Davide Azzalini
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Davide Azzalini has a total of 14 co-authors. Here are the top co-authors by number of shared publications:
- Francesco Amigoni
Politecnico di Milano, Milan, Italy
4 shared publications - Alberto Castellini
University of Verona
1 shared publication - Alessandro Farinelli
University of Verona
1 shared publication - Andrea Castelletti
Politecnico di Milano
1 shared publication - Benedetta Flammini1 shared publication
- Elisa Quintarelli
University of Verona
1 shared publication
Latest Publications
- 7 May 2025
- Published by Springer Nature
- p. 69-81
Trustworthy Inductive Knowledge for Tropical Cyclones Formation Detection
- 7 May 2025
- Published by Springer Nature
- p. 69-81
Trustworthy Inductive Knowledge for Tropical Cyclones Formation Detection
- Open Access
- 6 April 2025
- Published by Elsevier in Robotics and Autonomous Systems
- Vol. 191
Multi-Agent Pickup and Delivery with external agents
- 6 April 2025
- Published by Elsevier in Robotics and Autonomous Systems
- Vol. 191
Open AccessMulti-Agent Pickup and Delivery with external agents
- Open Access
- 7 August 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 45 (12) , 14131-14143
Adversarial Data Augmentation for HMM-Based Anomaly Detection
In this work, we concentrate on the detection of anomalous behaviors in systems operating in the physical world and for which it is usually not possible to have a complete set of all possible anomalies in advance. We present a data augmentation and retraining approach based on adversarial learning for improving anomaly detection. In particular, we first define a method for generating adversarial examples for anomaly detectors based on Hidden Markov Models (HMMs). Then, we present a data augmentation and retraining technique that uses these adversarial examples to improve anomaly detection performance. Finally, we evaluate our adversarial data augmentation and retraining approach on four datasets showing that it achieves a statistically significant performance improvement and enhances the robustness to adversarial attacks. Key differences from the state-of-the-art on adversarial data augmentation are the focus on multivariate time series (as opposed to images), the context of one-class classification (in contrast to standard multi-class classification), and the use of HMMs (in contrast to neural networks).
- 7 August 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 45 (12) , 14131-14143
Open AccessAdversarial Data Augmentation for HMM-Based Anomaly Detection
In this work, we concentrate on the detection of anomalous behaviors in systems operating in the physical world and for which it is usually not possible to have a complete set of all possible anomalies in advance. We present a data augmentation and retraining approach based on adversarial learning for improving anomaly detection. In particular, we first define a method for generating adversarial examples for anomaly detectors based on Hidden Markov Models (HMMs). Then, we present a data augmentation and retraining technique that uses these adversarial examples to improve anomaly detection performance. Finally, we evaluate our adversarial data augmentation and retraining approach on four datasets showing that it achieves a statistically significant performance improvement and enhances the robustness to adversarial attacks. Key differences from the state-of-the-art on adversarial data augmentation are the focus on multivariate time series (as opposed to images), the context of one-class classification (in contrast to standard multi-class classification), and the use of HMMs (in contrast to neural networks).
- 19 June 2022
- Published by Springer Nature
- p. 143-154
FARGO: A Fair, Context-AwaRe, Group RecOmmender System
- 19 June 2022
- Published by Springer Nature
- p. 143-154
FARGO: A Fair, Context-AwaRe, Group RecOmmender System
- 26 February 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 6 (2) , 2985-2992
A Minimally Supervised Approach Based on Variational Autoencoders for Anomaly Detection in Autonomous Robots
Detection of anomalies and faults is a crucial ability for fully autonomous robots. This letter proposes a new deep learning-based minimally supervised method for detecting anomalies in autonomous robots. We contribute a new Variational Auto-Encoder architecture able to model very long multivariate sensor logs exploiting a new incremental training method, which induces a progress-based latent space that can be used to detect anomalies both at runtime and offline. While most existing approaches are trained in a semi-supervised fashion and require big batches of nominal observations, our method is trained using unlabeled observations of a robot performing a task, containing both nominal and anomalous executions. Only a very little amount (even just one) of labeled nominal executions is then required to partition the learned latent space into nominal and anomalous regions. Experimental results show that our method outperforms state-of-the-art anomaly detectors commonly used in robotics both in terms of false positive rate and alert delay.
- 26 February 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 6 (2) , 2985-2992
A Minimally Supervised Approach Based on Variational Autoencoders for Anomaly Detection in Autonomous Robots
Detection of anomalies and faults is a crucial ability for fully autonomous robots. This letter proposes a new deep learning-based minimally supervised method for detecting anomalies in autonomous robots. We contribute a new Variational Auto-Encoder architecture able to model very long multivariate sensor logs exploiting a new incremental training method, which induces a progress-based latent space that can be used to detect anomalies both at runtime and offline. While most existing approaches are trained in a semi-supervised fashion and require big batches of nominal observations, our method is trained using unlabeled observations of a robot performing a task, containing both nominal and anomalous executions. Only a very little amount (even just one) of labeled nominal executions is then required to partition the learned latent space into nominal and anomalous regions. Experimental results show that our method outperforms state-of-the-art anomaly detectors commonly used in robotics both in terms of false positive rate and alert delay.