A5088120071- Semantic Web and Ontologies
- Privacy-Preserving Technologies in Data
- Natural Language Processing Techniques
- Data Quality and Management
- Topic Modeling
- Biomedical Text Mining and Ontologies
- Service-Oriented Architecture and Web Services
- Advanced Database Systems and Queries
- Internet Traffic Analysis and Secure E-voting
- Data Mining Algorithms and Applications
- Cryptography and Data Security
- Pediatric Urology and Nephrology Studies
- Ultrasound and Hyperthermia Applications
- Scientific Computing and Data Management
- Privacy, Security, and Data Protection
- Urological Disorders and Treatments
- Web Data Mining and Analysis
- Imbalanced Data Classification Techniques
- Data Management and Algorithms
- Recommender Systems and Techniques
- Wikis in Education and Collaboration
- Kidney Stones and Urolithiasis Treatments
- Advanced Clustering Algorithms Research
- Big Data and Business Intelligence
- Advanced Graph Neural Networks
Hôpital Edouard Herriot
2025
University of Cagliari
2013-2024
Vrije Universiteit Amsterdam
2019-2021
University of California, Irvine
2019-2021
Asia University
2019-2021
Sejong University
2021
Polytechnic University of Turin
2019
Nanjing University
2018
Azienda Ospedaliera San Camillo-Forlanini
2007-2013
Carlo Forlanini Hospital
2007-2013
Advances in information technology, and its use research, are increasing both the need for anonymized data risks of poor anonymization. We present a metric, δ-presence, that clearly links quality anonymization to risk posed by inadequate show existing techniques inappropriate situations where δ-presence is good metric (specifically, knowing an individual database poses privacy risk), algorithms effectively anonymizing meet δ-presence. The evaluated context real-world scenario, demonstrating...
Trajectory datasets are becoming more and popular due to the massive usage of GPS other location-based devices services. In this paper, we address privacy issues regarding identification individuals in static trajectory datasets. We provide protection by definig k-anonymity, meaning every released information refers at least k users/trajectories. propose a novel generalization-based approach that applies trajectories sequences general. also suggest use simple random reconstruction original...
In this paper we study when the disclosure of data mining results represents, per se, a threat to anonymity individuals recorded in analyzed database. The novelty our approach is that focus on an objective definition privacy compliance patterns without any reference preconceived knowledge what sensitive and not, basis rather intuitive realistic constraint should be guaranteed. particular, problem addressed here arises from possibility inferring output frequent itemset (i.e., set item-sets...
This work explores using Large Language Models (LLMs) to translate user preferences into energy optimization constraints for home appliances. We describe a task where natural language utterances are converted formal smart appliances, within the broader context of renewable community (REC) and in Italian scenario. evaluate effectiveness various LLMs currently available translating these resorting classical zero-shot, one-shot, few-shot learning settings, pilot dataset requests paired with...
A novel method is demonstrated that allows semantic and well-structured knowledge bases (such as DBpedia) to be easily queried directly from Wikipedia's pages. Using Swipe, naive users with no of RDF triples SPARQL can query DBpedia powerful questions such as: "Who are the U.S. presidents who took office when they were 55-year old or younger, during last 60 years", "Find town in California less than 10 thousand people". This accomplished by a Search Example (SBE) approach where user enter...
The process of discovering relevant patterns holding in a database, was first indicated as threat to database security by O' Leary [20]. Since then, many different approaches for knowledge hiding have emerged over the years, mainly context association rules and frequent itemsets mining. Following real-world data applications demands, this paper we shift, problem contexts where both arid extracted sequential structure. We provide statement, some theoretical issues including NP-hardness...
Ontologies have been widely used in numerous and varied applications, e.g. to support data modeling, information integration, knowledge management. With the increasing size of ontologies, ontology understanding, which is playing an important role different tasks, becoming more difficult. Consequently, summarization, as a way distill key from generate abridged version facilitate better getting growing attention. In this survey paper we review existing summarization techniques focus mainly on...
Ensuring the security of personal accounts has become a key concern due to widespread password attack techniques. Although passwords are primary defense against unauthorized access, practice reusing easy-to-remember increases risks for people. Traditional methods evaluating strength often insufficient since they overlook public information that users frequently share on social networks. In addition, while tend limit access their data single profiles, is unintentionally shared across multiple...
Abstract In the generic setting of objects × attributes matrix data analysis, co‐clustering appears as an interesting unsupervised mining method. A task provides a bi‐partition made co‐clusters: each co‐cluster is group associated to and these associations can support expert interpretations. Many constrained clustering algorithms have been proposed exploit domain knowledge improve partition relevancy in mono‐dimensional case (e.g. using must‐link cannot‐link constraints on one two...
This study aimed at estimating the prevalence of osteoporosis and osteopenia in a Sardinian isolated population using hand quantitative ultrasound investigating associated factors. The authors utilized subset data from large population-based epidemiologic survey carried out Ogliastra region Sardinia between 2003 2008. sample consists 6,326 men women aged ≥30 years, who underwent phalanges, bioelectrical impedance, anthropometric measurements, blood tests, standardized questionnaire...