Emanuele Guardiani
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Emanuele Guardiani has a total of 25 co-authors. Here are the top co-authors by number of shared publications:
- Luca Di Angelo
Department of Industrial and Information Engineering and Economics, University of L’Aquila, L’Aquila, Italy
29 shared publications - Paolo Di Stefano
Department of Industrial and Computer Engineering and Economics, University of L’Aquila, 67100 L’Aquila, Italy
25 shared publications - Anna Eva Morabito
Department of Innovation Engineering, University of Salento, Lecce, Italy
8 shared publications - Antonio Marzola
University of L’Aquila
8 shared publications Paolo Di Stefano
University of L‘Aquila
3 shared publications- Alessandro Paoli
University of Pisa
2 shared publications
Latest Publications
- Open Access
Plagiarism detection in parametric CAD models: A supervised similarity framework for engineering education
- Open Access
- 23 September 2026
- Published by Elsevier in Machine Learning with Applications
- Vol. 26
A dual-level evaluation framework for anatomical data augmentation: A comparative study on L2 vertebra semantic segmentation
- 23 September 2026
- Published by Elsevier in Machine Learning with Applications
- Vol. 26
Open AccessA dual-level evaluation framework for anatomical data augmentation: A comparative study on L2 vertebra semantic segmentation
- 15 August 2026
- Published by Springer Nature
- p. 155-166
Metrological Characterization and CAD-Agnostic Data Pipeline for Consumer-Grade XR Tracking in Functional Mechanical Design
- 15 August 2026
- Published by Springer Nature
- p. 155-166
Metrological Characterization and CAD-Agnostic Data Pipeline for Consumer-Grade XR Tracking in Functional Mechanical Design
- Open Access
- 22 May 2026
- Published by Springer Nature in International Journal on Interactive Design and Manufacturing (IJIDeM)
- Vol. 20 (10) , 1-17
Markerless spinal assessment: a purely geometric framework for automated landmark detection from 3D surface scans
Non-invasive assessment of spinal morphology traditionally relies on subjective manual palpation or data-driven deep learning models that often lack metrological interpretability. This study presents a fully automated, purely geometric framework for the localization and morphometric characterization of spinous processes directly from 3D dorsal surface scans. Leveraging continuous differential geometry and the scale-invariant properties of the shape index, the proposed algorithm operates independently of training data, physical markers, and ionizing radiation. Validation against expert clinical palpation demonstrated high spatial reliability, yielding a mean spatial deviation of 3.7 mm and a 98.6% Confidence Index in matching manually identified landmarks. Notably, the computational framework exhibited heightened morphological sensitivity, consistently extracting mathematically valid geometric signatures in spinal regions conservatively bypassed by the clinician. This resulted in a theoretical algorithmic False Negative Rate bounded between 13.5% and 14.6%, compared to a 33.1% manual rate. Furthermore, the system autonomously evaluated morphometric parameters, such as basal width, symmetry index, and local apical prominence, successfully classifying 327 apophyses into “prominent” (19%) and “masked” (81%) morphotypes across complex, soft-tissue-mediated topographies. While these findings highlight the method’s capability to standardize and objectify dorsal surface assessment, definitive anatomical fidelity requires future radiological correlation. Ultimately, this robust topographic profiling lays the foundation for autonomously quantifying structural asymmetries in clinical spinal deformities. Graphical abstract Graphical abstract summarizing the automated workflow from 3D scan to landmark extraction
- 22 May 2026
- Published by Springer Nature in International Journal on Interactive Design and Manufacturing (IJIDeM)
- Vol. 20 (10) , 1-17
Open AccessMarkerless spinal assessment: a purely geometric framework for automated landmark detection from 3D surface scans
Non-invasive assessment of spinal morphology traditionally relies on subjective manual palpation or data-driven deep learning models that often lack metrological interpretability. This study presents a fully automated, purely geometric framework for the localization and morphometric characterization of spinous processes directly from 3D dorsal surface scans. Leveraging continuous differential geometry and the scale-invariant properties of the shape index, the proposed algorithm operates independently of training data, physical markers, and ionizing radiation. Validation against expert clinical palpation demonstrated high spatial reliability, yielding a mean spatial deviation of 3.7 mm and a 98.6% Confidence Index in matching manually identified landmarks. Notably, the computational framework exhibited