We introduce QuaterGCN, a spectral Graph Convolutional Network (GCN) with quaternion-valued weights at whose core lies the Quaternionic Laplacian, a quaternion-valued Laplacian matrix by whose proposal we generalize two widely-used Laplacian matrices: the classical Laplacian (defined for undirected graphs) and the complex-valued Sign-Magnetic Laplacian (proposed within the spectral GCN SigMaNet to handle digraphs with weights of arbitrary sign). In addition to its generality, QuaterGCN is the only Laplacian to completely preserve the (di)graph topology that we are aware of, as it can handle graphs and digraphs containing antiparallel pairs of edges (digons) of different weight without reducing them to a single (directed or undirected) edge as done by other Laplacians. Experimental results show the superior performance of QuaterGCN compared to other state-of-the-art GCNs, particularly in scenarios where the information the digons carry is crucial to successfully address the task at hand.

This paper introduces SigMaNet, a generalized Graph Convolutional Network (GCN) capable of handling both undirected and directed graphs with weights not restricted in sign nor magnitude. The cornerstone of SigMaNet is the Sign-Magnetic Laplacian (LSM), a new Laplacian matrix that we introduce ex novo in this work. LSM allows us to bridge a gap in the current literature by extending the theory of spectral GCNs to (directed) graphs with both positive and negative weights. LSM exhibits several desirable properties not enjoyed by other Laplacian matrices on which several state-of-the-art architectures are based, among which encoding the edge direction and weight in a clear and natural way that is not negatively affected by the weight magnitude. LSM is also completely parameter-free, which is not the case of other Laplacian operators such as, e.g., the Magnetic Laplacian. The versatility and the performance of our proposed approach is amply demonstrated via computational experiments. Indeed, our results show that, for at least a metric, SigMaNet achieves the best performance in 15 out of 21 cases and either the first- or second-best performance in 21 cases out of 21, even when compared to architectures that are either more complex or that, due to being designed for a narrower class of graphs, should---but do not---achieve a better performance.

Many decisions in transportation management must be made before the uncertainty of possible traffic conditions is revealed. When making decisions with lasting implications over a medium to long timeframe, it is essential to consider not only the most probable scenario, possibly obtained through a forecasting model but also a range of potential outcomes. This approach allows for effective risk mitigation across a spectrum of scenarios, including less probable ones, and enhances the resilience of planning strategies. In this paper, we demonstrate the development of a generative model capable of learning the multivariate joint probability distribution of link speeds on a road network, using real data collected from sensors. The proposed model has shown its ability to generate scenarios that preserve correlations among variables, while producing samples that faithfully represent the empirical marginal distributions. To further enhance the performance of our Generative Adversarial Network (GAN) model, we employed a Variational AutoEncoder (VAE) for pre-training the generator network. Experimental results, conducted on three distinct benchmark datasets, highlight the potential of the proposed model in generating new scenario samples of multivariate variables. The Wasserstein distance between the generated distribution and the real data, confirms the good performance of our model with respect to state of the art models, based on copulae.

Modelling infectious disease spreading is crucial for planning effective containment measures, as shown in the COVID-19 pandemic. The effectiveness of planned measures can also be measured regarding saved lives and economic resources. Therefore, introducing methods able to model the evolution and the impact of measures, as well as planning tailored and updated measures, is a crucial step. Existing models for spreading modelling belong to two main classes: (i) compartmental models based on ordinary differential equations and (ii) contact-based models based on a contact structure using an underlining layer to simulate diffusion. Nevertheless, none of these methods can leverage the high computational power of artificial intelligence and deep learning. We propose a novel framework for simulating and analysing disease progression for these methods. The framework is based on the multiscale simulation of the spreading based on using a multiscale contact model built on top of a diffusion model customised by the user. The evolution of the spreading, modelled as a graph with attributed nodes, is then mapped into a latent space through graph embedding. Finally, deep learning models are used in the latent space to analyse and forecast methods without running expensive computational simulations of the contact-based model.

