arXiv subjects

Fabio Bonsignorio

Publications and source records attributed to Fabio Bonsignorio.

6 recordsLinked to original sources

arXiv2026

Constrained Bayesian Optimization for Hierarchical Federated Learning in IoT Networks for Plant Disease Classification

The deployment of Hierarchical Federated Learning (HFL) in resource-constrained Internet of Things (IoT) environments requires careful configuration to balance predictive performance with energy consumption and execution time. This challenge is particularly relevant to smart agriculture, where distributed IoT devices can support automated plant disease classification while operating under limited computational and communication resources. This paper presents a constrained Bayesian Optimization framework for the efficient configuration of HFL deployments. The proposed approach jointly explores the deep learning backbone architecture, aggregation strategy, and number of communication rounds, while the federation size is determined according to the spatial coverage requirements of the agricultural deployment. A weighted objective function captures user-defined trade-offs among energy consumption, execution time, and predictive performance, while explicit constraints ensure compliance with deployment-specific resource and accuracy requirements. The framework is evaluated on an IoT-based plant disease classification task considering multiple deep learning architectures, federated aggregation strategies, and communication-round settings. Experimental results across 30 independent optimization runs show that the proposed approach explores only 11.11% of the search space, while consistently identifying solutions within 1% of the exhaustive-search optimum, with a mean optimality gap of only 0.056%.

cs.LG↗

arXiv2026

Performance and Energy Trade-Off Analysis of Hierarchical Federated Learning for Plant Disease Classification

Early detection of plant diseases is critical for improving crop productivity, while it also facilitates the foundations of precision agriculture. Recent advances in distributed deep learning have enabled plant disease classification models to be trained across geographically distributed agricultural sensing infrastructures. However, deploying such systems in large-scale Internet of Things (IoT) environments, introduces significant challenges related to computational cost, energy consumption, and system efficiency. In this paper, we present a design-space exploration of hierarchical federated learning architectures for plant disease classification, with a particular focus on the trade-offs between predictive performance and energy efficiency. We further introduce a power- and energy-aware optimization framework that enables the systematic evaluation and selection of model-aggregator configurations under varying deployment constraints. The hierarchical federated architecture organizes distributed clients through intermediate aggregation layers, reducing communication and computational overhead. We evaluate multiple convolutional neural network architectures, including EfficientNet-B0, ResNet-50, and MobileNetV3-Large, in combination with different federated aggregation strategies such as FedAvg, FedProx, and FedAvgM. Experimental results demonstrate that different model-aggregator combinations exhibit distinct performance-energy trade-offs. Consequently, we highlight configurations that achieve competitive diagnostic accuracy and significantly reduce system resource requirements.

cs.DC↗

arXiv2025

An Active Inference Model of Covert and Overt Visual Attention

The ability to selectively attend to relevant stimuli while filtering out distractions is essential for agents that process complex, high-dimensional sensory input. This paper introduces a model of covert and overt visual attention through the framework of active inference, utilizing dynamic optimization of sensory precisions to minimize free-energy. The model determines visual sensory precisions based on both current environmental beliefs and sensory input, influencing attentional allocation in both covert and overt modalities. To test the effectiveness of the model, we analyze its behavior in the Posner cueing task and a simple target focus task using two-dimensional(2D) visual data. Reaction times are measured to investigate the interplay between exogenous and endogenous attention, as well as valid and invalid cueing. The results show that exogenous and valid cues generally lead to faster reaction times compared to endogenous and invalid cues. Furthermore, the model exhibits behavior similar to inhibition of return, where previously attended locations become suppressed after a specific cue-target onset asynchrony interval. Lastly, we investigate different aspects of overt attention and show that involuntary, reflexive saccades occur faster than intentional ones, but at the expense of adaptability.

cs.CV↗

arXiv2024

GISR: Geometric Initialization and Silhouette-based Refinement for Single-View Robot Pose and Configuration Estimation

In autonomous robotics, measurement of the robot's internal state and perception of its environment, including interaction with other agents such as collaborative robots, are essential. Estimating the pose of the robot arm from a single view has the potential to replace classical eye-to-hand calibration approaches and is particularly attractive for online estimation and dynamic environments. In addition to its pose, recovering the robot configuration provides a complete spatial understanding of the observed robot that can be used to anticipate the actions of other agents in advanced robotics use cases. Furthermore, this additional redundancy enables the planning and execution of recovery protocols in case of sensor failures or external disturbances. We introduce GISR - a deep configuration and robot-to-camera pose estimation method that prioritizes execution in real-time. GISR consists of two modules: (i) a geometric initialization module that efficiently computes an approximate robot pose and configuration, and (ii) a deep iterative silhouette-based refinement module that arrives at a final solution in just a few iterations. We evaluate GISR on publicly available data and show that it outperforms existing methods of the same class in terms of both speed and accuracy, and can compete with approaches that rely on ground-truth proprioception and recover only the pose.

cs.RO↗

arXiv2020

Site-selection criteria for the Einstein Telescope

The Einstein Telescope (ET) is a proposed next-generation, underground gravitational-wave (GW) detector to be based in Europe. It will provide about an order of magnitude sensitivity increase with respect to currently operating detectors, and furthermore, extend the observation band towards lower frequencies, i.e., down to about 3Hz. One of the first decisions that needs to be made is about the future ET site following an in-depth site characterization. Site evaluation and selection is a complicated process, which takes into account science, financial, political, and socio-economic criteria. In this paper, we provide an overview of the site-selection criteria for ET, provide a formalism to evaluate the direct impact of environmental noise on ET sensitivity, and outline the necessary elements of a site-characterization campaign.

physics.ins-det↗

arXiv2012

Quantifying the Evolutionary Self Structuring of Embodied Cognitive Networks

We outline a possible theoretical framework for the quantitative modeling of networked embodied cognitive systems. We notice that: 1) information self structuring through sensory-motor coordination does not deterministically occur in Rn vector space, a generic multivariable space, but in SE(3), the group structure of the possible motions of a body in space; 2) it happens in a stochastic open ended environment. These observations may simplify, at the price of a certain abstraction, the modeling and the design of self organization processes based on the maximization of some informational measures, such as mutual information. Furthermore, by providing closed form or computationally lighter algorithms, it may significantly reduce the computational burden of their implementation. We propose a modeling framework which aims to give new tools for the design of networks of new artificial self organizing, embodied and intelligent agents and the reverse engineering of natural ones. At this point, it represents much a theoretical conjecture and it has still to be experimentally verified whether this model will be useful in practice..

nlin.AO↗