Daniele Pretolesi

Mr. Daniele Pretolesi

orcid

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

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

Representative Publications

View All Publications
Verified
Journal Article
Open access
PDF file
GRGeorg Regal
Georg Regal
DPDaniele Pretolesi
Daniele Pretolesi
HFHelmut Schrom Feiertag
Helmut Schrom Feiertag
JPJaison Puthenkalam
Jaison Puthenkalam
MMMassimo Migliorini
Massimo Migliorini
MMMarkus Murtinger
Markus Murtinger
The contemporary geopolitical environment and strategic uncertainty shaped by asymmetric and hybrid threats urge the future development of hands-on training in realistic environments. Training in immersive, virtual environments is a promising approach. Immersive training can support training for contexts that are otherwise hard to access, dangerous, or have high costs. This paper discusses the challenges for virtual reality training in the CBRN (chemical, biological, radioactive, nuclear) domain. Based on initial considerations and a literature review, we conducted a survey and three workshops to gather requirements for CBRN training in virtual environments. We structured the gathered insights into four overarching themes—the future of CBRN training, ethical and safety requirements, evaluation and feedback, and tangible objects and tools. We provide insights on these four themes and discuss recommendations.

24 December 2024 in JMIR XR and Spatial Computing
Verified
Journal Article
Open access
OZOlivia Zechner
Olivia Zechner
HFHelmut Schrom Feiertag
Helmut Schrom Feiertag
RWRafael Wespi
Rafael Wespi
DPDaniele Pretolesi
Daniele Pretolesi
QNQuynh Nguyen
Quynh Nguyen
MTManfred Tscheligi
Manfred Tscheligi
Background: Mixed reality (MR) simulation training is emerging in paramedical education as a way to practice responding to stress-intensive scenarios like mass casualty incidents in a safe and controlled environment. Current training platforms, however, lack real-time stress and human performance monitoring tools. Objective: The study aims to enhance MR training for medical first responders through real-time evaluation of performance and stress levels, leveraging biosignal monitoring and advanced analytics to allow instructors to tailor feedback and maintain optimal challenge and safety levels. Methods: The study includes a structured, multiphase approach including initial requirement gathering (structured interviews and cocreation workshops), an online design survey, iterative prototype development, and a field trial (including training observations and interviews). Data were collected from 5 end user consortium members across Europe. Quantitative data from checklists were analyzed using frequencies and percentages to understand feature usage and event occurrences. Qualitative data from semistructured interviews and cocreation workshops were transcribed, coded, and subjected to thematic analysis to identify patterns and insights into the usability and effectiveness of the enhanced features in the MR training. Results: The study identified a number of requirements that medical first responders have for an MR training system, including requirements not included in currently available solutions. A total of 80 performance metrics were initially identified and refined to a set of 54 metrics, which were categorized into key performance indicator groups such as scene safety, triage performance, and communication. Requirements for smart wearables to monitor stress levels are provided and highlight the importance of a user-centered design process to provide users with effective tools that fit their needs. Stress visualization preferences are described in the form of a dashboard as well as in virtual environments surrounding the avatar. Using an iterative design process and user feedback, a training system was developed, integrating real-time performance tracking and stress monitoring. The field trial provided insights into the practical use of these features during a real training exercise, showed interaction preferences between trainer and trainees, and highlighted further improvement opportunities. Conclusions: This research enhances MR training for paramedics by integrating real-time performance metrics and stress indicators based on a human-centered design approach that aligns with end user needs, thereby laying the foundation for developing more effective and immersive training solutions for high-stress professions.

22 September 2023 in IEEE Transactions on Emerging Topics in Computing
Verified
Journal Article
Closed access
DPDaniele Pretolesi
Daniele Pretolesi
DGDavide Garbarino
Davide Garbarino
DGDaniele Giampaoli
Daniele Giampaoli
AVAndrea Vian
Andrea Vian
ABAnnalisa Barla
Annalisa Barla
This paper examines how geometric deep learning techniques may be employed to analyze academic collaboration networks (ACNs) and how using textual information drawn from publications improves the overall performance of the system. The proposed experimental pipeline was used to analyze the collaboration network of the Machine Learning Genoa Center (MaLGa) research group. First, we find the optimal method for embedding the input data graph and extracting meaningful keywords for the available publications. We then use Graph Neural Networks (GNN) for node type and research topic classification. Finally, we explore how the resulting corpus can be used to create a recommender system for optimal navigation of the ACN. Our results show that the GNN-based recommender system achieved high accuracy in suggesting unexplored nodes to users. Overall, this study demonstrates the potential for using geometric deep learning and Natural Language Processing (NLP) to best represent the scientific production of ACNs. In the future, we plan to incorporate the temporal nature of the data and navigation statistics of users exploring the graph as additional input for the recommender system.

20 March 2024
Verified
Book Chapter
Closed access
PDF file
DPDaniele Pretolesi
Daniele Pretolesi
OZOlivia Zechner
Olivia Zechner
DGDaniel Garcia Guirao
Daniel Garcia Guirao
HFHelmut Schrom Feiertag
Helmut Schrom Feiertag
MTManfred Tscheligi
Manfred Tscheligi