Breast cancer is the second leading cause of cancer-related death after lung cancer in women. Early detection of breast cancer in X-ray mammography is believed to have effectively reduced the mortality rate since 1989. However, a relatively high false positive rate and a low specificity in mammography technology still exist. In this work, a computer-aided automatic mammogram analysis system is proposed to process the mammogram images and automatically discriminate them as either normal or cancerous, consisting of three consecutive image processing, feature selection, and image classification stages. In designing the system, the discrete wavelet transforms (Daubechies 2, Daubechies 4, and Biorthogonal 6.8) and the Fourier cosine transform were first used to parse the mammogram images and extract statistical features. Then, an entropy-based feature selection method was implemented to reduce the number of features. Finally, different pattern recognition methods (including the Back-propagation Network, the Linear Discriminant Analysis, and the Naive Bayes Classifier) and a voting classification scheme were employed. The performance of each classification strategy was evaluated for sensitivity, specificity, and accuracy and for general performance using the Receiver Operating Curve. Our method is validated on the dataset from the Eastern Health in Newfoundland and Labrador of Canada. The experimental results demonstrated that the proposed automatic mammogram analysis system could effectively improve the classification performances.

Artificial intelligence (AI)-based decision-making systems are employed nowadays in an ever growing number of online as well as offline services-some of great importance. Depending on sophisticated learning algorithms and available data, these systems are increasingly becoming automated and data-driven. However, these systems can impact individuals and communities with ethical or legal consequences. Numerous approaches have therefore been proposed to develop decision-making systems that are discrimination-conscious by-design. However, these methods assume the underlying data distribution is stationary without drift, which is counterfactual in many realworld applications. In addition, their focus has been largely on minimizing discrimination while maximizing prediction performance without necessary flexibility in customizing the tradeoff according to different applications. To this end, we propose a learning algorithm for fair classification that also adapts to evolving data streams and further allows for a flexible control on the degree of accuracy and fairness. The positive results on a set of discriminated and non-stationary data streams demonstrate the effectiveness and flexibility of this approach.

Accountability in the workplace is critically important and remains a challenging problem, especially with respect to workplace safety management. In this paper, we introduce a novel notion, the Internet of Responsibilities, for accountability management. Our method sorts through the list of responsibilities with respect to hazardous positions. The positions are interconnected using directed acyclic graphs (DAGs) indicating the hierarchy of responsibilities in the organization. In addition, the system detects and collects responsibilities, and represents risk areas in terms of the positions of the responsibility nodes. Finally, an automatic reminder and assignment system is used to enforce a strict responsibility control without human intervention. Using blockchain technology, we further extend our system with the capability to store, recover and encrypt responsibility data. We show that through the application of the Internet of Responsibility network model driven by Big Data, enterprise and government agencies can attain a highly secured and safe workplace. Therefore, our model offers a combination of interconnected responsibilities, accountability, monitoring, and safety which is crucial for the protection of employees and the success of organizations.

This work stems from the Italian project H-CIM (Health-Care Intelligent Monitoring), aimed at developing a wearable sensor data streams based home-monitoring system to support self-rehabilitation of elderly outpatients. Different from the pervasive data stream applications, which are always accompanied by the evolution of unstable class concepts, this project requires stable standard and personalized rehabilitation exercises patterns be provided to assess outpatient's self-therapy progress at home. In this designed pipeline, the representation sequences of the personal standard rehabilitation exercises in wearable sensor streams is therefore first benchmarked, then an assessment system which integrates multistage data processing and analyzing is proposed to enable elders to manage their own rehabilitation progress properly. The system proved to be an effective tool for supporting compliance monitoring and personalized self-rehabilitation; it is currently under further development within the Italian project Home-IoT, with the aim to become a more general data stream analytics service, not only devoted to rehabilitation exercises assessment.

Sentiment Analysis is a broad task that involves the analysis of various aspect of the natural language text.However, most of the approaches in the state of the art usually investigate independently each aspect, i.e.Subjectivity Classification, Sentiment Polarity Classification, Emotion Recognition, Irony Detection.In this paper we present a Multi-View Sentiment Corpus (MVSC), which comprises 3000 English microblog posts related the movie domain.Three independent annotators manually labelled MVSC, following a broad annotation schema about different aspects that can be grasped from natural language text coming from social networks.The contribution is therefore a corpus that comprises five different views for each message, i.e. subjective/objective, sentiment polarity, implicit/explicit, irony, emotion.In order to allow a more detailed investigation on the human labelling behaviour, we provide the annotations of each human annotator involved.

