-time with learners in a purely automatic way. When coping with such models, keeping a bound on the number of parameters might be important for multiple reasons. First, as these models are typically based on expert knowle...

In modern and personalised education, there is a growing interest in developing learners' competencies and accurately assessing them. In a previous work, we proposed a procedure for deriving a learner model for automatic skill assessment from a task-specific competence rubric, thus simplifying the implementation of automated assessment tools. The p...

The field of computational thinking education has grown in recent years as researchers and educators have sought to develop and assess students' computational thinking abilities. While much of the research in this area has focused on defining computational thinking, the competencies it involves and how to assess them in teaching and learning contex...

In modern and personalised education, there is a growing interest in developing learners’ competencies and accurately assessing them. In a previous work, we proposed a procedure for deriving a learner model for automatic skill assessment from a task-specific competence rubric, thus simplifying the implementation of automated assessment tools. The p...

In the effort to counteract problems associated with the current carbon intensive transport system, app-based tools persuading mobility behaviour change have emerged worldwide. Most of such apps adopt a gamified approach and motivate behaviour change through external extrinsic motivational factors such as real-life prizes, that are attributed based...

Automatic assessment of learner competencies is a fundamental task in intelligent tutoring systems. An assessment rubric typically and effectively describes relevant competencies and competence levels. This paper presents an approach to deriving a learner model directly from an assessment rubric defining some (partial) ordering of competence levels...

Directed graphical models such as Bayesian nets are often used to implement intelligent tutoring systems able to interact in real-time with learners in a purely automatic way. When coping with such models, keeping a bound on the number of parameters might be important for multiple reasons. First, as these models are typically based on expert knowle...

We introduce ADAPQUEST, a software tool written in Java for the development of adaptive questionnaires based on Bayesian networks. Adaptiveness is intended here as the dynamical choice of the question sequence on the basis of an evolving model of the skill level of the test taker. Bayesian networks offer a flexible and highly interpretable framewor...

A test is adaptive when the sequence and number of questions is dynamically tuned on the basis of the estimated skills of the taker. Graphical models, such as Bayesian networks, are used for adaptive tests as they allow to model the uncertainty about the questions and the skills in an explainable fashion, especially when coping with multiple skills...

A test is adaptive when its sequence and number of questions is dynamically tuned on the basis of the estimated skills of the taker. Graphical models, such as Bayesian networks, are used for adaptive tests as they allow to model the uncertainty about the questions and the skills in an explainable fashion, especially when coping with multiple skills...

We present a Bayesian approach to conversational recommender systems. After any interaction with the user, a probability mass function over the items is updated by the system. The conversational feature corresponds to a sequential discovery of the user preferences based on questions. Information-theoretic criteria are used to optimally shape the in...

We present a conversational recommendation system based on a Bayesian approach. A probability mass function over the items is updated after any interaction with the user, with information-theoretic criteria optimally shaping the interaction and deciding when the conversation should be terminated and the most probable item consequently recommended....

The present urban transportation system, mostly tailored for cars, has long shown its limitations. In many urban areas, public transportation and soft mobility would be able to effectively satisfy many travel needs. However, they tend to be neglected, due to a deep-rooted car dependency. How can we encourage people to make sustainable mobility choi...

Nowadays, most people carry around a powerful smartphone which is well suited to constantly monitor the location and sometimes even the activity of its user. This makes tracking prevalent and leads to a large number of projects concerned with trajectory data. One area of particular interest is transport and mobility, where data is important for urb...

Due to the current diffusion of Smartphones and the always increasing quality and availability of sensors, travel data collected by Smartphones have become a fundamental source of information about mobility choices and transport usage. The little effort required to users in the data collection process, makes automatic Smartphone-based mobility trac...

Cities seek to improve alternatives to car to counteract problems associated with traffc and carbon-intensive lifestyles. Novel tools that exploit ICTs to persuade mobility behaviour change are emerging as effective supports for existing structural and regulatory tools. For instance, in Bellinzona a living lab was created to co-design with citizens...

Cities seek to improve alternatives to car to counteract problems associated with traffic and carbon-intensive lifestyles. Novel tools that exploit ICTs to persuade mobility behaviour change are emerging as effective supports for existing structural and regulatory tools. For instance, in Bellinzona a living lab was created to co-design with citizen...

