Articolo in rivista, 2022, ENG, 10.1109/TVT.2022.3178612

Federated feature selection for cyber-physical systems of systems

Cassarà P.; Gotta A.; Valerio L.

CNR-ISTI, Pisa, Italy; CNR-ISTI, Pisa, Italy; CNR-IIT, Pisa, Italy

Autonomous vehicles (AVs) generate a massive amount of multi-modal data that once collected and processed through Machine Learning algorithms, enable AI-based services at the Edge. In fact, only a subset of the collected data present infor- mative attributes to be exploited at the Edge. Therefore, extracting such a subset is of utmost importance to limit computation and com- munication workloads. Doing that in a distributed manner imposes the AVs to cooperate in finding an agreement on which attributes should be sent to the Edge. In this work, we address such a problem by proposing a federated feature selection (FFS) algorithm where the AVs collaborate to filter out, iteratively, the less relevant at- tributes in a distributed manner, without any exchange of raw data, thought two different components: a Mutual-Information-based feature selection algorithm run by the AVs and a novel aggregation function based on the Bayes theorem executed on the Edge. The FFS algorithm has been tested on two reference datasets: MAV with images and inertial measurements of a monitored vehicle, WESAD with a collection of samples from biophysical sensors to monitor a relative passenger. The numerical results show that the AVs converge to a minimum achievable subset of features with both the datasets, i.e., 24 out of 2166 (99%) in MAV and 4 out of 8 (50%) in WESAD, respectively, preserving the informative content of data.

IEEE transactions on vehicular technology 71 (9), pp. 9937–9950

Keywords

Federated learning, Feature selection, Distributed learning, Mutual information

CNR authors

Gotta Alberto, Valerio Lorenzo, Cassara Pietro

CNR institutes

IIT – Istituto di informatica e telematica, ISTI – Istituto di scienza e tecnologie dell'informazione "Alessandro Faedo"