Real world applications of machine learning in natural language processing can span many different domains and usually require a huge effort for the annotation of domain specific training data. For this reason, domain adaptation techniques have gained a lot of attention in the last years. In order to derive an effective domain adaptation, a good feature representation across domains is crucial as well as the generalisation ability of the predictive model. In this paper we address the problem of domain adaptation for sentiment classification by combining deep learning, for acquiring a cross-domain high-level feature representation, and ensemble methods, for reducing the cross-domain generalization error. The proposed adaptation framework has been evaluated on a benchmark dataset composed of reviews of four different Amazon category of products, significantly outperforming the state of the art methods.

The automatic detection of sarcasm and irony in user generated contents is one of the most challenging task of Natural Language Processing. In this paper we address this problem by introducing Bayesian Model Averaging (BMA), an ensemble approach to take into account several classifiers according to their reliabilities and their marginal probability predictions. The impact of the most used expressive signals (pragmatic particles and POS tags) have been evaluated in baseline models (traditional classifiers and majority voting) as well as in the proposed BMA approach. Experimental results highlight two main findings: (1) not all the features are equally able to characterize sarcasm and irony and (2) BMA not only outperforms traditional state of the art models, but is also able to ensure notable generalization capabilities both on ironic and sarcastic text.

BACKGROUND: The complexity of biological data related to the genetic origins of tumour cells, originates significant challenges to glean valuable knowledge that can be used to predict therapeutic responses. In order to discover a link between gene expression profiles and drug responses, a computational framework based on Consensus p-Median clustering is proposed. The main goal is to simultaneously predict (in silico) anticancer responses by extracting common patterns among tumour cell lines, selecting genes that could potentially explain the therapy outcome and finally learning a probabilistic model able to predict the therapeutic responses. RESULTS: The experimental investigation performed on the NCI60 dataset highlights three main findings: (1) Consensus p-Median is able to create groups of cell lines that are highly correlated both in terms of gene expression and drug response; (2) from a biological point of view, the proposed approach enables the selection of genes that are strongly involved in several cancer processes; (3) the final prediction of drug responses, built upon Consensus p-Median and the selected genes, represents a promising step for predicting potential useful drugs. CONCLUSION: The proposed learning framework represents a promising approach predicting drug response in tumour cells.

The huge amount of textual data on the Web has grown in the last few years rapidly creating unique contents of massive dimension. In a decision making context, one of the most relevant tasks is polarity classification of a text source, which is usually performed through supervised learning methods. Most of the existing approaches select the best classification model leading to over-confident decisions that do not take into account the inherent uncertainty of the natural language. In this paper, we pursue the paradigm of ensemble learning to reduce the noise sensitivity related to language ambiguity and therefore to provide a more accurate prediction of polarity. The proposed ensemble method is based on Bayesian Model Averaging, where both uncertainty and reliability of each single model are taken into account. We address the classifier selection problem by proposing a greedy approach that evaluates the contribution of each model with respect to the ensemble. Experimental results on gold standard datasets show that the proposed approach outperforms both traditional classification and ensemble methods.

In the last decade, new approaches focused on modeling uncertainty over complex relational data have been developed. In this paper, one of the most promising of such approaches, known as probabilistic relational model (PRM), has been investigated and extended in order to measure and include semantic relationships for addressing web page classification problems. Experimental results show the potential of the proposed method of capturing the "strength" of existing relationships (links) and the capacity of including this information into the probability model.

This paper deals with a wireless pervasive communication system to support advanced healthcare applications. The proposed system is based on an ad hoc interaction of mobile body sensor networks with independent wireless sensor networks already deployed within the environments in order to allow a continuous and context aware health monitoring for patients along their daily life scenarios with an unprecedented precision and flexibility of sensing. After an accurate protocol characterization, simulation results are provided, underlining remarkable performance with respect to existing solutions, for different mobility models and node density values.

Automatically assessing the value of bioavailability from the chemical structure of a molecule is a very important issue in biomedicine and pharmacology. In this paper, we present an empirical study of some well known Machine Learning techniques, including various versions of Genetic Programming, which have been trained to this aim using a dataset of molecules with known bioavailability. Genetic Programming has proven the most promising technique among the ones that have been considered both from the point of view of the accurateness of the solutions proposed, of the generalization capabilities and of the correlation between predicted data and correct ones. Our work represents a first answer to the demand for quantitative bioavailability estimation methods proposed in literature, since the previous contributions focus on the classification of molecules into classes with similar bioavailability.