Nowadays, most people own a smartphone which is well suited to constantly record the movement of its user. One use of the gathered mobility data is to provide users with feedback and suggestions for personal behavior change. Such eco-feedback on mobility patterns may stimulate users to adopt more energy-efficient mobility choices. In this paper, we...

We propose a new approach for the statistical comparison of algorithms which have been cross-validated on multiple data sets. It is a Bayesian hierarchical method; it draws inferences on single and on multiple datasets taking into account the mean and the variability of the cross-validation results. It is able to detect equivalent classifiers and t...

GoEco! is one of several smartphone applications that perform automatic mobility tracking. In contrast to many others, it uses the tracked movement data to compute possible behavioral improvements of its users, and provides this assessment as eco-feedback in various forms. These include booklets detailing user journeys and possible alternatives in...

GoEco! is one of several smartphone applications that perform automatic mobility tracking. In contrast to many others, it uses the tracked movement data to compute possible behavioral improvements of its users, and provides this assessment as eco-feedback in various forms. These include booklets detailing user journeys and possible alternatives in...

An adaptive test is a computer-based testing technique which adjusts the sequence of questions on the basis of the estimated ability level of the test taker. We suggest the use of credal networks, a generalization of Bayesian networks based on sets of probability mass functions, to implement adaptive tests exploiting the knowledge of the test devel...

Background and aims: According to the existing literature, musicians are at risk to experience a range of musculoskeletal painful conditions. Recently, digital technology has been developed to investigate pain location and pain extent. The aim of this study was to describe pain location and pain extent in musicians using a digital method for pain...

We develop a novel prognostic method for estimating the Remaining Useful Life (RUL) of industrial equipment and its uncertainty. The novelty of the work is the combined use of a fuzzy similarity method for the RUL prediction and of Belief Function Theory for uncertainty treatment. This latter allows estimating the uncertainty affecting the RUL pred...

Usually one compares the accuracy of two competing classifiers via null hypothesis significance tests (nhst). Yet the nhst tests suffer from important shortcomings, which can be overcome by switching to Bayesian hypothesis testing. We propose a Bayesian hierarchical model which jointly analyzes the cross-validation results obtained by two classifie...

The project GoEco! takes advantage of the wide availability of smartphones, in order to overcome the traditional awareness-raising approach used to foster sustainable mobility and exploit eco-feedback, social norms and peer pressure elements in an ICT-based motivation system. In particular, it uses a smartphone app to analyze how we can encourage p...

The large interest in analyzing one's own fitness led to the development of more and more powerful smartphone applications. Most are capable of tracking a user's position and mode of locomotion, data that do not only reflect personal health, but also mobility choices. A large field of research is concerned with mobility analysis and planning for a...

This paper proposes a prior near-ignorance model for regression based on a set of Gaussian Processes (GP). GPs are natural prior distributions for Bayesian regression. They offer a great modeling flexibility and have found widespread application in many regression problems. However, a GP requires the prior elicitation of its mean function, which re...

Most hypothesis testing in machine learning is done using the frequentist null-hypothesis significance test, which has severe drawbacks. We review recent Bayesian tests which overcome the drawbacks of the frequentist ones.

We present a robust Dirichlet process for estimating survival functions from samples with right-censored data. It adopts a prior near-ignorance approach to avoid almost any assumption about the distribution of the population lifetimes, as well as the need of eliciting an infinite dimensional parameter (in case of lack of prior information), as it h...

The statistical comparison of multiple algorithms over multiple data sets is fundamental in machine learning. This is typically carried out by the Friedman test. When the Friedman test rejects the null hypothesis, multiple comparisons are carried out to establish which are the significant differences among algorithms. The multiple comparisons are u...

In this work, we consider two prognostic approaches for the prediction of the Remaining Useful Life (RUL) of degrading equipment. The first approach is based on Gaussian Process Regression (GPR) and provides the probability distribution of the equipment RUL; the second approach adopts a Similarity-Based Regression (SBR) method for the RUL predictio...

Advanced diagnostics and prognostics tools are expected to play an important role in ensuring safe and long term operation in nuclear power plants. In this context, we use Gaussian Process Regression (GPR) to build a stochastic model of the equipment degradation evolution and apply it for prognostics. GPR is a probabilistic technique for non-linear...

