Dipartimento di Matematica e Informatica - Tesi di Dottorato

Permanent URI for this collectionhttps://lisa.unical.it/handle/10955/103

Questa collezione raccoglie le Tesi di Dottorato afferenti al Dipartimento di Matematica e Informatica dell'Università della Calabria.

Browse

Author: search.filters.author.Calimeri, FrancescoStart date: 2020

Search Results

Now showing 1 - 3 of 3
  • Thumbnail Image
    Item
    Design and Implementation of an ASP-based Stream Reasoner
    (Università della Calabria, 2023-07-04) Mastria, Elena; Calimeri, Francesco; Perri, Simona; Zangari, Jessica
    Stream Reasoning (SR) is a relatively young research field that evolved from Stream Processing (SP) more than a decade ago. It focuses on studying and developing advanced approaches and techniques for the continuous application of inference techniques to highly dynamic data streams. Data streams are (theoretically) infinite streams of information that dynamically change over time. These are generated by sources (e.g., sensors, devices, social networks, etc.) that monitor a physical or virtual environment, continuously reporting the relative state and changes. While SP aims at quickly processing data streams while answering continuous queries on their elements, SR tackles inferencing new information taking into account the content of data streams along with background knowledge on the application domain. Recently, SR has been studied in several fields, and has become more and more relevant in diverse application scenarios, such as IoT, Smart Cities, Emergency Management, and Healthcare. In such types of context, applications require complex query answering in a minimal amount of time. This amount is defined from the application domain at hand and is typically real-time (< 1 second) or near real-time(< 1 minute). Therefore, an SR system (i.e., stream reasoner) must be able to perform complex reasoning tasks while efficiently processing heterogeneous data streams together with large background knowledge bases. Different SR approaches have been proposed in fields such as Data Stream Management Systems (DSMS), Complex Event Processing (CEP), Semantic Web, and Knowledge Representation and Reasoning (KRR). Among declarative KRR paradigms, Answer Set Programming (ASP) is a well-established formalism developed in the area of logic programming and non-monotonic reasoning. Thanks to the availability of robust and efficient implementations, ASP is successfully employed outside of academia to implement several real-world applications. Recently, ASP gained attention as a basis for SR, and significant steps in this direction have been taken. Several ASP-based solutions have been proposed: some combining SP and ASP implementations into a single engine, others natively extending ASP with SR constructs. However, existing ASP-based stream reasoners appear not mature enough concerning the desirable requirements for SR. This thesis focuses on designing and implementing a novel, reliable ASPbased stream reasoner. The main goal is to obtain a system featuring the following properties: (i) efficiently scale over real-world application domains; (ii) support a language that inherits the highly declarative nature and ease of use from ASP; (iii) easily extendable with new constructs that are relevant for practical SR scenarios. Therefore, we herein present the stream reasoner I-DLVsr. The input language is a straightforward extension of ASP with constructs to reason over data streams. The implementation relies on a tight interaction between two state-of-the-art solutions in ASP and SP: I2-DLV and Apache Flink, respectively. We tested I-DLV-sr on several real-world and synthetic domains to explore its capabilities in modeling SR scenarios and assess its performance. In the conducted experiments, the system obtained good results, proving the viability of the proposed approach and the robustness of the implementation herein presented.
  • Thumbnail Image
    Item
    Deep Learning and Graph Theory for Brain Connectivity Analysis in Multiple Sclerosis
    (Università della Calabria, 2020-01-16) Marzullo, Aldo; Leone, Nicola; Calimeri, Francesco; Terracina, Giorgio;
    Multiple sclerosis (MS) is a chronic disease of the central nervous system, leading cause of nontraumatic disability in young adults. MS is characterized by inflammation, demyelination and neurodegenrative pathological processes which cause a wide range of symptoms, including cognitive deficits and irreversible disability. Concerning the diagnosis of the disease, the introduction of Magnetic Resonance Imaging (MRI) has constituted an important revolution in the last 30 years. Furthermore, advanced MRI techniques, such as brain volumetry, magnetization transfer imaging (MTI) and diffusion-tensor imaging (DTI) are nowadays the main tools for detecting alterations outside visible brain lesions and contributed to our understanding of the pathological mechanisms occurring in normal appearing white matter. In particular, new approaches based on the representation of MR images of the brain as graph have been used to study and quantify damages in the brain white matter network, achieving promising results. In the last decade, novel deep learning based approaches have been used for studying social networks, and recently opened new perspectives in neuroscience for the study of functional and structural brain connectivity. Due to their effectiveness in analyzing large amount of data, detecting latent patterns and establishing functional relationships between input and output, these artificial intelligence techniques have gained particular attention in the scientific community and is nowadays widely applied in many context, including computer vision, speech recognition, medical diagnosis, among others. In this work, deep