The Smart Mobility vision calls for dynamic resource and service discovery to cope with the intrinsic topology volatility of Internet of Things (IoT) platforms without sacrificing the required business continuity and service flexibility. For an extended automation of collaboration within and across enterprise boundaries, trust management is equally important, granting security, reliability and scalability at the same time. To tackle the above challenges, this paper proposes the integration of a semantic-based service management layer in an IoT infrastructure grounded on the Hyperledger Sawtooth blockchain. Every service in the outlined framework is annotated with reference to a domain ontology, so that smart contracts can exploit knowledge representation and non-standard reasoning for service registration, discovery, outcomes explanation and service selection. A case study on power management of Plug-in Electric Vehicles (PEVs) is proposed to clarify the benefits of the proposal. Early performance evaluation results support the feasibility and sustainability of the approach.

• Five-star framework to assess On-Device AI in Internet of Everything scenarios • Mafalda 2.0 federated incremental learning model with semantic explainability • Evaluation of Mafalda 2.0 against state-of-the-art On-Device AI approaches • Concrete examples of global and local explainability and federated learning As the Internet of Things (IoT) evolves into an Internet of Everything (IoE), adapting Artificial Intelligence (AI) and Machine Learning (ML) approaches to pervasive computing devices is not enough. Collaborative intelligence is required, calling for on-device AI frameworks combining adequate accuracy and computational efficiency levels with incremental learning on continuous data streams, federated learning in distributed architectures and symbolic explainability formalisms to foster trustworthiness with interpretable trained models and comprehensible prediction outcomes. To fill this gap, the paper introduces a five-star rating for on-device AI based on the Semantic Web of Everything (SWoE) paradigm, and presents the five-star Mafalda 2.0 framework. It combines statistical data processing with Knowledge Graph technologies for information representation and automated reasoning to support: semi-automatic or fully data-driven ontology definition; on-device training to generate highly interpretable semantics-based models; prediction framed as a semantic matchmaking problem, exploiting non-standard reasoning services endowed with logic-based justifications to provide comprehensible results as well as counterfactual and contrastive explanations. An experimental campaign on four publicly available datasets has been carried out to validate the efficiency and accuracy of the proposal, along with federated learning and explainability examples.

The evolution of metering technologies has enabled the collection of a vast amount of energy consumption data, offering new opportunities for more efficient energy management. While utility providers increasingly leverage machine learning and data visualization to simplify and optimize data analysis, current systems often present barriers in understanding collected data. This paper introduces a novel multi-agent architecture that integrates Large Language Models (LLMs) to enhance the interpretability of smart meter data. Developed within the Digital Enterprise initiative by Lutech S.p.A., the proposed framework enables natural language interactions and the generation of energy-related reports. An early evaluation has been conducted through a series of basic interaction tests, demonstrating the feasibility of the approach and its potential to improve data-driven decision-making.

Hyperautomation aims to digitize end-to-end business processes, but most of the current solutions and platforms still rely on pre-defined workflows to carry out complex tasks. However, business process automation can greatly benefit from recent technological innovations at the intersection of Large Language Models (LLMs) and Multi-Agent systems (MAS). In this paper, we present an Agentic Artificial Intelligence (AI) framework where a central LLM-driven orchestrator dynamically plans and delegates tasks to specialized LLM agents, which in turn exploit tools to act on business platforms and other external systems. A case study based on document management illustrates how the approach is able to deal with complex requests involving source file parsing and report generation, leveraging an approach based on Retrieval Augmented Generation (RAG) to enable knowledge sharing among specialized agents. Finally, the proposed framework introduces a practical blueprint for scalable, explainable Agentic AI in enterprise hyperautomation environments.

