Roberto Saia (0000-0002-1734-0437)

Personal information

Biography

My research involves the data mining, the pattern recognition, the artificial intelligence, and
the Security areas. It is mainly oriented toward the design and development of new approaches
for the Recommender Systems, the Credit Scoring Systems, and the Fraud Detection Systems.
It also involves the security analysis of the blockchain-based applications, such us the Bitcoin
and Ethereum cryptocurrencies.

Activities

Collapse all

University of Cagliari: Cagliari, IT

2016 to present | Postdoctoral Researcher (Department of Mathematics and Computer Science)

Employment

Roberto Saia

https://orcid.org/0000-0002-1734-0437

Personal information

Websites & social links

Other IDs

Keywords

Countries

Biography

Activities

Employment (1)

University of Cagliari: Cagliari, IT

Education and qualifications (3)

University of Cagliari: Cagliari, IT

University of Cagliari: Cagliari, IT

University of Cagliari: Cagliari, IT

Works (49)

Enhancing EEG-Based User Verification with a Normalized Neural Network Ensemble Approach

HUMAD 2024: International Workshop on Human-Centered Modeling and Adaptation for Digital Transformation

RoadSense3D: A Framework for Roadside Monocular 3D Object Detection

Investigating the Effectiveness of 3D Monocular Object Detection Methods for Roadside Scenarios

Can Existing 3D Monocular Object Detection Methods Work in Roadside Contexts? A Reproducibility Study

Influencing brain waves by evoked potentials as biometric approach: taking stock of the last six years of research

Credit scoring by leveraging an ensemble stochastic criterion in a transformed feature space

A Blockchain-Based Distributed Paradigm to Secure Localization Services

Wireless Internet, Multimedia, and Artificial Intelligence: New Applications and Infrastructures

A combined entropy-based approach for a proactive credit scoring

A General Approach for Risk Controlled Trading Based on Machine Learning and Statistical Arbitrage

Dissecting Ponzi schemes on Ethereum: Identification, analysis, and impact

A Local Feature Engineering Strategy to Improve Network Anomaly Detection

Popularity Prediction of Instagram Posts

Popularity Prediction of Instagram Posts

Analysis of a Consensus Protocol for Extending Consistent Subchains on the Bitcoin Blockchain

A discretized enriched technique to enhance machine learning performance in credit scoring

A discretized extended feature space (DEFS) model to improve the anomaly detection performance in network intrusion detection systems

A supervised multi-class multi-label word embeddings approach for toxic comment classification

Evaluating the benefits of using proactive transformed-domain-based techniques in fraud detection tasks

Internet of entities (IoE): A blockchain-based distributed paradigm for data exchange between wireless-based devices

Introducing a vector space model to perform a proactive credit scoring

A Holistic Auto-Configurable Ensemble Machine Learning Strategy for Financial Trading

Fraud detection for E-commerce transactions by employing a prudential Multiple Consensus model

A probabilistic-driven ensemble approach to perform event classification in intrusion detection system

A wavelet-based data analysis to credit scoring

Unbalanced data classification in fraud detection by introducing a multidimensional space analysis

Forecasting E-Commerce Products Prices by Combining an Autoregressive Integrated Moving Average (ARIMA) Model and Google Trends Data

A discrete wavelet transform approach to fraud detection

A fourier spectral pattern analysis to design credit scoring models

A frequency-domain-based pattern mining for credit card fraud detection

Evaluating credit card transactions in the frequency domain for a proactive fraud detection approach

Exploiting the evaluation frequency of the items to enhance the recommendation accuracy

Popularity Does Not Always Mean Triviality: Introduction of Popularity Criteria to Improve the Accuracy of a Recommender System

Semantics-aware content-based recommender systems: Design and architecture guidelines

A class-based strategy to user behavior modeling in recommender systems

A linear-dependence-based approach to design proactive credit scoring models

A semantic approach to remove incoherent items from a user profile and improve the accuracy of a recommender system

An entropy based algorithm for credit scoring

Binary sieves: Toward a semantic approach to user segmentation for behavioral targeting

Exploiting a Determinant-based Metric to Evaluate a Word-embeddings Matrix of Items

Exploiting a Determinant-Based Metric to Evaluate a Word-Embeddings Matrix of Items

Improving the accuracy of latent-space-based recommender systems by introducing a cut-off criterion

Representing items as word-embedding vectors and generating recommendations by measuring their linear independence

Using neural word embeddings to model user behavior and detect user segments

A Latent Semantic Pattern Recognition Strategy for an Untrivial Targeted Advertising

A new perspective on recommender systems: A class path information model

Multiple behavioral models: A divide and conquer strategy to fraud detection in financial data streams

Semantic coherence-based user profile modeling in the recommender systems context

Peer review (574 reviews for 130 publications/grants)