Federated learning (FL) is emerging as a new paradigm to train machine learning models in distributed systems. Rather than sharing, and disclosing, the training dataset with the server, the model parameters (e.g. neural networks weights and biases) are optimized collectively by large populations of interconnected devices, acting as local learners. FL can be applied to power-constrained IoT devices with slow and sporadic connections. In addition, it does not need data to be exported to third parties, preserving privacy. Despite these benefits, a main limit of existing approaches is the centralized optimization which relies on a server for aggregation and fusion of local parameters; this has the drawback of a single point of failure and scaling issues for increasing network size. The paper proposes a fully distributed (or server-less) learning approach: the proposed FL algorithms leverage the cooperation of devices that perform data operations inside the network by iterating local computations and mutual interactions via consensus-based methods. The approach lays the groundwork for integration of FL within 5G and beyond networks characterized by decentralized connectivity and computing, with intelligence distributed over the end-devices. The proposed methodology is verified by experimental datasets collected inside an industrial IoT environment.

Classical and centralized Artificial Intelligence (AI) methods require moving data from producers (sensors, machines) to energy hungry data centers, raising environmental concerns due to computational and communication resource demands, while violating privacy. Emerging alternatives to mitigate such high energy costs propose to efficiently distribute, or federate, the learning tasks across devices, which are typically low-power. This paper proposes a novel framework for the analysis of energy and carbon footprints in distributed and federated learning (FL). The proposed framework quantifies both the energy footprints and the carbon equivalent emissions for vanilla FL methods and consensus-based fully decentralized approaches. We discuss optimal bounds and operational points that support green FL designs and underpin their sustainability assessment. Two case studies from emerging 5G industry verticals are analyzed: these quantify the environmental footprints of continual and reinforcement learning setups, where the training process is repeated periodically for continuous improvements. For all cases, sustainability of distributed learning relies on the fulfillment of specific requirements on communication efficiency and learner population size. Energy and test accuracy should be also traded off considering the model and the data footprints for the targeted industrial applications.

Wireless propagation is conventionally considered as the enabling tool for transporting information in digital communications. However, recent research has shown that the perturbations of the same electromagnetic (EM) fields that are adopted for data transmission can be used as a powerful sensing tool for device-free radio vision. Applications range from human body motion detection and localization to passive gesture recognition. In line with the current evolution of mobile phone sensing [1], radio terminals are not only ubiquitous communication interfaces, but they also incorporate novel or augmented sensing potential, capable of acquiring an accurate human-scale understanding of space and motion. This article shows how radio-frequency (RF) signals can be employed to provide a device-free environmental vision and investigates the detection and tracking capabilities for potential benefits in daily life.

Fall detection and localization of human operators inside a workspace are major issues in ensuring a safe working environment. Recent research has shown that the perturbations of the radio-frequency (RF) signals commonly adopted for wireless communications can also be used as sensing tools for device-free human motion detection. Device-free RF-based human sensing applications range from tag-less body localization to detection and monitoring of human well-being (e-Health). In this paper, we propose a real-time system for human body motion sensing with special focus on joint body localization and fall detection. The proposed system continuously monitors and processes the RF signals emitted by industry-compliant radio devices operating in the 2.4 GHz ISM band and supporting machine-to-machine communication functions. Human-induced diffraction and multipath phenomena that affect RF signal propagation are leveraged for body localization while for fall detection a hidden Markov model is applied to discern different postures of the operator and to detect safety-relevant events by tracking the received signal strength indicator footprints. Fall detection performances are corroborated by extensive experimental measurements in different settings. In addition, we propose also a sensor fusion tool that is able to integrate the device-free RF-based sensing system within an industrial image sensors framework. Preliminary results, conducted during field trial measurements, confirm the effectiveness of the proposed approach in terms of localization accuracy, and sensitivity/specificity to correctly detect a fall event from preimpact postures.

This paper deals with the problem of radio localization of moving terminals (MTs) for indoor applications with mixed line-of-sight/non-line-of-sight (LOS/NLOS) conditions. To reduce false localizations, a grid-based Bayesian approach is proposed to jointly track the sequence of the positions and the sight conditions of the MT. This method is based on the assumption that both the MT position and the sight condition are Markov chains whose state is hidden in the received signals [hidden Markov model (HMM)]. The observations used for the HMM localization are obtained from the power-delay profile of the received signals. In ultrawideband (UWB) systems, the use of the whole power-delay profile, rather than the total power only, allows to reach higher localization accuracy, as the power-profile is a joint measurement of time of arrival and power. Numerical results show that the proposed HMM method improves the accuracy of localization with respect to conventional ranging methods, especially in mixed LOS/NLOS indoor environments