Global ETD Search
Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.
Results
Showing 1 to 20 of 43 for “"Settore INFO-01/A - Informatica"”.
-
ADAPTIVE FRAMEWORKS FOR KNOWLEDGE EXTRACTION IN HETEROGENEOUS DATA ENVIRONMENTS
… data environments. It combines unsupervised information extraction with advanced representation learning techniques, incorporating external knowledge bases to enhance semantic understanding. SHIFT modular architecture provides seamless adaptation to different data modalities and domain …
-
DOMAIN KNOWLEDGE-GUIDED LEARNING FOR ROBUST MYOCARDIAL INFARCTION DETECTION FROM 12-LEAD ELECTROCARDIOGRAMS
Background: Myocardial infarction (MI) represents one of the leading causes of morbidity and mortality on a global scale. Diagnosis is primarily based on the interpretation of the 12-lead electrocardiogram (ECG) according to established clinical guidelines that specify alterations in ECG …
-
ASSISTIVE TECHNOLOGIES SUPPORTING BLIND AND LOW VISION PEOPLE DURING NAVIGATION
The thesis investigates navigation systems for blind and low vision people, proposing three main contributions. First, the thesis proposes two sonification techniques to provide guidance instructions to blind and low vision people during navigation. The proposed solutions are compared with a …
-
ONLINE LEARNING, UNIFORM CONVERGENCE, AND A THEORY OF INTERPRETABILITY
… stochastic feedback graphs without prior information on the distribution of the graphs. Additionally, we derive improved regret bounds for bandits with expert advice and explore the impact of intermediate observations in the delayed feedback setting, designing a meta-algorithm to achieve …
-
SUPPORTING COMPANIES IN THEIR DIGITAL TRANSITION TO SMART MANUFACTURING SYSTEMS
Industry 4.0 (I4.0), which is considered to be the fourth industrial revolution, is now a well-established concept. However, it presents significant challenges for several manufacturing sectors. Luxury fashion is a key example, showing two blocking factors. First, the need to keep not only design, …
-
DATA GOVERNANCE FRAMEWORK FOR ML-BASED, DATA-INTENSIVE DISTRIBUTED SYSTEMS
… an entropy-based metric ($M_H$) that quantifies information content retention. Then, we develop sliding window heuristic algorithms that address the NP-hard problem of optimal service selection by employing moving optimization windows that balance local and global objectives. Moreover, we provide …
-
LEARNING UNDER STRUCTURE AND UNCERTAINTY: ALGORITHMS FOR BANDIT AND ONLINE DECISION MAKING
… at each round the learner receives a question (information available prior to a decision), provides an answer (an action or prediction), and observes a feedback signal that may be partial, noisy, or structured. This iterative loop captures a wide range of sequential decision problems and serves …
-
A computer vision framework to transform produce waste into value for agricultural sustainability
L'abstract è presente nell'allegato / the abstract is in the attachment
-
Efficient Adaptation of Large Language Models in Natural Language Processing
… Language Processing (NLP) tasks, including Information Retrieval (IR). Despite their strong generalisation capabilities, LLMs still require domain- and task-specific fine-tuning to achieve competitive performance in highly specialised scenarios. LLMs exhibit some generalisation abilities, …
-
Decentralized and Intelligent Systems to Enhance Workplace Safety
Occupational injuries and illnesses continue to affect workers worldwide, resulting in severe consequences for the affected individuals, companies, and society in general. Despite initiatives to improve workplace safety and legislative efforts, the number of accidents still remains very high, …
-
Knowledge-aware Methods for Explainable Decision Support in Lifelong Learning
… resources, and the difficulty of supporting informed learning decisions at scale. While digital platforms provide unprecedented access to education, learners often face overwhelming choices and limited guidance while navigation. The increasing availability of learning data and technological …
-
Advancing Information Extraction with Large Language Models: The Role of Structured Understanding in Knowledge Management and AI Safety
Nowadays, most of the world’s information is produced in unstructured textual form. This vast amount of text represents an invaluable source of knowledge, yet it remains challenging for machines to interpret and transform into actionable insights. Information Extraction (IE) offers a promising …
-
Knowledge Engineering via Large Language Models
… text into structured, reusable, and queryable information. The central question guiding this work is how far the understanding capabilities of LLMs can automate the organization and retrieval of knowledge traditionally curated by human experts. The research explores two complementary strategies …
-
MITIGATING DATA SCARCITY CHALLENGES IN MEDICAL IMAGING ANALYSIS:ADVANCED LEARNING APPROACHES WITH EMPHASIS ON HEMOPHILIC ULTRASOUND IMAGES
Medical imaging plays a crucial role in hemophilia research and clinical practice, particularly in assessing joint health and bleeding events. Ultrasound (US) imaging is a fundamental tool in the diagnostic process and is currently used to identify when the joint recess is filled with synovial …
-
ON THE PROBABILISTIC MODELLING OF PAIN
Pain is a complex subjective experience encompassing sensory, affective, and cognitive dimensions. Evidence challenges the linear relationship between nociceptive activation and pain perception, revealing scenarios where pain is felt without nociceptive input or vice versa. This research is based …
-
THE CHALLENGE OF DOMAIN SHIFT IN REAL-WORLD ROBOTIC VISION: TOWARD SCALABLE, UNSUPERVISED, AND CLOUD-BASED ADAPTATION
Mobile robots are an emergent technology more and more present in contexts such as homes, offices, and hospitals to assist humans in daily life activities. Given the complexity of human-centric environments, robotic vision, namely computer vision embedded in mobile robots, has become an essential …
-
DISTRIBUTED AND DELAYED ONLINE LEARNING
This thesis investigates the design and analysis of distributed and delayed online learning algorithms. First, we introduce delayed online learning, where model updates rely on feedback arriving with variable delays. We study the online learning problem with curved losses and delayed feedback, …
-
TRUSTED RUNTIME ENVIRONMENTS FOR EMBEDDED SYSTEMS: FROM MEMORY PROTECTION TO SECURE VIRTUALIZATION
… and provides developers with clearer diagnostic information to support efficient patching. For temporal memory safety, a novel remote attestation protocol is presented to model heap state and detect use-after-free vulnerabilities. The approach relies on a precomputation analysis to identify a …
-
Efficient Neural Coding Under Resource Constraints: A Rate-Distortion Theory Perspective
L'abstract è presente nell'allegato / the abstract is in the attachment
Page 1 of 3