Pierpaolo Tommasi

Predicting Severity of Road Traffic Congestion Using Semantic Web Technologies

Predictive reasoning, or the problem of estimating future observations given some historical information, is an important inference task for obtaining insight on cities and supporting efficient urban planning. This paper, focusing on transportation, presents how severity of road traffic congestion can be predicted using semantic Web technologies. In particular we present a system which integrates numerous sensors (exposing heterogenous, exogenous and raw data streams such as weather information, road works, city events or incidents) to improve accuracy and consistency of traffic congestion prediction. Our prototype of semantics-aware prediction, being used and experimented currently by traffic controllers in Dublin City Ireland, works efficiently with real, live and heterogeneous stream data. The experiments have shown accurate and consistent prediction of road traffic conditions, main benefits of the semantic encoding.

Smart traffic analytics in the semantic web with STAR-CITY

This paper gives a high-level presentation of STAR-CITY, a system supporting semantic traffic analytics and reasoning for city. STAR-CITY, which integrates (human and machine-based) sensor data using variety of formats, velocities and volumes, has been designed to provide insight on historical and real-time traffic conditions, all supporting efficient urban planning. Our system demonstrates how the severity of road traffic congestion can be smoothly analyzed, diagnosed, explored and predicted using semantic web technologies. Our prototype of semantics-aware traffic analytics and reasoning, illustrated and experimented in Dublin Ireland, but also tested in Bologna Italy, Miami USA and Rio Brazil works and scales efficiently with real, historical together with live and heterogeneous stream data. This paper highlights the lessons learned from deploying and using a system in Dublin City based on Semantic Web technologies.

STAR-CITY: semantic traffic analytics and reasoning for CITY

This paper presents STAR-CITY, a system supporting semantic traffic analytics and reasoning for city. STAR-CITY, which integrates (human and machine-based) sensor data using variety of formats, velocities and volumes, has been designed to provide insight on historical and real-time traffic conditions, all supporting efficient urban planning. Our system demonstrates how the severity of road traffic congestion can be smoothly analyzed, diagnosed, explored and predicted using semantic web technologies. We present how semantic diagnosis and predictive reasoning, both using and interpreting semantics of data to deliver useful, accurate and consistent inferences, have been exploited and adapted systematized in an intelligent user interface. Our prototype of semantics-aware traffic analytics and reasoning, experimented in Dublin City Ireland, works and scales efficiently with historical together with real live and heterogeneous stream data.

QuerioDALI: Question Answering Over Dynamic and Linked Knowledge Graphs

We present a domain-agnostic system for Question Answering over multiple semi-structured and possibly linked datasets without the need of a training corpus. The system is motivated by an industry use-case where Enterprise Data needs to be combined with a large body of Open Data to fulfill information needs not satisfied by prescribed application data models. Our proposed Question Answering pipeline combines existing components with novel methods to perform, in turn, linguistic analysis of a query, named entity extraction, entity/graph search, fusion and ranking of possible answers. We evaluate QuerioDALI with two open-domain benchmarks and a biomedical one over Linked Open Data sources, and show that our system produces comparable results to systems that require training data and are domain-dependent. In addition, we analyze the current challenges and shortcomings.

Data Access Linking and Integration with DALI: Building a Safety Net for an Ocean of City Data

DALI is a practical system that exploits Linked Data to provide federated entity search and spatial exploration across hundreds of information sources containing Open and Enterprise data pertaining to cities, which are stored in tabular files or in their original enterprise systems. Our system is able to lift data into a meaningful linked structure with explicit semantics, and support novel contextual search and retrieval tasks by identifying related entities across models and data sources. We evaluate in two pilot scenarios. In the first, data-engineers bring together public and enterprise datasets about public safety. In the second, knowledge-engineers and domain-experts, build a view of health and social care providers for vulnerable populations. We show that our approach can re-use data assets and provides better results than pure text-based approaches in finding relevant information, as well as satisfying specific information needs.

Improving cross-domain information sharing in care coordination using semantic web technologies

We present an approach to access and consolidate complex information spanning multiple specialist domains and make it available to non-experts. We are using a combination of business rules and contextual exploration to reduce interface complexity and improve consumability. We present a use case and a prototype on top of a real-world enterprise solution for coordinating Social care and Health care. We evaluate our system through a user study. Our results indicate that our approach reduces the time required to obtain business results compared to a baseline graph exploration approach.

Finding mr and mrs entity in the city of knowledge

More and more urban data is published every day, and consequently, consumers want to take advantage of this body of knowledge. Unfortunately, metadata and schema information around this content is sparse. To effectively fulfill user information needs, systems must be able to capture user intent and context in order to evolve beyond current search and exploration techniques. A Linked Data approach is uniquely positioned to surface information and provide interoperability across a diversity of information sources, from consumer data residing in the original enterprise systems, to relevant open city data in tabular form. We present a prototype for contextual knowledge mining that enables federated access and querying of entities across hundreds of enterprise and open datasets pertaining to cities. The proposed system is able to (1) lift raw tabular data into a connected and meaningful structure, contextualized within the Web of Data, and (2) support novel search and exploration tasks, by identifying closely related entities across datasets and models. Our user experiments and prototype show how semantics, used to consolidate city information and reuse assets from the Web of Data, improve dataset search and provide users effective means to explore related entities and content to fit their information needs.

Note Highlights: Surfacing Relevant Concepts from Unstructured Notes for Health Professionals

Health and social care professionals are under increasing pressure to assimilate the ever-growing volume of data from case notes and electronic medical records. In this paper, we propose and evaluate with domain experts a cognitive system for patient-centric care that leverages and combines natural language processing, semantics, and learning from users over time to support care professionals making informed and timely decisions while reducing the burden of interacting with large volumes of unstructured patient notes. We propose methods for highlighting the entities embedded in the unstructured data and providing a personalized view of an individual. We evaluate through a user study and show a consensus between what the domain experts and the system consider relevant and discuss early feedback on the value of our Note Highlights methods to domain experts.

On-Demand Integration and Linking of Open Data Information

This paper introduces an extension of DALI, a framework for data integration and visualisation. When integrating new data, DALI automatically tries to recognise the schema and contents of the file, semantically lift them, and annotate them with existing ontologies. The extension presented in this paper allows users to import data from external data portals, namely portals using CKAN or Socrata, based on the results of a search query or by selecting individual datasets. Furthermore, we perform a semantic expansion of the search terms provided by the user in order to identify datasets that might still be relevant while not containing the exact search terms.

A linked data approach to care coordination

The success of a society is often judged by its ability to support the most vulnerable. Supporting the most vulnerable individuals is extremely challenging from an information needs perspective, since it requires data from numerous domains and systems, including Social Care, Healthcare, Public Safety and Juridical systems. Information sharing on this scale gives rise to scientific and technical challenges with regard to data representation, access, integration and retrieval granularity. This is a practice-oriented paper presenting a Linked Data-based approach that is uniquely positioned to access and surface information across domains and data sources using a combination of vulnerability indexes and contextual exploration. We apply this approach on a set of enterprise systems from IBM to develop an information sharing architecture and prototype for Care Coordination with a focus on Social Care and Healthcare. We report on expert feedback and user studies that indicate that our approach indeed reduces the time required to gain some business insight while maintaining the flexibility of a Linked Data-based integration approach.