• Automated analysis methods for semantic reasoners in Mobile Edge Computing. • On an Android device, 6 reasoners analyzed on correctness, time and memory usage. • Correctness, time, memory and energy footprint of 3 reasoners tested on a single-board computer. • Hardware-based and software-based energy profilers have been used and compared. • Multiplatform automated benchmarking tool for semantic reasoners upgraded. The integration of Semantic Web technologies into Mobile Edge Computing (MEC) platforms is enhancing the capabilities of real-time, context-aware applications across diverse domains. MEC brings processing closer to the network edge, reducing latency and allowing for the improvement of data privacy, while Semantic Web technologies provide machine-interpretable knowledge representation and reasoning capabilities. Despite their potential, deploying semantic reasoners on edge devices is challenging due to their resource-intensive nature, which requires significant memory availability, computational power, and energy. Furthermore, correctness, performance and energy consumption are simultaneously important, as MEC semantics-based applications often call for real-time queries for autonomous agent decision or user-oriented decision support. This paper presents an extensive experimental evaluation of Web Ontology Language (OWL) reasoners deployed in MEC environments, assessing correctness, processing time, memory usage, and energy consumption across both a reference tablet and a single-board computer. For energy measurement, both software profiling and hardware monitoring have been exploited and compared. The study is supported by a modular, cross-platform benchmarking framework that automates data collection and ensures reproducibility. The findings highlight the trade-offs between reasoning capabilities and resource consumption, offering valuable insights for refining testing methodologies as well as optimizing semantic reasoners in MEC settings.

As an application and service platform, the World Wide Web spans from simple informational websites to rich social media and Software-as-a-Service (SaaS) clients. While innovative capabilities are increasingly provided by Deep Learning (DL) Artificial Intelligence (AI) architectures such as pre-trained trans-formers, so far Web applications and services have integrated them only via cloud-based implementations. Deep-Learning-as-a-Service (DLaaS) is establishing itself for professional and personal use, with prevalent business models including pay-per-use and monthly subscriptions. With growing concerns over data privacy, response latency, and service costs, executing DL inference directly within the user's browser appears as a com-pelling alternative to cloud-based solutions. This paper introduces local intelligence via Browser Extension for Real- Time applications (liBERTa), a modular browser extension-based architecture for real-time client-side DL inference. By operating entirely within the browser, liBERTa reduces reliance on external servers. Its modular design consists of independent layers for data extraction, model inference, and results presentation, granting flexibility and adaptability across different kinds of applications and services. Experimental results from a case study on website privacy policy classification demonstrate the feasibility of the approach, showing that lightweight transformer models can achieve competitive accuracy while maintaining inference times suitable for real-world use on commodity hardware.

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.

Mobile reasoners play a pivotal role in the so-called Semantic Web of Things. While several tools exist for the Android platform, iOS has been neglected so far. This is due to architectural differences and unavailability of OWL manipulation libraries, which make porting existing engines harder. This paper presents Mini-ME Swift, the first Description Logics reasoner for iOS. It implements standard (Subsumption, Satisfiability, Classification, Consistency) and non-standard (Abduction, Contraction, Covering, Difference) inferences in an OWL 2 fragment. Peculiarities are discussed and performance results are presented, comparing Mini-ME Swift with other state-of-the-art OWL reasoners.