Dario Guidotti

Dr. Dario Guidotti

orcid

Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
11 June 2025 in IEEE Access
Verified
Journal Article
Open access
DGDario Guidotti
Dario Guidotti
LPLaura Pandolfo
Laura Pandolfo
LPLuca Pulina
Luca Pulina
Industry 4.0 has driven a paradigm shift in manufacturing, pushing industries to adopt innovative technologies for more efficient decision-making. A key component of this revolution is predictive maintenance, which plays a central role in this transformation by leveraging, among others methods, supervised machine learning techniques to anticipate equipment failures, optimise maintenance schedules, and enhance operational efficiency. This study presents a Systematic Literature Review (SLR) of 216 peer-reviewed papers published between 2019 and 2024, analysing the adoption of supervised machine learning techniques for predictive maintenance in various industrial domains, including manufacturing, machinery, energy, and smart systems. Unlike previous SLRs that broadly examine ML applications, this review provides a structured taxonomy of predictive maintenance methods, highlighting their domain-specific usage and prevalence in safety-critical industries. Additionally, we analyse the types of datasets used, revealing a strong preference for real-world data but limited public availability, which poses challenges for reproducibility and benchmarking. This study identifies key trends in ML adoption and offers insights into future research directions, thereby reinforcing the need for open datasets, explainable AI, and cross-domain generalisation.

17 January 2025 in Information Technology & Tourism
Verified
Journal Article
Open access
PDF file
DGDario Guidotti
Dario Guidotti
LPLaura Pandolfo
Laura Pandolfo
LPLuca Pulina
Luca Pulina
With digital technology increasingly shaping the tourism industry, understanding customer sentiment and identifying key themes in reviews is crucial for enhancing service quality. However, traditional sentiment analysis and keyword extraction models typically demand significant time, computational resources, and labelled data for training. In this paper, we explore how Large Language Models (LLMs) can be leveraged to automatically classify reviews as positive or negative and extract relevant keywords without the need for dedicated training. Additionally, we frame the keyword extraction task as a tool to assist human users in comprehending and interpreting review content, especially in scenarios where ground truth labels for keywords are unavailable. To evaluate our approach, we conduct an experimental analysis using several datasets of tourism reviews and various LLMs. Our results demonstrate the reliability of LLMs as zero-shot classifiers for sentiment analysis and showcase the efficacy of the approach in extracting meaningful keywords from reviews, providing valuable insights into customer sentiments and preferences. Overall, this research contributes to the intersection of information technology and tourism by presenting a practical solution for sentiment analysis and keyword extraction in tourism reviews, leveraging the capabilities of LLMs as versatile tools for enhancing decision-making processes in the tourism industry.

5 March 2019 in IEEE Transactions on Neural Systems and Rehabilitation Engineering
Verified
Journal Article
Open access
DGDario Guidotti
Dario Guidotti
FLFrancesco Leofante
Francesco Leofante
ATArmando Tacchella
Armando Tacchella
CCClaudio Castellini
Claudio Castellini
In the context of assistive robotics, myocontrol is one of the so-far unsolved problems of upper-limb prosthetics. It consists of swiftly, naturally and reliably converting biosignals, non-invasively gathered from an upper-limb disabled subject, into control commands for an appropriate self-powered prosthetic device. Despite decades of research, traditional surface electromyography cannot yet detect the subject’s intent to an acceptable degree of reliability, that is, enforce an action exactly when the subject wants it to be enforced. In this work we tackle one such kind of mismatch between the subject’s intent and the response by the myocontrol system, and show that Formal Verification can indeed be used to mitigate it. Eighteen intact subjects were engaged in two Target Achievement Control tests in which a standard myocontrol system was compared with two “repaired” ones, one based on a non-formal technique, and thus enforcing no guarantee of safety, and the other using the Satisfiability Modulo Theories (SMT) technology to rigorously enforce the desired property. The experimental results indicate that both repaired systems exhibit better reliability than the non-repaired one. The SMT-based system causes only a modest increase in the required computational resources with respect to the non-formal technique; as opposed to this, the non-formal technique can be easily implemented in existing myocontrol systems, potentially increasing their reliability.

12 July 2023 in Information
Verified
Journal Article
Open access
PDF file
DGDario Guidotti
Dario Guidotti
LPLaura Pandolfo
Laura Pandolfo
LPLuca Pulina
Luca Pulina
Interest in machine learning and neural networks has increased significantly in recent years. However, their applications are limited in safety-critical domains due to the lack of formal guarantees on their reliability and behavior. This paper shows recent advances in satisfiability modulo theory solvers used in the context of the verification of neural networks with piece-wise linear and transcendental activation functions. An experimental analysis is conducted using neural networks trained on a real-world predictive maintenance dataset. This study contributes to the research on enhancing the safety and reliability of neural networks through formal verification, enabling their deployment in safety-critical domains.

31 July 2024 in Soft Computing
Verified
Journal Article
Open access
PDF file
SDStefano Demarchi
Stefano Demarchi
DGDario Guidotti
Dario Guidotti
LPLuca Pulina
Luca Pulina
ATArmando Tacchella
Armando Tacchella
NeVer2 is an open-source, cross-platform tool aimed at designing, training, and verifying neural networks. It seamlessly integrates popular learning libraries with our verification backend, offering their functionalities via a graphical interface. Users can design the structure of a neural network by intuitively arranging blocks on a canvas. Subsequently, network training involves specifying dataset sources and hyperparameters through dialog boxes. After training, the verification process entails two steps: (i) incorporating input preconditions and output postconditions via dedicated blocks, and (ii) initiating verification with a simple “push-button” action. To our knowledge, there is currently no other publicly available tool that encompasses all these features. In this paper, we present a comprehensive description of NeVer2, illustrating its complete integration of design, training, and verification through examples. Additionally, we conduct experimental analyses on various verification benchmarks to illustrate the trade-off between completeness and computability using different algorithms. We also include a comparison with state-of-the-art tools such as $$\alpha $$ α , $$\beta $$ β -CROWN and NNV for reference.

1 January 2020
Verified
Book Chapter
Open access
PDF file
DGDario Guidotti
Dario Guidotti
LFLeofante Francesco
Leofante Francesco
LPLuca Pulina
Luca Pulina
TATacchella Armando
Tacchella Armando
Verification of deep neural networks has witnessed a recent surge of interest, fueled by success stories in diverse domains and by abreast concerns about safety and security in envisaged applications. Complexity and sheer size of such networks are challenging for automated formal verification techniques which, on the other hand, could ease the adoption of deep networks in safety-and security-critical contexts. In this paper we focus on enabling stateof-the-art verification tools to deal with neural networks of some practical interest. We propose a new training pipeline based on network pruning with the goal of striking a balance between maintaining accuracy and robustness, while also making the resulting networks amenable to formal analysis. The results of our experiments with a portfolio of pruning algorithms and verification tools show that our approach is successful for the kind of networks we consider and for some combinations of pruning and verification techniques, thus bringing deep neural networks closer to the reach of formallygrounded methods.