Giuseppe Loseto

• PhD in Information Engineering
• PostDoc Position at Polytechnic University of Bari

Due to the rapid expansion of e-commerce and urbanization, Last-Mile Delivery (LMD) faces increasing challenges related to cost, timeliness, and sustainability. Artificial intelligence (AI) techniques are widely used to optimize fleet management, while augmented and mixed reality (AR/MR) technologies are being adopted to enhance warehouse operation...

Industrial Internet of Things (IIoT) is becoming increasingly important for companies world-wide since it allows integrating data from different areas and sectors, thus creating new opportunities to raise efficiency, flexibility, and productivity. However, IIoT also exposes companies to new risks and threats, which implies new challenges related to...

(Full-text: https://doi.org/10.1016/j.iot.2024.101439) The ever-complex information environments and rapidly expanding data volumes of the modern digital infrastructure demand efficient knowledge organization and retrieval techniques. The Semantic Web initiative has defined principles and technologies, such as the Resource Description Framework (RD...

Highlights What are the main findings? Novel data-driven and knowledge-based energy digital-twin framework integrating a Retrieval-Augmented Generation (RAG) approach. Prototype applied to a real-world scenario involving the management of high-voltage energy infrastructures, showcasing the framework feasibility and effectiveness in operational envi...

Emerging distributed intelligence paradigms for the Internet of Things (IoT) call for flexible and dynamic reconfiguration of elementary services, resources and devices. In order to achieve such capability, this paper faces complex interoperability and autonomous decision problems by proposing a thorough framework based on the integration of the Se...

Artificial Intelligence (AI) models can issue smart, context-sensitive recommendations to help patients self-manage their illnesses, including medication regimens, dietary habits, physical activity, and avoiding flare-ups. Instead of merely positing an “edict,” the AI model can also explain why the recommendation was issued: why one should stay ind...

In the Semantic Web of Everything, observation data collected from sensors and devices disseminated in smart environments must be annotated in order to produce a Knowledge Base (KB) or Knowledge Graph (KG) which can be used subsequently for inference. Available approaches allow defining complex data models for mapping tabular data to KBs/KGs: while...

The World Wide Web is increasingly adopted as an application development platform in desktop and mobile contexts. As a building block of the Semantic Web of Everything vision, reasoning engines should be able to run in the client side of Web applications without resorting to remote servers for inference tasks. In order to fill a gap in the availabi...

Machine Learning (ML) is increasingly exploited in a wide range of application areas to analyze data streams from large-scale sensor networks, train predictive models and perform inference. The Cloud-Edge Intelligence (CEI) computing paradigm integrates cloud infrastructures for resource-intensive ML tasks with devices at the border of a local ne...

(Full text: http://sisinflab.poliba.it/Publications/2023/LSRGIFBLD23) Artificial Intelligence (AI) in Cyber-Physical Systems allows machine learning inference on acquired data with ever greater accuracy, thanks to models trained with massive amounts of information generated by Internet of Things devices. Edge Intelligence is increasingly adopted to...

(Full text: http://sisinflab.poliba.it/Publications/2023/LSRGB23) Video streaming accounts for the majority of worldwide Internet traffic, and HTTP-based multimedia has the largest share among technologies and protocols. The wide availability of mobile devices and wireless broadband networks currently leads to wider heterogeneity of fruition contex...

The integration of blockchain platforms with Artificial Intelligence (AI) technologies is increasingly frequent in research and industry. Semantic Web technologies provide peculiar opportunities, since they have been devised for information interoperability at Web scale and enable intelligent software agents for knowledge-driven task automation and...

It is challenging for programmers to build a mobile health app that is rich in AI features, and near impossible for non-technical users such as domain experts and patients. However, it is exactly these users that possess the domain knowledge and experience on how to best manage health conditions, and how AI features can help achieve that goal. End-...

There is an increasing shift towards the self-management of long-term chronic illness by patients in a home setting, supported by personal health electronic equipment. Among others, self-management requires comprehensive education on the illness, i.e., understanding the effects of nutritional, fitness, and medication choices on personal health; and...

Artificial Intelligence (AI) in Cyber-Physical Systems allows machine learning inference on acquired data with ever greater accuracy, thanks to models trained with massive amounts of information generated by Internet of Things devices. Edge Intelligence is increasingly adopted to execute inference on data at the border of local networks, exploiting...

