Paulo Figueiras

Discovering semantic relations from unstructured data for ontology enrichment: Asssociation rules based approach

Ontologies have been used in information system development as one of the main knowledge representation tool. Ontologies are composed by concepts, a hierarchy, arbitrary relations between concepts, and possibly other axioms. However, ontology building is a time-consuming process, and it should be supported by automatic finding of interesting, possible relationships among concepts. This paper describes how an analysis of co-occurrences of concepts in unstructured sources of information can be used to provide interesting relationships for enriching ontological structures. We apply association rule theory to construct ontological concept relations and evaluate the importance of such relations for supporting the building process of a domain ontology. Preliminary results were collected using scientific published papers from the building and construction sector, which were used as an input for applying our method. A knowledge browsing environment was developed in order to support the analysis process.

An architecture for big data processing on intelligent transportation systems. An application scenario on highway traffic flows

The transportation sector, and in particularly intelligent transportation systems, generate large volumes of real-time data that needs to be managed, communicated, interpreted, aggregated, and analyzed. To this end, innovative big data processing and mining as well as optimization techniques, need to be developed and applied in order to support real-time decision-making capabilities. Towards this end, this paper presents an ETL (extract, transform and load) architecture for intelligent transportation systems, addressing an application scenario on dynamic toll charging for highways. The ETL approach presented here, is responsible for preparing the data to be used by traffic prediction services, which will dynamically affect toll prices within different contexts. The proposed architecture relies on the adoption of “big data” technologies, to process and store large volumes of data from heterogeneous sources, provided by different highway operators. The proposed architecture is capable of handling real-time and historical data using big data technologies such as Spark on Hadoop and MongoDB. The DATEX-II data model is adopted, in order to harmonize traffic data provided by the highway operators. The work presented here, is still part of ongoing work currently addressed under the EU H2020 OPTIMUM project. Preliminary results achieved so far do not address the final conclusions of the project, but enabled us to demonstrate considerable gains in performance, when compared to other traditional ETL approaches, and also form the basis for pointing out and discuss future work directions and opportunities in the area of the development of big data processing and mining methods under the ITS domain.

Personalized Intelligent Mobility Platform: An Enrichment Approach Using Social Media

This chapter aims to present a technical approach for developing a personalized mobility knowledge base supported by mechanisms for extracting and processing tweets related with traffic events, in order to support highly specific assistance and recommendations to urban commuters. In order to address a personalized mobility knowledge base, a step-wise approach is presented with the purpose of construction and enriching a knowledge model from heterogeneous data sources providing real-time information via Personal Digital Assistants (PDAs). The approach presented is decomposed into several steps, starting from data collection and knowledge base formalization targeting the development of a personalized intelligent route planner, enabling a more efficient decision support to urban commuters. The work presented here, is still part of ongoing work currently addressed under the EU FP7 MobiS project. Results achieved so far do not address the final conclusions of the project but form the basis for the formalization of the domain knowledge do be acquired.

Data Processing and Harmonization for Intelligent Transportation Systems: An Application Scenario on Highway Traffic Flows

In the advent of ITS (Intelligent Transportation Systems) the transportation sector generates large volumes of real-time data that needs to be collected, harmonized, interpreted, aggregated, and analysed. To this end, innovative big data processing and mining, together with optimization techniques, need to be developed and applied to better support real-time decision-making capabilities. This chapter presents an ETL (Extract-Transform-Load) architecture for intelligent transportation systems, addressing an application scenario on dynamic toll charging for highways. The ETL approach presented is responsible for preparing the data to be used by traffic prediction services, which will dynamically affect toll prices within different contexts. It relies on the adoption of “big data” technologies, to process and store large volumes of data from heterogeneous sources, provided by different highway operators, and is capable of handling real-time and historical data. The DATEX-II data model is adopted, enabling harmonization of traffic data provided by the highway operators.

Ontological Interaction Using JENA and SPARQL Applied to Onto-AmazonTimber Ontology

Knowledge representation and use are fundamental processes in many areas. The use of a semantic referential (i.e, a domain ontology and a set of related tools to exploit it) to represent knowledge has allowed the development of new mechanisms of semantic search, inferences, and analysis of complex content, but the development of a semantic referential is still a complex task, time-consuming and fundamentally performed by knowledge holders. Taking that into account this work discusses the development of a semantic referential applied to botanical identification process in the Brazilian Amazon area, mainly focused on the mechanisms of interaction and access to a domain ontology (named Onto-AmazonTimber) based on JENA API and SPARQL queries. The main aspects of the development of this work are presented and discussed here. Current challenges and open points are also addressed.

An Approach for Detecting Traffic Events Using Social Media

Nowadays almost everyone has access to mobile devices that offer better processing capabilities and access to new information and services, the Web is undoubtedly the best tool for sharing content, especially through social networks. Web content enhanced by mobile capabilities, enable the gathering and aggregation of information that can be useful for our everyday lives as, for example, in urban mobility where personalized real-time traffic information, can heavily influence users’ travel habits, thus contributing for a better way of living. Current navigation systems fall short in several ways in order to satisfy the need to process and reason upon such volumes of data, namely, to accurately provide information about urban traffic in real-time and the possibility to personalize the information presented to users. The work presented here describes an approach to integrate, fuse and process tweet messages from traffic agencies, with the objective of detecting the geographical span of traffic events, such as accidents or road works. Tweet messages are considered in this work given their uniqueness, their real time nature, which may be used to quickly detect a traffic event, and their simplicity. We also address some imprecisions ranging from lack of geographical information, imprecise and ambiguous toponyms, overlaps and repetitions as well as visualization to our data set in the UK, and a qualitative study on the use of the approach using tweets in other languages, such as Greek. Finally, we present an application scenario, where traffic information is processed from tweets massages, triggering personalized notifications to users through Google Cloud Messaging on Android smartphones. The work presented here is still part of on-going work. Results achieved so far do not address the final conclusions but form the basis for the formalization of a domain knowledge along with the urban mobility services.

Big Data Harmonization for Intelligent Mobility: A Dynamic Toll-Charging Scenario

The need for interoperability in mobility data is more crucial than ever. Due to a panoply of data sources, from traffic sensors to GPS data, mobility data is increasingly more complex in terms of volume, heterogeneity, availability and quality. To turn such complex data into shareable, meaningful data, interoperability approaches must be implemented, namely through the use of standards. The presented work, aims at developing an approach for transforming and harmonize, traffic related data acquired from highway sensor network, supported by an ITS reference data model (DATEX-II). CRISP-DM methodology is addressed here, as a methodology for guiding the developments of the proposed approach. The main challenge is to cope with a scalable big data- platform for traffic-related data collection, supporting an innovative dynamic toll-charging model in a real-world scenario. This work is supported by a European Commission-funded project, named OPTIMUM, and presents some preliminary results from data harmonization processes developed.

Understanding Personal Mobility Patterns for Proactive Recommendations

This paper proposes an innovative methodology for extracting and learning personal mobility patterns. The objective is to award daily commuters in a city with personalized and proactive recommendations, related with their mobility habits on a daily basis. In currently approaches, users have to explicitly provide their routes (origin, destination and date/time) to a routing engine in order to be notified about traffic events. The proposed approach goes beyond and learns daily mobility habits from the users, without the need to provide any information. The work presented here, is currently being addressed under the EU OPTIMUM project. Results achieved establish the basis for the formalization of the OPTIMUM domain knowledge on personal mobility patterns.

A Semantic Enrichment Approach Based on the Vector Space Model Supporting Collaboration in the Manufacturing Domain

Knowledge is a word that can have multiple definitions, one can think of it as information, understanding or skill that you get from previous experiences or education. In the business world, independently of the size of the companies, knowledge is without any doubt power. If in one hand the access to internal knowledge is crucial to support better decision and management strategies, on the other, when knowledge is shared by means of collaboration between partnered companies it could be the negotiations empowering base.This work presents a knowledge gathering, enrichment and sharing approach, based on concepts such as Information Retrieval, Knowledge Management and Semantic technologies, that envisions to help Manufacturing Industry companies, engaged in collaborative e-procurement tasks, to share and gain easy and fast access to crucial knowledge.The presented work was created and validated in Building & Construction domain and will be integrated in Horizon 2020 C2NET project in the Manufacturing domain. Namely, the relevant achievements pursued by this work are the following: (i) conceptualization of a model that enables the semantic enrichment of knowledge sources supported by domain experts; and (ii) implementation of a proof-of-concept focusing on the Manufacturing Industry context.Copyright