The aim of this paper is to derive new near-ignorance models on the probability simplex, which do not directly involve the Dirichlet distribution and, thus, are alternative to the Imprecise Dirichlet Model (IDM). We focus our investigation on a particular class of distributions on the simplex which is known as the class of Normalized Infinitely Div...

In offshore oil platforms, choke valve erosion is a major issue. An indicator of the choke valve health state is the valve flow coefficient, which is a function of measured and allocated parameters. The allocated parameters are typically provided by a physics-based model which has been proved to be inaccurate for some operating conditions. As a con...

The Dirichlet process (DP) is one of the most popular Bayesian nonparametric models. An open problem with the DP is how to choose its infinite dimensional parameter (base measure) in case of lack of prior information. In this work we present the Imprecise DP (IDP) -- a prior near-ignorance DP-based model that does not require any choice of this pro...

Bayesian methods are ubiquitous in machine learning. Nevertheless, the analysis of empirical results is typically performed by frequentist tests. This implies dealing with null hypothesis significance tests and p-values, even though the shortcomings of such methods are well known. We propose a nonparametric Bayesian version of the Wilcoxon signed-r...

This paper considers the problem of erosion in choke valves used on offshore oil platforms. A parameter commonly used to assess the valve erosion state is the flow coefficient, which can be analytically calculated as a function of both measured and allocated parameters. Since the allocated parameter estimation is unreliable, the obtained evaluation...

In this work, we consider two practical situations with different information available, concerning the prediction of the Remaining Useful Life (RUL) of a creeping turbine blade for which a sequence of observations of the creep strain level is available. In the first case considered, we have available a stochastic model of the creep growth process...

This paper presents a similarity-based approach for the prediction of the Remaining Useful Life (RUL) of sea water filters placed upstream the heat exchangers of a nuclear reactor condenser. The prognostic approach is developed considering a library of reference degradation trajectories containing parameter observations taken from a set of similar...

In practical industrial applications, different prognostic approaches can be used depending on the information available for the model development. In this paper, we consider three different cases: (1) a physics-based model of the degradation process is available; (2) a set of degradation observations measured on components similar to the one of in...

We look at different prognostic approaches and the way of quantifying confidence in equipment Remaining Useful Life (RUL) prediction. More specifically, we consider: (1) a particle filtering scheme, based on a physics-based model of the degradation process; (2) a bootstrapped ensemble of empirical models trained on a set of degradation observations...

The safety of nuclear power plants can be enhanced, and the costs of operation and maintenance reduced, by means of prognostic and health management systems which enable detecting, diagnosing, predicting, and proactively managing the equipment degradation toward failure. We propose a prognostic method which predicts the Remaining Useful Life (RUL)...

The problem of predicting the Remaining Useful Life (RUL) of a creeping turbine blade is considered in this work. We assume to have a sequence of direct measurements of the blade creep strain; failure is declared with respect to a threshold value of maximum creep strain, beyond which the blade cracks. An ensemble of bootstrapped models is developed...

The valve flow coefficient is commonly used as a parameter to assess the erosion state of choke valves in offshore oil platforms. In particular, the difference between the theoretical value of the valve flow coefficient and its actual value calculated during operation is retained as the valve health indicator. The actual valve flow coefficient is a...

The oil and gas industry is constantly trying to improve the quality of their operations. The focus is put on developing and demonstrating technology, methods and work processes related to the monitoring of equipment conditions and performance to ensure optimal performance and maintenance of critical Structure, System or Components (SSCs). An ident...

With the hundreds of signal measurements made in a nuclear power plant, the cost of sensor maintenance has become significant and the effects of sensor failures substantial, with lost power production and lost revenues for the operating utility. In this respect, continuous and effective monitoring of sensor performance reduces unnecessary maintenan...

To efficiently control a process, accurate sensor measurements must be provided of the signals used by the controller to decide which actions to actuate in order to maintain the system in the desired conditions. Noisy or faulty sensors must, then, be promptly detected and their signals corrected in order to avoid wrong control decisions. In this wo...

Sensors are placed at various locations in a production plant to monitor the state of its components and accordingly operate its control and protection. For the plant state monitoring to be effective, the sensors themselves must be monitored for detecting anomalies in their functioning and for reconstructing the correct values of the signals measur...