(Full text: http://sisinflab.poliba.it/Publications/2022/RSBGLIP22) The Internet of Everything and Semantic Web can be joined by giving more intelligence to pervasive systems. To that end, reasoning capabilities should be enabled even for very resource-constrained embedded devices. This paper presents Tiny-ME (the Tiny Matchmaking Engine), a matchm...

Modern smartphones offer advanced sensing, connectivity, and processing capabilities for data acquisition, processing, and generation: but it can be difficult and costly to develop mobile research apps that leverage these features. Nevertheless, in life sciences and other scientific domains, there often exists a need to develop advanced mobile apps...

The benefits of automatic identification technologies in healthcare have been largely recognized. Nevertheless, unlocking their potential to support the most knowledge-intensive medical tasks requires to go beyond mere item identification. This paper presents an innovative Decision Support System (DSS), based on a semantic enhancement of Near Field...

Background Systemic Sclerosis (SSc) is a connective tissue disease characterized by severe alterations in the microvasculature and progressive fibrosis of the skin and internal organs [1]. Management of SSc is not easy, for both patients and physicians [2]. Symptoms are manifold and have a significant impact on patient’s daily autonomy and psycholo...

The Semantic Web of Things (SWoT) integrates knowledge representation and reasoning techniques originally devised for the Semantic Web into Internet of Things architectures, in order to provide more advanced service/resource management and discovery. This paper proposes a novel SWoT framework, enabling collaborative discovery of sensors and actuato...

Novel Internet of Things (IoT) applications and services rely on an intelligent understanding of the environment leveraging data gathered via heterogeneous sensors and micro-devices. Though increasingly effective, Machine Learning (ML) techniques generally do not go beyond classification of events with opaque labels, lacking machine-understandable...

Ambient Intelligence aims at simplifying the interaction of a user with her surrounding context, minimizing the effort needed to increase comfort and assistance. Nevertheless, especially in built and structured environments, current technologies and market solutions are often far from providing the required levels of automation, coordination and ad...

ThePhysical Semantic Web (PSW) is a novel paradigm built upon the Google Physical Web (PW) approach and devoted to improve the quality of interactions in the Web of Things. Beacons expose semantic annotations instead of basic identifiers, ıe\ machine-understandable descriptions of physical resources. This enables novel ontology-based object adverti...

The Semantic Web of Things (SWoT) aims to support smart semantics-enabled applications and services in pervasive contexts. Due to architectural and performance issues, most Semantic Web reasoners are often impractical to be ported: they are resource consuming and are basically designed for standard inference tasks on large ontologies. On the contra...

This paper proposes a novel Semantic Web of Things framework, enabling collaborative discovery of sensors and actuators in pervasive contexts. It is based on a backward-compatible extension of the Constrained Application Protocol (CoAP), supporting advanced semantic matchmaking via non-standard inference services. The framework also integrates effi...

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...

The Physical Semantic Web is proposed as an enhancement to the Google Physical Web approach for the Internet of Things. It allows associating beacons to semantic annotations (instead of trivial identifiers), in order to enable more powerful expressiveness in human-things and things-things interactions. This paper presents a general frame-work for t...

The paper proposes a knowledge-based framework for mobile autonomous robots. It exploits data annotation for semantic-based context description. High-level event/situation detection and action decision are performed through a semantic matchmaking approach, supporting approximate matches and relevance-based ranking. The framework was fully implement...

The Linked Data Platform (LDP) W3C Recommendation defined resource management primitives for HTTP only, pushing into the background not-negligible use cases related to Web of Things (WoT) scenarios where HTTP-based communication and infras- tructures are unfeasible. This paper proposes a mapping of the LDP specification for Constrained Application...

This paper proposes a mapping of the Linked Data Platform (LDP) specification for Constrained Application Protocol (CoAP). Main motivation stems from the fact that LDP W3C Recommendation presents resource management primitives for HTTP only. A general translation of LDP-HTTP requests and responses is provided, as well as a framework for HTTP-to-CoA...

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...

Pervasive applications and services are increasingly based on the intelligent interpretation of data gathered via heterogeneous sensors dipped in the environment. Classical Machine Learning (ML) techniques often do not go beyond a basic classification, lacking a meaningful representation of the detected events. This paper introduces a early proposa...

The pursuit of new tools for monitoring the quality level of any kind of perishable product, in particular food, along all the supply chain, answers to the demand of reducing losses and waste and thus guaranteeing both customers’ safety and satisfaction and vendors’ interests. The combination of sensors with the wireless network technology offers a...

