Pythagoras Karampiperis

Applying Semantic Web technologies to improve the retrieval, credibility and use of health-related web resources.

The number of health-related websites is increasing day-by-day; however, their quality is variable and difficult to assess. Various “trust marks” and filtering portals have been created in order to assist consumers in retrieving quality medical information. Consumers are using search engines as the main tool to get health information; however, the major problem is that the meaning of the web content is not machine-readable in the sense that computers cannot understand words and sentences as humans can. In addition, trust marks are invisible to search engines, thus limiting their usefulness in practice. During the last five years there have been different attempts to use Semantic Web tools to label health-related web resources to help internet users identify trustworthy resources. This paper discusses how Semantic Web technologies can be applied in practice to generate machine-readable labels and display their content, as well as to empower end-users by providing them with the infrastructure for expressing and sharing their opinions on the quality of health-related web resources.

The BigDataEurope Platform – Supporting the Variety Dimension of Big Data

The management and analysis of large-scale datasets – described with the term Big Data – involves the three classic dimensions volume, velocity and variety. While the former two are well supported by a plethora of software components, the variety dimension is still rather neglected. We present the BDE platform – an easy-to-deploy, easy-to-use and adaptable (cluster-based and standalone) platform for the execution of big data components and tools like Hadoop, Spark, Flink, Flume and Cassandra. The BDE platform was designed based upon the requirements gathered from seven of the societal challenges put forward by the European Commission in the Horizon 2020 programme and targeted by the BigDataEurope pilots. As a result, the BDE platform allows to perform a variety of Big Data flow tasks like message passing, storage, analysis or publishing. To facilitate the processing of heterogeneous data, a particular innovation of the platform is the Semantic Layer, which allows to directly process RDF data and to map and transform arbitrary data into RDF. The advantages of the BDE platform are demonstrated through seven pilots, each focusing on a major societal challenge.

ER designer toolkit: a graphical event definition authoring tool

Currently there exist several tools for Complex Event Recognition, varying from design platforms for business process modeling (BPM) to advanced Complex Event Processing (CEP) engines. Several efforts have been reported in literature aiming to support domain experts in the process of defining event recognition (ER) rules. However, few of them offer graphical design environments for the definition of such rules, limiting the broad adoption of ER systems. In this paper, we present a graphical Event Definition Authoring Tool, referred to as the Event Recognition Designer Toolkit (ERDT) with which, a domain expert can easily design event recognition rules on temporal data and produce standalone Event Recognizers.

Enhancing the Levenberg-Marquardt Method in Neural Network training using the direct computation of the Error Cost Function Hessian

The Levenberg-Marquardt (LM) algorithm is a very popular training method in Neural Networks due to its accuracy and robustness. LM outperforms gradient based methods that use direct calculation of the first derivative of the error cost function through back-propagation. In this paper we will examine how the direct computation of the diagonal elements of the Hessian matrix of the error cost function can be used to improve the performance of the original LM algorithm.

Data-Driven Schema Matching in Agricultural Learning Object Repositories

As the wealth of structured repositories of educational content for agricultural object is increasing, the problem of heterogeneity between them on a semantic level is becoming more prominent. Ontology matching is a technique that helps to identify the correspondences on the description schemas of different sources and provide the basis for interesting applications that exploit the information in a linked fashion. The present paper presents a data-driven approach for discovering matches between different classification schemas. The approach is based on content analysis and linguistic processing in order to extract information in the form of relation tuples, use the extracted information to associate the content of different repositories and match their underlying classification schemas based on the degree of content similarity. The preliminary results verified the validity of the approach, as both experiments produced a semantically valid matching in 68% of the examined classes. The results also exposed the need for refinements on the linguistic processing of the available textual information and on the definition of relation similarity, as well as, the need to exploit structural information in order to move from discovering semantically valid matches to effectively handling class specializations and generalizations.