heightened morphological sensitivity, consistently extracting mathematically valid geometric signatures in spinal regions conservatively bypassed by the clinician. This resulted in a theoretical algorithmic False Negative Rate bounded between 13.5% and 14.6%, compared to a 33.1% manual rate. Furthermore, the system autonomously evaluated morphometric parameters, such as basal width, symmetry index, and local apical prominence, successfully classifying 327 apophyses into “prominent” (19%) and “masked” (81%) morphotypes across complex, soft-tissue-mediated topographies. While these findings highlight the method’s capability to standardize and objectify dorsal surface assessment, definitive anatomical fidelity requires future radiological correlation. Ultimately, this robust topographic profiling lays the foundation for autonomously quantifying structural asymmetries in clinical spinal deformities. Graphical abstract Graphical abstract summarizing the automated workflow from 3D scan to landmark extraction
- Open Access
- 28 April 2026
- Published by Elsevier in SSRN Electronic Journal
Plagiarism Detection in Parametric CAD Models: A Supervised Similarity Framework for Engineering Education
The widespread integration of Computer-Aided Design (CAD) software into engineering education has transformed instructional practices and assessment strategies, creating new challenges for academic integrity. In parametric modelling environments, plagiarism extends beyond simple geometric duplication to include the reuse of modelling sequences, feature-tree structures, and constraint-based design intentions. Traditional plagiarism-detection tools, primarily designed for text-based documents, are ineffective at capturing the procedural and relational aspects of CAD models. This study introduces a technology-aware plagiarism-detection framework designed explicitly for parametric CAD coursework. The proposed method incorporates multi-level similarity analysis, combining geometric comparisons, feature-tree structure assessments, chronological modelling sequences, and sketch-level constraint evaluations. By examining both the final artefacts and the underlying design intent, the system aims to differentiate between independent problem-solving processes and copied or minimally modified models. The framework was tested on a classroom dataset of student submissions. Results demonstrate enhanced effectiveness in detecting unwarranted similarities while minimising sensitivity to minor variations, thereby supporting fairer and more transparent assessments. Beyond detection, the proposed approach aims to contribute to the development of analysis-based training tools that promote academic integrity in computer-aided design teaching. This study emphasises the importance of understanding plagiarism in CAD environments as a technology-mediated phenomenon, thereby requiring specialised assessment strategies aligned with contemporary engineering pedagogy.
- 28 April 2026
- Published by Elsevier in SSRN Electronic Journal
Open AccessPlagiarism Detection in Parametric CAD Models: A Supervised Similarity Framework for Engineering Education
The widespread integration of Computer-Aided Design (CAD) software into engineering education has transformed instructional practices and assessment strategies, creating new challenges for academic integrity. In parametric modelling environments, plagiarism extends beyond simple geometric duplication to include the reuse of modelling sequences, feature-tree structures, and constraint-based design intentions. Traditional plagiarism-detection tools, primarily designed for text-based documents, are ineffective at capturing the procedural and relational aspects of CAD models. This study introduces a technology-aware plagiarism-detection framework designed explicitly for parametric CAD coursework. The proposed method incorporates multi-level similarity analysis, combining geometric comparisons, feature-tree structure assessments, chronological modelling sequences, and sketch-level constraint evaluations. By examining both the final artefacts and the underlying design intent, the system aims to differentiate between independent problem-solving processes and copied or minimally modified models. The framework was tested on a classroom dataset of student submissions. Results demonstrate enhanced effectiveness in detecting unwarranted similarities while minimising sensitivity to minor variations, thereby supporting fairer and more transparent assessments. Beyond detection, the proposed approach aims to contribute to the development of analysis-based training tools that promote academic integrity in computer-aided design teaching. This study emphasises the importance of understanding plagiarism in CAD environments as a technology-mediated phenomenon, thereby requiring specialised assessment strategies aligned with contemporary engineering pedagogy.
- Open Access
- 15 April 2026
- Published by Elsevier in SSRN Electronic Journal
Plagiarism Detection in Parametric CAD Models: A Supervised Similarity Framework for Engineering Education
The widespread integration of Computer-Aided Design (CAD) software into engineering education has transformed instructional practices and assessment strategies, creating new challenges for academic integrity. In parametric modelling environments, plagiarism extends beyond simple geometric duplication to include the reuse of modelling sequences, feature-tree structures, and constraint-based design intentions. Traditional plagiarism-detection tools, primarily designed for text-based documents, are ineffective at capturing the procedural and relational aspects of CAD models. This study introduces a technology-aware plagiarism-detection framework designed explicitly for parametric CAD coursework. The proposed method incorporates multi-level similarity analysis, combining geometric comparisons, feature-tree structure assessments, chronological modelling sequences, and sketch-level constraint evaluations. By examining both the final artefacts and the underlying design intent, the system aims to differentiate between independent problem-solving processes and copied or minimally modified models. The framework was tested on a classroom dataset of student submissions. Results demonstrate enhanced effectiveness in detecting unwarranted similarities while minimising sensitivity to minor variations, thereby supporting fairer and more transparent assessments. Beyond detection, the proposed approach aims to contribute to the development of analysis-based training tools that promote academic integrity in computer-aided design teaching. This study emphasises the importance of understanding plagiarism in CAD environments as a technology-mediated phenomenon, thereby requiring specialised assessment strategies aligned with contemporary engineering pedagogy.
- 15 April 2026
- Published by Elsevier in SSRN Electronic Journal
Open AccessPlagiarism Detection in Parametric CAD Models: A Supervised Similarity Framework for Engineering Education
The widespread integration of Computer-Aided Design (CAD) software into engineering education has transformed instructional practices and assessment strategies, creating new challenges for academic integrity. In parametric modelling environments, plagiarism extends beyond simple geometric duplication to include the reuse of modelling sequences, feature-tree structures, and constraint-based design intentions. Traditional plagiarism-detection tools, primarily designed for text-based documents, are ineffective at capturing the procedural and relational aspects of CAD models. This study introduces a technology-aware plagiarism-detection framework designed explicitly for parametric CAD coursework. The proposed method incorporates multi-level similarity analysis, combining geometric comparisons, feature-tree structure assessments, chronological modelling sequences, and sketch-level constraint evaluations. By examining both the final artefacts and the underlying design intent, the system aims to differentiate between independent problem-solving processes and copied or minimally modified models. The framework was tested on a classroom dataset of student submissions. Results demonstrate enhanced effectiveness in detecting unwarranted similarities while minimising sensitivity to minor variations, thereby supporting fairer and more transparent assessments. Beyond detection, the proposed approach aims to contribute to the development of analysis-based training tools that promote academic integrity in computer-aided design teaching. This study emphasises the importance of understanding plagiarism in CAD environments as a technology-mediated phenomenon, thereby requiring specialised assessment strategies aligned with contemporary engineering pedagogy.
- 5 February 2026
- Published by Springer Nature
- p. 28-40
A Novel Shape Index-Based Method for Automatic Localization of Spinal Apophyses
- 5 February 2026
- Published by Springer Nature
- p. 28-40
A Novel Shape Index-Based Method for Automatic Localization of Spinal Apophyses
- 5 February 2026
- Published by Springer Nature
- p. 520-530
An Intelligent Framework for End-of-Life ICT Components Valorization: a Zero-Shot Approach
- 5 February 2026
- Published by Springer Nature
- p. 520-530
An Intelligent Framework for End-of-Life ICT Components Valorization: a Zero-Shot Approach
- 5 February 2026
- Published by Springer Nature
- p. 509-519
An Automated Pipeline for Dens Morphometry Based on Enhanced Statistical Shape Modeling of the C2 Vertebra
- 5 February 2026
- Published by Springer Nature
- p. 509-519
An Automated Pipeline for Dens Morphometry Based on Enhanced Statistical Shape Modeling of the C2 Vertebra