1 code implementation • 8 Apr 2024 • Sannara Ek, Riccardo Presotto, Gabriele Civitarese, François Portet, Philippe Lalanda, Claudio Bettini
Although supervised learning methods are the most effective in this task, their effectiveness is constrained to using a large amount of labeled data during training.
no code implementations • 11 Mar 2024 • Luca Arrotta, Claudio Bettini, Gabriele Civitarese, Michele Fiori
Neuro-Symbolic AI (NeSy) provides an interesting research direction to mitigate this issue, by infusing common-sense knowledge about human activities and the contexts in which they can be performed into HAR deep learning classifiers.
1 code implementation • 23 Jun 2023 • Riccardo Presotto, Sannara Ek, Gabriele Civitarese, François Portet, Philippe Lalanda, Claudio Bettini
In this paper, we propose a novel strategy to combine publicly available datasets with the goal of learning a generalized HAR model that can be fine-tuned using a limited amount of labeled data on an unseen target domain.
no code implementations • 8 Jun 2023 • Luca Arrotta, Gabriele Civitarese, Claudio Bettini
In this work, we propose a novel approach based on a semantic loss function that infuses knowledge constraints in the HAR model during the training phase, avoiding symbolic reasoning during classification.
no code implementations • 19 Apr 2023 • Luca Arrotta, Gabriele Civitarese, Samuele Valente, Claudio Bettini
Supervised Deep Learning (DL) models are currently the leading approach for sensor-based Human Activity Recognition (HAR) on wearable and mobile devices.
no code implementations • 22 Nov 2022 • Marco Colussi, Gabriele Civitarese, Dragan Ahmetovic, Claudio Bettini, Roberta Gualtierotti, Flora Peyvandi, Sergio Mascetti
Joint bleeding is a common condition for people with hemophilia and, if untreated, can result in hemophilic arthropathy.
no code implementations • 15 Apr 2021 • Claudio Bettini, Gabriele Civitarese, Riccardo Presotto
Indeed, FedHAR combines active learning and label propagation to semi-automatically annotate the local streams of unlabeled sensor data, and it relies on FL to build a global activity model in a scalable and privacy-aware fashion.
no code implementations • 7 Jun 2019 • Gabriele Civitarese, Riccardo Presotto, Claudio Bettini
While the majority of the proposed techniques are based on supervised learning, semi-supervised approaches are being considered to significantly reduce the size of the training set required to initialize the recognition model.