Shayan Sharifi
PhD Student in AI & Applied Data Science | Computer Engineer
Shayan Sharifi
PhD Student in AI & Applied Data Science | Computer Engineer
I am a PhD student in AI and Applied Data Science at the University of Trieste, conducting research in the Waveslab under the supervision of Prof. Giulia Cisotto. My expertise lies in multimodal learning, explainable AI (XAI), time-series analysis, agentic AI, and computer vision. I completed my Master's thesis at RWTH Aachen University within the Institute for Automotive Engineering (ika), under the supervision of Dr. Till Beemelmanns and Prof. Pietro Zanutigh. I hold a Master's degree in ICT Engineering from the University of Padova, graduating with a score of 110/110, as well as a Bachelor's degree in Computer Engineering. In my professional career, I have served as the Head of the IT Section and a web developer at Hermes Espeins, and I am the founder of Luminsco.
Latest News
ADSAI PhDs Summit
On July 2nd we invited the PhD students in ADSAI to to discuss the issues in the departemnt and proposals which were provided by repesentatives to address some of them.
Current Projects
Explainable AI for ECG-based Screening of LGE+ Cardiomyopathies
This study aims to develop explainable machine-learning and deep-learning models to identify ECG-derived signatures associated with LGE-positive cardiomyopathies, currently detectable only through contrast-enhanced cardiac magnetic resonance imaging. If successful, the project would provide a low-cost, non-invasive proxy based on routine ECG recordings to support early risk stratification and guide referral to specialised, more expensive and invasive diagnostic pathways only for patients with suspicious ECG profiles. The study is carried out in collaboration with ASUGI–Cattinara.
Multi-modal Explainable 3D Object Detection
We proposed a Trustworthy AI perception module that is remarkably robust, integrates faithful explainability, and calibrated uncertainty estimates. Building on a transformer-based detector, we derive explanation from the attention mechanism at inference time and validate their faithfulness using perturbation-based consistency tests. Experiments show faithful saliency behavior, improved robustness, and well-calibrated uncertainty estimates. Finally, we deploy these Trustworthy AI elements in a prototype vehicle and provide an XAI Interface that visualizes documentation artifacts, model uncertainty state, and saliency maps, demonstrating the feasibility of trustworthy perception monitoring in real time
Selected Publications
Feature Importance via Shapley Values in Random Forests for Sleep Apnea and Hypopnea Detection
Cisotto, G., Sharifi, S., Sadeghzadehdarandash, S., & Badia, L.
Preprint / Journal Submission, 2025
Towards Trustworthy and Explainable AI for Perception Models: From Concept to Prototype Vehicle Deployment
Beemelmanns, T., Sharifi, S., Mehrotra, M., Choudhuri, A., & Eckstein, L.
2026 IEEE International Conference on Intelligent Transportation Systems (ITSC), 2026
Collaboration
I am open to academic collaborations, research initiatives, and consulting on data pipeline architectures or machine learning / deep learning infrastructure deployments. Feel free to connect if you want to swap ideas or look at challenging data engineering vectors together.