Search

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 representation and explanation of taxonomies. This paper proposes a framework for semantic-enhanced data mining on sensor streams, amenable to resource-constrained pervasive contexts. It merges an ontology-based characterization of data distributions with non-standard reasoning for a fine-grained event detection. The typical classification problem of ML is treated as a resource discovery by exploiting semantic matchmaking. Outputs of classification are endowed with computer-processable descriptions in standard Semantic Web languages, while explanation of matchmaking outcomes motivates confidence on results. A case study on road and traffic analysis has allowed to validate the proposal and achieve an assessment with respect to state-of-the-art ML algorithms.

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 adaptivity. Devices should interact autonomously, should reach opportunistic decisions and take actions accordingly. In particular, user activities and profiles should be among the manifold implicitfactors to be taken into account in that process. Home and Building Automation (HBA) is one of the most relevant scenarios suffering from the poorness of the allowed system intelligence, automation and adaptivity. Devices are logically associated through static profiles defined at system deployment stage. The large majority of solutions are proprietary and centralized, and require manual configuration. This paper proposes a novel semantic-based framework complying with the emerging Social Internet of Things paradigm. Infrastructured spaces can be intended as populated by device agents organized in social networks, interacting autonomously and sharing information, cooperating and orchestrating resources. A service-oriented architecture allows collaborative dissemination, discovery and composition of service/resource descriptions. Semantic Web languages are adopted as knowledge representation layer and mobile-oriented implementations of non-monotonic inferences for semantic matchmaking are used to give decision capabilities to software agents. Finally, the Linked Data Platform (LDP) over the Constrained Application Protocol (CoAP) provides the knowledge organization and sharing infrastructure underpinning social object interactions. The framework has been implemented and tested in a home automation prototype integrating several communication protocols and off-the-shelf devices. Experiments advocate the effectiveness of the approach.

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 accurate and meaningful descriptions of locations, Points of Interest (POIs), road segments and environmental conditions. We present here a general framework leveraging an enriched cartography, which may be useful not only to enhance travel satisfaction and safety, but also to regulate vehicle efficiency, traffic and environmental impact.

The Augmented Reality (AR) is often said to have the potential for a revolution in the way we discover Points Of Interest (POIs) and experience our cities. Nevertheless, to date the AR promise has only partially become true, because the information content supporting location-based resource discovery is usually shallow. Semantic-based technologies allow expressing rich, accurate and meaningful descriptions of POIs, so helping in improving the quality of discovery.

We investigate on the possibility of transforming concepts in Description Logics into relational databases and queries in such a way that subsumption between the original concepts can be decided as query answering over a database. For the positive results, we show a translation of ${\cal ALN}$-concepts into pairs (database, query) such that, in order to decide Subsumption $C \sqsubseteq D$one evaluates the query resulting from the translation of D over the database resulting from C. For the negative results, we show that no compilation is possible for expressive Description Logics.

We propose a novel object discovery framework integrating the application layer of Bluetooth and RFID standards. The approach is motivated and illustrated in an innovative u-commerce setting. Given a request, it allows an advanced discovery process, exploiting semantically annotated descriptions of goods available in the u-marketplace. The RFID data exchange protocol and the Bluetooth service discovery protocol have been modified and enhanced to enable support for such semantic annotation of products. Modifications to the standards have been conceived to be backward compatible, thus allowing the smooth coexistence of the legacy discovery and/or identification features. Also noteworthy is the introduction of a dedicated compression tool to reduce storage/transmission problems due to the verbosity of XML-based semantic languages.

We propose a framework and tractable algorithms for semantic-based automated Web service composition, fully compliant with Semantic Web technologies. The approach exploits the recently proposed Concept Abduction inference service in Description Logics to extend Concept covering definition to expressive logics, and to solve Concept Covering problems in a significant subset of OWL-DL. We show how the proposed approach also deals with not-exact solutions, computing an approximate composition and providing an explanation of which part of the request is not covered by the composite service. We present the formalization of the approach, the proposed algorithms, a prototype system implementing the approach, and illustrate experiments carried out with it.

We propose to extend standard Radio Frequency IDentification (RFID) usage by storing semantically annotated data within RFID tags memory, so that objects may actually 'describe themselves' in a variety of scenarios. In particular here we exploit our approach to carry out an advanced matchmaking process using metadata stored in RFIDs. A 'fully backward compatible' modification to the original RFID data exchange protocol is presented, allowing to implement an advanced resource discovery framework. A compression algorithm specifically devised to ease embedding of annotated DIG description is also proposed. Motivations and benefits of the approach are outlined in a tracking of agricultural and food products case study.

In this paper, we present a novel resource discovery framework for m-commerce. We extend the original Bluetooth service discovery protocol by integrating a semantic layer within the application level of the standard. Given a request, this layer makes possible an enhanced discovery process exploiting the semantics of the resource descriptions exposed by a hotspot. The enhancement is compatible with the basic discovery protocol, thus allowing the smooth coexistence of the service discovery approaches. We present and motivate our semantic-based discovery protocol in an innovative m-commerce framework and show its benefits.

We propose a knowledge representation approach to the semantic retrieval by content of graphics described in Scalable Vector Graphics (SVG), the novel XML based W3C approved standard language for describing two-dimensional graphics. The approach is based on a description logic devised for the semantic indexing and retrieval of complex objects. We provide a syntax to describe basic shapes, complex objects as compositions of basic ones, and transformations. An extensional semantics, which is compositional, is introduced for defining retrieval, classification, and subsumption services. Algorithms exploiting reasoning services, which are sound with respect to the semantics, are also described. Using our logical approach as a formal specification, we implemented a prototype system. A set of experiments, carried out on a testbed of SVGdocuments to assess the retrieval capabilities of the system, is presented.

Subband coding is a well-established technique. Coding algorithms, however, rarely try to exploit residual similarities between subbands in order to get both coding gain and improvement in visual appearance. In this work we propose a simple postprocessing technique for edge enhancement and ringing-artifact reduction in subband-coded images. The proposed technique employs morphological filtering for preliminary image simplification and uses a novel dual-window nonlinear operator for subsequent edge enhancement. Visual appearance and numerical results confirm the validity of the approach. A simple coding scheme, designed to test the efficiency of the approach, gives good results. © 2001 Society of Photo-Optical Instrumentation Engineers.

Content-based image retrieval systems are being actively investigated owing to their ability to retrieve images based on the actual visual content rather than by manually associated textual descriptions. This paper considers the issues related to the porting of such systems to the World Wide Web and proposes some ways to solve them. To substantiate our ideas, we propose a web-based image retrieval system that allows the user to express a query as a simple sketch portraying ‘what’ she/he is looking for. The system relies on a three-layer relevance feedback architecture to progressively refine retrieval results according to the user's preferences. We also emphasize the use of the vector space model for features representation and the cosine distance for similarity ranking. Performances are presented using both well-assessed information retrieval measures and subjective evaluation criteria.

In this article we describe the results of a study on similarity evaluation in image retrieval using color, object orientation, and relative position as content features, in a framework oriented to image repositories where the semantics of stored images are limited to a specific domain. The focus is not on a complete description of image content, which is supposed to be known to some extent, but on the extraction of simple and immediate features that can assure, through their combination, automated image analysis and efficient retrieval. Relevance feedback is introduced as an effective way to improve retrieval accuracy. A simple prototype system is also introduced that computes feature descriptors and allows users to enter queries, browse the retrieved images, and refine the results through relevance feedback analysis. © 1998 SPIE and IS&T.