learning methods were developed to support biomedical image analysis, in particular for the classification and the characterization of MS patients based on structural connectivity information. Graph theory, indeed, constitutes a sensitive tool to analyze the brain networks and can be combined with novel deep learning techniques to detect latent structural properties useful to investigate the progression of the disease. In the first part of this manuscript, an overview of the state of the art will be given. We will focus our analysis on studies showing the interest of DTI for WM characterization in MS. An overview of the main deep learning techniques will be also provided, along with examples of application in the biomedical domain. In a second part, two deep learning approaches will be proposed, for the generation of new, unseen, MRI slices of the human brain and for the automatic detection of the optic disc in retinal fundus images. In the third part, graph-based deep learning techniques will be applied to the study of brain structural connectivity of MS patients. Graph Neural Network methods to classify MS patients in their respective clinical profiles were proposed with particular attention to the model interpretation, the identification of potentially relevant brain substructures, and to the investigation of the importance of local graph-derived metrics for the classification task. Semisupervised and unsupervised approaches were also investigated with the aim of reducing the human intervention in the pipeline.
  • Thumbnail Image
    Item
    Towards an effective and explainable AI: studies in the biomedical domain
    (Università della Calabria, 2021-07-05) Bruno, Pierangela; Greco, Gianluigi; Calimeri, Francesco
    Providing accurate diagnoses of diseases and maximizing the effectiveness of treatments requires, in general, complex analyses of many clinical, omics, and imaging data. Making a fruitful use of such data is not straightforward, as they need to be properly handled and processed in order to successfully perform medical diagnosis. This is why Artificial Intelligence (AI) is largely employed in the field. Indeed, in recent years, Machine Learning (ML), and in particular Deep Learning (DL), techniques emerged as powerful tools to perform specific disease detection and classification, thus providing significant support to clinical decisions. They gained a special attention in the scientific community, especially thanks to their ability in analyzing huge amounts of data, recognizing patterns, and discovering non-trivial functional relationships between input and output. However, such approaches suffer, in general, from the lack of proper means for interpreting the choices made by the learned models, especially in the case of DL ones. This work is based on both a theoretical and methodological study of AI techniques suitable for the biomedical domain; furthermore, we put a specific focus on the practical impact on the application and adaptation of such techniques to relevant domain. In this work, ML and DL approaches have been studied and proper methods have been developed to support (i) medical imaging diagnostic and computer-assisted surgery via detection, segmentation and classification of vessels and surgical tools in intra-operative images and videos (e.g., cine-angiography), and (ii) data-driven disease classification and prognosis prediction, through a combination of data reduction, data visualization and classification of high-dimensional clinical and omics data, to detect hidden structural properties useful to investigate the progression of the disease. In particular, we focus on defining a novel approach for automated assessment of pathological conditions, identifying latent relationships in different domains and supporting healthcare providers in finding the most appropriate preventive interventions and therapeutic strategies. Furthermore, we propose a study about the analysis of the internal processes performed by the artificial networks during classification tasks, with the aim to provide a AI-based model explainability. This manuscript is presented in four parts, each focusing on a special aspect of DL techniques and offering different examples of their application in the biomedical domain. In the first part we introduce clinical and omics data along with the popular processing methods to improve the analyses; we also provide an overview of the main DL techniques and approaches aimed at performing disease prediction and prevention and at identifying bio-markers via biomedical data and images. In the second part we describe how we applied DL techniques to perform the segmentation of vessels in the ilio-femoral images. Furthermore, we propose a combination of multi-instance segmentation network and optical flow to solve the multiinstance segmentation and detection tasks in endoscopic images. In the third part a combination of data reduction and data visualization techniques is proposed for the reduction of clinical and omics data and their visualization into images, with the aim of performing DL-based classification. Furthermore, we present a ML-based approach to develop a risk model for class prediction from high-dimensional gene expression data, for the purpose of identifying a subset of genes that may influence the survival rate of specific patients. Eventually, in the fourth part we provide a study on the behaviour of AI-based systems during classification tasks, such as image-based disease classification, which is a widely studied topic in the recent years; more in detail, we show how DL-based systems can be studied with the aim of identifying the most relevant elements involved in the training processes and validating the network’s decisions, and possibly the clinical treatment and recommendation.