CV
This is a description of the page. You can modify it in '_pages/cv.md'. You can also change or remove the top pdf download button.
Contact Information
| Name | Alberto Zancanaro |
| Professional Title | Ph.D. in Information Engineering | Deep learning and generative AI for biomedical signals and complex systems |
| [email protected] |
Professional Summary
Machine learning researcher working on deep generative models for biomedical signals and complex systems, from model design to deployment in embedded and federated settings.
Experience
-
2022 - 2025 Padua, Italy
Doctoral Researcher
University of Padua
- Deep generative models for biomedical signals: classification, anomaly detection and reconstruction of EEG and other biological data.
-
2023 - 2024 Padua, Italy
Teaching Assistant
University of Padua
- Teaching assistant for two editions of the eHealth course, M.Sc. in ICT for Internet and Multimedia.
-
2024 - 2024 Klagenfurt, Austria
Visiting Researcher
University of Klagenfurt
- Development and deployment of deep learning models on embedded devices.
- Application of federated learning techniques to biological data.
-
2020 - 2021 Coimbra, Portugal
Visiting Student
University of Coimbra
- Development of deep learning models for the analysis of EEG signals.
Education
-
2022 - 2025 Padua, Italy
Ph.D.
University of Padua
Information Engineering
- Thesis: Modeling complex living systems via deep learning and signal processing.
-
2019 - 2021 Padua, Italy
M.Sc.
University of Padua
ICT for Internet and Multimedia
- Life and Health
- Curriculum: Life and Health.
- Thesis: Deep learning algorithms for the analysis of EEG signals for neuroscience and motor rehabilitation.
-
2015 - 2018 Padua, Italy
B.Sc.
University of Padua
Information Engineering
- Thesis: Compartmental model for estimating the kinetics of the 11C-PIB drug.
Projects
-
Deep Learning applied to Biological Data
Classification, anomaly detection and reconstruction of biological data.
-
Deep Learning for EEG — research framework
Personal library for deep learning on EEG: models built from configuration dictionaries, Weights & Biases experiment tracking, reusable pipelines.
-
soft-DTW-Rust
Implementation of the soft-DTW algorithm in Rust with Python bindings; published on PyPI.
-
Unity AR application
Python-side neural network tracks hand movement and streams it to Unity, where C# scripts drive objects in an AR scene.
Publications
-
2025 Artificial intelligence for advanced functional materials: exploring current and future directions
Journal of Physics: Materials
-
2025 BlockDTW: Efficient and Scalable Similarity Search Algorithm for Healthcare-Focused Time-Series
2025 IEEE Conference on Standards for Communications and Networking (CSCN)
-
2024 Status update scheduling in remote sensing under variable activation and propagation delays
Ad Hoc Networks
-
2024 hvEEGNet: a novel deep learning model for high-fidelity EEG reconstruction
Frontiers in Neuroinformatics
-
2024 An AI-empowered energy-efficient portable NIRS solution for precision agriculture: A pilot study on a citrus fruit
2024 19th Conference on Computer Science and Intelligence Systems (FedCSIS)
-
2024 The Impact of Mis-Labeled Artefacts on Deep Learning Models for EEG Analysis: a Case Study
International Meeting on Computational Intelligence Methods for Bioinformatics and Biostatistics
-
2023 Modeling value of information in remote sensing from correlated sources
Computer Communications
-
2023 Tackling age of information in access policies for sensing ecosystems
Sensors
-
2023 veegnet: A new deep learning model to classify and generate eeg
Proceedings of the 9th International Conference on Information and Communication Technologies for Ageing Well and e-Health, ICT4AWE 2023, Prague, Czech Republic, April 22-24, 2023
-
2023 Impact of transmission delays over age of information under finite horizon scheduling
2023 IEEE 28th International Workshop on Computer Aided Modeling and Design of Communication Links and Networks (CAMAD)
-
2023 hvEEGNet: exploiting hierarchical VAEs on EEG data for neuroscience applications
arXiv preprint arXiv:2312.00799
-
2023 vEEGNet: learning latent representations to reconstruct EEG raw data via variational autoencoders
International Conference on Information and Communication Technologies for Ageing Well and e-Health
-
2022 Challenges of the age of information paradigm for metrology in cyberphysical ecosystems
2022 IEEE International Workshop on Metrology for Living Environment (MetroLivEn)
-
2022 Variational autoencoder for early stress detection in smart agriculture: A pilot study
2022 IEEE Workshop on Metrology for Agriculture and Forestry (MetroAgriFor)
-
2022 Analytical evaluation of age of information in networks of correlated sources
2022 IEEE Workshop on Metrology for Agriculture and Forestry (MetroAgriFor)
-
2021 CNN-based approaches for cross-subject classification in motor imagery: From the state-of-the-art to DynamicNet
2021 IEEE conference on computational intelligence in bioinformatics and computational biology (CIBCB)
Skills
Programming (): Python (primary), Rust, C++, C# (Unity), JavaScript
ML frameworks (): PyTorch, TensorFlow, Keras
Scientific stack (): NumPy, SciPy, scikit-learn, pandas, Matplotlib
Methods (): Deep generative models (VAE, diffusion), transformers, self-supervised learning, federated learning, signal processing
Tools (): Linux, Git, Docker, LaTeX, Neovim, Weights & Biases
Languages
Italian : Native
English : C1 — working language of research and teaching
French : A2