Tools

Sisinf Lab logo
SisInfLab people interviewed by Radio Frequenza Libera

Dr. Michele Ruta and SWoT@SisInfLab people interviewed in The cornerD programme of Radio Frequenza Libera on Monday, February 3rd.

The podcast is available here or can be listened through the Music Bar on top of SWoT website.



The Semantic Web of Things (SWoT) is an emerging vision in Information and Communication Technology (ICT), joining together some of the most important paradigms of the decade: the Semantic Web and the Internet of Things.
The Semantic Web initiative [1] aims at allowing available information in the World Wide Web to be seamlessly shared, reused and combined by software agents. Each available resource in the semantic-enabled Web should be properly described in order to infer new information from the one stated in the semantically annotated resource descriptions.
The Internet of Things vision [2] promotes on a global scale the ubiquitous computing paradigm. In ubiquitous and pervasive contexts, intelligence is embedded into objects and physical locations by means of a large number of heterogeneous micro-devices, such as RFID tags or sensors, each conveying a small amount of information. Due to space, power and cost constraints, devices are usually endowed with very low storage, little or no processing capabilities and short-range, low-throughput wireless links allowing only a simple service/resource fruition.
Ideas and technologies borrowed from the Semantic Web vision may allow to overcome these limitations. In fact the SWoT vision enables knowledge-based systems that achieve high degrees of autonomic capability for information storage, management and discovery, also providing transparent access to information sources in a given area.

References:

  1. T. Berners-Lee, J. Hendler, O. Lassila, The semantic Web, Scientific American 284 (5) (2001) 28-37.
  2. ITU, Internet Reports 2005: The Internet of Things (November 2005).


Mini-ME - the Mini Matchmaking Engine

Due to architectural and performance reasons, it is currently unfeasible or impractical to use available Semantic Web reasoners in the Semantic Web of Things. Therefore we are developing a prototypical mobile reasoner for the SWoT. It supports standard Semantic Web technologies through the OWL API and implements both standard reasoning tasks for knowledge base (KB) management (subsumption, classification, satisfiability) and non-standard inference services for semantic-based matchmaking and resource ranking (abduction and contraction). Mini-ME is developed in Java, adopting Android as the current target computing platform, but running also on Java SE.


Kinect posture and gesture recognition

We are developing a framework for automated posture and gesture detection, exploiting depth data from Microsoft Kinect. The recognition problem is handled as a resource discovery. An ontology for geometry-based semantic description of postures has been developed and encapsulated in a Knowledge Base (KB), also including several instances representing pose and gesture templates to be detected. Each key posture is annotated adopting standard Semantic Web languages. Semantic-based matchmaking allows to compare the retrieved annotations with templates populating the Knowledge Base and a similarity-based ranking supports the discovery of the best matching posture. The ontology further allows to annotate a gesture from its component key postures, in order to enable recognition of gestures in a similar way.


iDriveSafe 1.0

iDriveSafe 1.0 is a mobile Apple iPhone application for semantic-enhanced real-time car diagnostics and driving assistance. The system is able to identify specific high-level events and conditions, based on low-level data streams such as vehicle health and safety equipments; environmental factors and driving style. Exploiting Semantic Web techniques and technologies, events are semantically annotated w.r.t. an ontology modeling factors influencing driving safety. Annotated descriptions undergo a semantic matchmaking process which is able to discover all possible risk factors. The matchmaking outcome is used to suggest the driver actions and behaviors she can adopt in order to minimize risks.


iDriveSafe 2.0

iDriveSafe 2.0 is an evolution of the first version that supports also the measurement of exhaust emissions, fuel consumption and autonomy and engine load. The system is able to evaluate driving performance, environmental impact and risk level, and to suggest users how to reduce or even eliminate danger by exploiting a semantic-based matchmaking. Improvements have been performed in the design of the user interface that is now formed by a set of coloured icons. Each icon changes her colour depending on the semantic matchmaking results and emits an acoustic signal to inform drivers.


Mobile User Profiler

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 activities of a user.
A smart profiling agent has been proposed able to perform an automated profile annotation by adopting Semantic Web languages. The crawler agent runs on the user smartphone and performs a multimodal (i.e., involving several heterogeneous data sources) and continuous sensing collecting and processing information without human intervention. The multimodality requires specialized analyses for each kind of collected data. The agent mines the user habits automatically and annotates them in a logic-based formalism to build a daily profile to be further exploited in context-aware knowledge-based applications.


Smart Building Automation

Home and Building Automation (HBA) is a growing research and industrial sector attracting efforts from several disciplines, coalescing into a research area known as Ambient Intelligence (AmI). The integration of knowledge representation languages and reasoning techniques (originally devised for the Semantic Web) into standard home automation protocols can allow to offer high-level services to users and to adapt the environment dynamically and automatically to varying conditions, overcoming limitations of current implementations based on preset conditions. Exploiting semantic-based matchmaking, the user profile can be compared with house configuration (which includes devices settings and appliances behavior), so identifying the home features best fitting user needs. Furthermore, household equipments are autonomously able to reach the status better satisfying users' activities or device requirements.


Semantic POI Annotation with JOSM




We are currently developing a prototypical software tool for editing semantic-based annotations of OpenStreetMap points of interest (POIs), through a fully visual user interface based on simple drag-and-drop operations. We chose to extend the open source JOSM (Java OpenStreetMap editor) application.
Thanks to an easily understandable GUI, our tool can make any OpenStreetMap contributor capable of enriching maps along the Semantic Web / Linked Open Data vision. No specific knowledge of Semantic Web languages and underlying logic-based formalisms is required.


BE-free@campus: Barriers and Exclusion-free at campus




BE-free@campus: Barriers and Exclusion-free at campus project aims to provide a personal assisted navigation to disabled people within the Polytechnic of Bari facilities of the university campus. A fully functional tool was developed for Android mobile devices.
The embedded OsmAnd routing engine takes advantage of the crowd-sourced OpenStreetMap project, whose maps has been enriched with new tags providing accessibility data. The engine has been extended in order to provide multi-level indoor navigation.
The crowd-sourcing approach is also adopted to let users view indoor maps on any web browser. The open source project OSMTools is extended.


Semantic Sensor Networks




Main restraints curbing a deep integration of Semantic Sensor Networks (SSNs) with complex and articulated architectures, basically reside in too elementary allowed discovery capabilities.
The proposed approach presents a novel SSN framework, supporting a resource discovery grounded on semantic-based matchmaking. Offered contributions are: (i) a backward-compatible extension of Constrained Application Protocol (CoAP) resource discovery; (ii) data mining exploitation to detect high-level events from raw data; (iii) employment of non-standard inference services for retrieving and ranking resources; (iv) adoption of W3C standard SSN-XG ontology to annotate data, events and device features.

Contacts


Valid XHTML 1.1   Valid CSS

:: hosted by SisInf Lab http://sisinflab.poliba.it ::