Using Open Information Extraction and Linked Open Data towards Ontology Enrichment and Alignment

The interlinking, maintenance and updating of different Linked Data repositories is steadily becoming a critical issue as the amount of published data increases. The wealth of information across the World Wide Web can be exploited in order to provide additional information about the way that an object is described in the real world. This paper proposes a method for discovering new concepts and examining the equivalence of properties in different LOD description schemas by using Open Information Extraction techniques on web resources. The method relies on constructing association graphs from the extracted information, proceeding to a transfer on the conceptual level using information previously known from the LOD repositories and examining the similarities and discrepancies between the produced graphs and the LOD descriptions, as well as between the graphs derived from different repositories.

User-Oriented Content Retrieval Using Image Segmentation Techniques

The need for applying advanced social information retrieval techniques for personalizing web-based information discovery has been identified as a key challenge. Until now, significant R&D effort has been devoted aiming towards applying collaborative filtering techniques for educational content retrieval. However, limited attention has been given to the use of educational metadata as a mean to enhance social filtering techniques via educationally informed filtering decisions. In this paper we propose the use of an add-on filtering service on existing social filtering systems/applications so as to create a data post-filtering mechanism that makes use of intelligence stored in TEL metadata. The proposed methodology starts with the generation of a matrix that represents the educational characteristics of the resources suggested by typical social filtering techniques and applies post-filtering using the educational “footprint” of the resources already used by the targeted end-user.

POWDER as Enabling Technology for the Semantic Interoperability of Agricultural Repositories

Current approaches to the interoperability of heterogeneous resources typically maintain coordinated clones over which querying infrastructure operates. In the case of large-scale repositories, and especially when no single schema is clearly established so that the problem can be reduced to transforming legacy data, a more dynamic approach would be a benefit. In many real-world situation, however, useful queries need to combine information from different sources that are actively maintained in incompatible schemata and are too large to systematically clone. Examples include the various agricultural resource repositories and databases such as meteorological archives and GIS. In this position paper we explore the applicability of the W3C Protocol for Web Description Resources (POWDER) as infrastructure for the efficient and distributed retrieval of the meta-information needed to dynamically re-write queries in one schema to the (set of) semantically equivalent queries that need to be executed over the various heterogeneous schemata. This enables information providers to publish information in any schema as long as POWDER is used to annotate their repository with the coordination-related meta-information. Querying engines can then exploit existing and established resource discovery mechanisms implemented over the POWDER protocol to retrieve the meta-information pertinent to any single triple pattern in a query and use that to dynamically perform query rewriting.

Special issue on semantic descriptions of medical web resources: technologies to support their creation, maintenance and access.

The internet is designed for direct use by people searching for information through their browsers; accessing health-related information has never been easier. The increasing amount of freelyavailable, health-related web content creates, on the one hand, excellent conditions for selfeducation of patients as well as physicians but, on the other hand, however, it entails substantial risks if such information is trusted, irrespective of the low competence, or even bad intentions, of its authors. Furthermore, it is difficult for health information consumers, such as patients and the general public, to assess, by themselves, the quality of the information, as they are not always familiar with medical domains and vocabularies. Semantic Web technologies have been proposed as a way to address this problem. The Semantic Web is “an extension of the current Web in which information is given a well-defined meaning, better enabling computers and people to work in cooperation”. It is based on metadata; that is, on semantic annotations of web content. These metadata can be expressed in different ways using the Resource Description Framework (RDF) language and Web Ontology Language. Using these standardized languages, which express both data and rules for connecting and reasoning about the data, it is possible to create machine-processable descriptions (labels) of web resources. To support patients and consumers in retrieving suitable information sources, a number of quality labelling initiatives have been developed across Europe. 6 One approach is the “trust mark” method, where a third-party agency ascertains, on a regular basis, whether the quality of the information on the website is acceptable or not. Another approach is when a third-party authority selects, or filters, websites for the public to use. Both approaches can be supported with the use of Semantic Web tools and metadata that facilitate health-related web resources description, classification and retrieval. The aim of this special issue of Health Informatics Journal is to reflect progress in the use of Semantic Web techniques for the description of health-related web resources and to outline the major challenges and future prospects. It builds on the 1 International Workshop on Describing Medical Web Resources (DRMed 2008), held in conjunction with the 21 International Congress of the European Federation for Medical Informatics (MIE 2008). The four papers selected after a peer review process, cover the major topics targeted by this special issue: