A5030929146- Semantic Web and Ontologies
- Business Process Modeling and Analysis
- Service-Oriented Architecture and Web Services
- Big Data and Business Intelligence
- Advanced Database Systems and Queries
- Data Quality and Management
- Software System Performance and Reliability
- Scientific Computing and Data Management
- Data Stream Mining Techniques
- Data Management and Algorithms
- Context-Aware Activity Recognition Systems
- Complex Network Analysis Techniques
- Access Control and Trust
- Network Security and Intrusion Detection
- Cloud Computing and Resource Management
- Recommender Systems and Techniques
- Time Series Analysis and Forecasting
- Software Engineering Techniques and Practices
- Peer-to-Peer Network Technologies
- IoT and Edge/Fog Computing
- Personal Information Management and User Behavior
- Topic Modeling
- Innovative Approaches in Technology and Social Development
- Web Data Mining and Analysis
- Opinion Dynamics and Social Influence
University of Milan
2015-2024
Khalifa University of Science and Technology
2018-2023
University of Trieste
2023
RWTH Aachen University
2023
Consorzio Interuniversitario Nazionale per l'Informatica
2017-2022
Weatherford College
2021
Flint Institute Of Arts
2021
Urban planning Institute of the Republic of Slovenia
2021
Joint Programming Initiative Urban Europe
2021
Universidade Lusófona
2021
Big Data domain is one of the most promising ICT sectors with substantial expectations both on side market growing and design shift in area data storage managment analytics. However, today, level complexity achieved lack standardisation management architectures represent a huge barrier towards adoption execution analytics especially for those organizations SMEs not including sufficient amount competences knowledge. The full potential Analytics (BDA) can be unleashed only through definition...
Encoding methods are employed across several process mining tasks, including predictive monitoring, anomalous case detection, trace clustering, etc. These usually performed as preprocessing steps and responsible for mapping complex event data information into a numerical feature space. Most papers choose existing encoding arbitrarily or employ strategy based on expert domain knowledge. Moreover, by using their default parameters without evaluating other options. This practice can lead to...
The Big Data revolution promises to build a data-driven ecosystem where better decisions are supported by enhanced analytics and data management.However, major hurdles still need be overcome on the road that leads commoditization wide adoption of Analytics (BDA).Big complexity is first factor hampering full potential BDA.The opacity variety technologies computations, in fact, make BDA failure prone resource-intensive process, which requires trial-and-error approach.This problem even...
This paper investigates the effectiveness of GPT-4o-2024-08-06, one Large Language Models (LLM) from OpenAI, in detecting business process anomalies, with a focus on rework anomalies. In our study, we developed GPT-4o-based tool capable transforming event logs into structured format and identifying reworked activities within logs. The analysis was performed synthetic dataset designed to contain anomalies but free loops. To evaluate anomaly detection capabilities GPT 4o-2024-08-06, used three...
This paper is a collaborative effort between Linguistics, Law, and Computer Science to evaluate stereotypes biases in automated translation systems. We advocate gender-neutral as means promote gender inclusion improve the objectivity of machine translation. Our approach focuses on identifying bias English-to-Italian translations. First, we define following human rights law linguistics literature. Then proceed by gender-specific terms such she/lei he/lui key elements. then cosine similarity...
Organizational risk management should not only rely on protecting data and information but also knowledge which is underdeveloped in many cases or measures are applied an uncoordinated, dispersed way. Therefore, we propose a consistent top-down translation from the organizational goals to implemented controls overcome these shortcomings. Our approach adopted domain of IT security allows measure how well protection actually pursued organizations. This affects organizations' abilities prove...
The Big Data revolution has promised to build a data-driven ecosystem where better decisions are supported by enhanced analytics and data management. However, critical issues still need be solved in the road that leads commodization of Analytics, such as management complexity protection security privacy. In this paper, we focus on first issue propose methodology based Model Driven Engineering (MDE) aims substantially lower amount competences needed pipeline support automation analytics....
Online process mining refers to a class of techniques for analyzing in real-time event streams generated by the execution business processes. These are crucial reactive monitoring processes, timely resource allocation and detection/prevention dysfunctional behavior. Many interesting advances have been made research community recent years, but there is no consensus on exact set properties these achieve. This article fills gap identifying evaluation goals online examining their fulfillment...
This work aims at investigating and quantifying the Urban Transport System (UTS) resilience enhancement enabled by adoption of emerging technology such as Internet Everything (IoE) new trend Connected Community (CC). A conceptual extension Functional Resonance Analysis Method (FRAM) its formalization have been proposed used to model UTS complexity. The scope is identify system functions their interdependencies with a particular focus on those that relation impact people communities. Network...
This article aims at introducing a new configurable and multipurpose electronic voting service based on the blockchain infrastructure. The objective is to design an architecture automatically translate configuration defined by end user into cloud-based deployable bundle, automating business logic definition, configuration, cloud provider selection. presents preliminary results of system SOA-based services definition implemented with smart contracts.
One of the main challenges Cognitive Computing (CC) is reacting to evolving environments in near-real time. Therefore, it expected that CC models provide solutions by examining a summary past history, rather than using full historical data. This strategy has significant benefits terms response time and space complexity but poses new term concept-drift detection, where both long short dynamics should be taken into account. In this paper, we introduce Concept-Drift Event Stream Framework...
Machine learning models are routinely integrated into <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">process mining</i> pipelines to carry out tasks like data transformation, noise reduction, anomaly detection, classification, and prediction. Often, the design of such is based on some ad-hoc assumptions about corresponding distributions, which not necessarily in accordance with xmlns:xlink="http://www.w3.org/1999/xlink">non-parametric</i>...
A Language Model is a term that encompasses various types of models designed to understand and generate human communication. Large Models (LLMs) have gained significant attention due their ability process text with human-like fluency coherence, making them valuable for wide range data-related tasks fashioned as pipelines. The capabilities LLMs in natural language understanding generation, combined scalability, versatility, state-of-the-art performance, enable innovative applications across...
'Big Data' techniques are often adopted in cross-organization scenarios for integrating multiple data sources to extract statistics or other latent information. Even if these do not require the support of a schema processing data, common conceptual model is typically defined address name resolution. This implies that each local source tasked applying semantic lifting procedure expressing term model. Semantic heterogeneity then potentially introduced data. In this paper we illustrate...
Process mining uses business event logs to understand the flow of activities, identify anomalous cases and enhance processes. Today, real-time process tools mainly deal with a single task at time (process discovery, conformance checking, enhancement or concept change detection). In this paper, we introduce an underlined layer overlapping multiple online tasks smooth their integration. Following case clustering approach, based on trace analysis, our proposal supports simultaneously?: drift...
Assuring anomaly-free business process executions is a key challenge for many organizations. Traditional techniques address this using prior knowledge about anomalous cases that seldom available in real-life. In work, we propose the usage of word2vec encoding and One-Class Classification algorithms to detect anomalies by relying on normal behavior only. We investigated 6 different types over 38 real synthetics event logs, comparing predictive performance Support Vector Machine, Local Outlier...
Multimodal Analytics in Big Data architectures implies compounded configurations of the data processing tasks. Each modality requires specific analytics that triggers Scalability can be reached at cost an attentive calibration resources shared by different tasks searching for a trade-off with multiple requirements they impose. We propose methodology to address multimodal within same approach get simplified architecture fully exploit potential parallel infrastructures. Multiple sources are...
We present a way of building ontologies that proceeds in bottom-up fashion, defining concepts as clusters concrete XML objects. Our rough are based on simple relations like association and inheritance, well value restrictions, can be used to enrich update existing upper ontologies. Then, we show how automatically generated assertions our associated with flexible degree trust by nonintrusively collecting user feedback the form implicit explicit votes. Dynamic trust-based views filter out...
Organizations are showing growing interest in paradigms where business models and services compatibility is adaptively tested, e.g. by applying automatic systems to check rules consistency. In this paper, we build on the original proposal OMG of using first-order logics for representing vocabularies propose an approach based description (DL) as formal logic support rules. By translating SBVR into OWL DL ontologies, standard inference procedures can be applied model consistency open-world,...