This paper summarizes all research advancements obtained by the Politecnico di Bari through the RES NOVAE Project activities in the field of the smart grids. Such activities have been aimed at bringing substantial contributions in the development of smart grid in medium-voltage and low-voltage distribution systems. Since the scientific approach to...

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...

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-ag...

The Semantic Web of Things (SWoT) vision aims to provide more advanced resource management and discovery w.r.t. standard Internet of Things architectures, by means of the integration of knowledge representation and reasoning techniques originally devised for the Semantic Web. This paper proposes a novel SWoT framework, based on a backward-compatibl...

The integration of knowledge representation and reasoning techniques (originally devised for the Semantic Web) in most common Wireless Sensor Networks (WSNs) protocols can allow to reach higher levels of autonomicity w.r.t. classic network architectures that basically provide only simplistic discovery capabilities. This paper presents a complete Se...

Nowadays smartphones play a significant role in gathering relevant data about their owners. Micro-devices embedded in Personal Digital Assistants (PDAs) perform a continuous sensing, the phone call lists, PIM (Personal Information Manager), text messages and so on allow to collect and mine data enough for a high-level description of daily activitie...

The Semantic Web of Things (SWoT) blends the Semantic Web and the Internet of Things visions. Due to architectural and performance issues, it is currently impractical to use available reasoners for processing semantic-based information in pervasive computing scenarios. This paper presents a prototypical mobile matchmaker for the SWoT, supporting Se...

Reasoning in pervasive computing has to face computational issues inherited by mobile platforms. This paper presents a prototypical reasoner for mobile devices, which leverages Semantic Web technologies to implement both standard (subsumption, satisfiability, classification) and non-standard (abduction, contraction) inferences for moderately expres...

Current mobile systems for assisted navigation have limited effectiveness in satisfying user needs. The information content supporting location-based service discovery and path calculation is usually shallow. Semantic-based technologies can allow to overcome these limitations, by exploiting more accurate and meaningful descriptions of locations, po...

Ambient Intelligence aims at autonomic coordination and control of appliances and subsystems located in a given environment. Home and Building Automation (HBA) complies with this paradigm but it is based on an explicit interaction with the user and a static set of operational scenarios. This paper pro-poses a more flexible multi-agent approach, lev...

Main restraints curbing a deep integration of Semantic Sensor Networks with complex and articulated architectures, basically residein too elementary allowed discovery capabilities. Several studies agree advanced querying and retrieval mechanisms are needed to truly fulfill the potential of the SSN paradigm. This paper presents a novel SSN framework...

The Semantic Web of Things (SWoT) is a novel paradigm, blending the Semantic Web and the Internet of Things visions. Due to architectural and performance issues, it is currently impractical to use available reasoners for processing semantic-based information and perform resource discovery in pervasive computing scenarios. This paper presents a prot...

Home and building automation aims at improving features and capabilities of household systems and appliances. Nevertheless, cur- rent solutions poorly support dynamic scenarios and context-awareness. The integration of knowledge representation features and reasoning tech- niques (originally devised for the Semantic Web) into standard home automatio...

This paper describes a knowledge-based framework for a driving assistance via smartphone. Vehicle information extracted through On Board Diagnostics (OBD-II) protocol, data acquired from smartphone embedded micro-devices and information retrieved from the Web are properly combined. Data fusion and classification algorithms allow to identify and ann...

Domotics aims to improve features and capabilities of building systems and appliances. In spite of increasing self-management of electrical equipments, current solutions refer to static scenarios and require an explicit and elementary interaction with the user. Hence the real pervasiveness and context-awareness of enabled functions is still poor. T...

The paper proposes an integrated framework which uses knowledge representation theory and languages to annotate relevant product information in a semantically rich and unambiguous fashion so disclosing several added-value services in multiple supply chain stages, without depending on a back-end in-frastructure. EPCglobal RFID protocol standard has...

The integration of knowledge representation languages and reasoning techniques (originally devised for the Semantic Web) into stan-dard home automation protocols can allow to offer high-level services to users. A semantic-based approach is proposed, able to interface users and devices (whose features are expressed by means of semantically anno-tate...

Current technologies for Home and Building Automation (HBA) require an explicit interaction with the user and allow a static set of operational scenarios, defined during system implementation. More flexible HBA solutions are needed to enable the so-called Ambient Intelligence, permitting an automatic coordination and control of appliances and sub-s...