Serverless computing enables greater flexibility and efficiency in the cloud-to-edge continuum. Artificial Intelligence and Machine Learning (AI/ML) applications benefit greatly from this paradigm, as they need to gather, preprocess, aggregate and analyze data at various scales. In such contexts, the increasing hardware/software resource availability of Internet of Things (IoT) devices provides the opportunity to exploit them not only as data sources in AI/ML infrastructures, but also as computational nodes for model training and inference; nevertheless, comprehensive frameworks are still mostly missing. This work introduces an innovative serverless computing architecture which expands the cloud-to-edge continuum toward IoT devices. The same functions can run on IoT, edge and cloud nodes with minimal to no code modification and they can be invoked through a uniform interface. A federated learning framework is defined based on the proposed architecture, exploiting an existing IoT-oriented ML algorithm in a novel way. Notably, IoT nodes are used for both federated training and local inference tasks. A full prototype implementation has been built with off-the-shelf technologies and devices. A case study on federated machine learning for activity recognition and experiments have been conducted to validate key elements of the proposal.

The progress of building automation devices and networks is curbed by application models with limited device autonomy, static configuration scenarios, and frequent explicit user interaction. This paper presents a novel approach inspired to social network interactions for increased object self-configuration and self-orchestration in home and building automation. Objects become autonomous social agents, interacting and coordinating automatically as new information about the environment is available. The framework is grounded on a service-oriented architecture for encapsulating, exchanging, and composing device capabilities and on semantic-based service description, discovery and aggregation exploiting nonstandard inference services. The proposed approach was implemented in two different testbeds and experimental evaluations of feasibility and performance were carried out with respect to a home automation case study.

The Semantic Web and Internet of Things visions are converging toward the so-called Semantic Web of Things (SWoT). It aims to enable smart semantic-enabled applications and services in ubiquitous contexts. Due to architectural and performance issues, it is currently impractical to use existing Semantic Web reasoners. They are resource consuming and are basically optimized for standard inference tasks on large ontologies. On the contrary, SWoT use cases generally require quick decision support through semantic matchmaking in resource-constrained environments. This paper presents Mini-ME, a novel mobile inference engine designed from the ground up for the SWoT. It supports Semantic Web technologies and implements both standard (subsumption, satisfiability, classification) and non-standard (abduction, contraction, covering) inference services for moderately expressive knowledge bases. In addition to an architectural and functional description, usage scenarios are presented and an experimental performance evaluation is provided both on a PC testbed (against other popular Semantic Web reasoners) and on a smartphone.

Home and building automation (HBA) trends toward the Ambient Intelligence paradigm, which aims to autonomously coordinate and control appliances and subsystems in a given environment. Nevertheless, HBA is based on an explicit user-home interaction and basically enables static and predetermined scenarios. This paper proposes a more flexible multi-agent approach, leveraging semantic-based resource discovery and orchestration for HBA applications. Backward-compatible enhancements to EIB/KNX domotic standard allow to support the semantic characterization of user profiles and device functionalities, thus enabling: 1) negotiation of the most suitable home services/functionalities according to implicit and explicit user needs and 2) device-driven interaction for adapting the environment to context evolution. A power-management problem in HBA is presented as a case study to better clarify the proposal and assess its effectiveness.

Current technologies for Home and Building Automation (HBA) basically require an explicit interaction with the user and allow a static set of operational scenarios defined during system implementation. On the contrary, novel HBA solutions should enable so-called ambient intelligence, deriving from a flexible and automatic control of appliances and subsystems dipped into an environment. To this aim, this paper proposes backward-compatible enhancements to one of the most widespread domotic standards, i.e., EIB/KNX ISO/IEC 14543-3, able to support advanced, knowledge-based and context-aware functionalities, grounded on the semantic annotation of both user profiles and device capabilities. Such an approach enables novel resource discovery, matchmaking, and decision support features in HBA. Main benefits are in: (i) determining the most suitable services/functionalities according to implicit and explicit user needs and (ii) allowing device-driven interaction for autonomous adaptation of the environment to context modification. A case study is presented to better clarify the proposed framework also highlighting main characteristics, while performance evaluation is provided to assess its effectiveness.