Until recently tactical analysis in elite soccer were based on observational data using variables which discard most contextual information. Analyses of team tactics require however detailed data from various sources including technical skill, individual physiological performance, and team formations among others to represent the complex processes underlying team tactical behavior. Accordingly, little is known about how these different factors influence team tactical behavior in elite soccer. In parts, this has also been due to the lack of available data. Increasingly however, detailed game logs obtained through next-generation tracking technologies in addition to physiological training data collected through novel miniature sensor technologies have become available for research. This leads however to the opposite problem where the shear amount of data becomes an obstacle in itself as methodological guidelines as well as theoretical modelling of tactical decision making in team sports is lacking. The present paper discusses how big data and modern machine learning technologies may help to address these issues and aid in developing a theoretical model for tactical decision making in team sports. As experience from medical applications show, significant organizational obstacles regarding data governance and access to technologies must be overcome first. The present work discusses these issues with respect to tactical analyses in elite soccer and propose a technological stack which aims to introduce big data technologies into elite soccer research. The proposed approach could also serve as a guideline for other sports science domains as increasing data size is becoming a wide-spread phenomenon.

/pdf/big-data-and-tactical-analysis-in-elite-soccer-future-2pu4o8bjc4.pdf

Big data and tactical analysis in elite soccer: future challenges and opportunities for sports science

Knowledge representation is a long-standing research area of computer science that aims at representing human knowledge in a form that computers can interpret. Most knowledge representation approaches, however, have suffered from poor user interfaces. It turns out to be difficult for users to learn and use the logic-based languages in which the knowledge has to be encoded. A new approach to design more intuitive but still reliable user interfaces for knowledge representation systems is the use of controlled natural language (CNL). CNLs are subsets of natural languages that are restricted in a way that allows their automatic translation into formal logic. A number of CNLs have been developed but the resulting tools are mostly just prototypes so far. Furthermore, nobody has yet been able to provide strong evidence that CNLs are indeed easier to understand than other logic-based languages. The goal of this thesis is to give the research area of CNLs for knowledge representation a shift in perspective: from the present explorative and proof-of-concept-based approaches to a more engineering-focussed point of view. For this reason, I introduce theoretical and practical building blocks for the design and application of controlled English for the purpose of knowledge representation. I first show how CNLs can be defined in an adequate and simple way by the introduction of a novel grammar notation and I describe efficient algorithms to process such grammars. I then demonstrate how these theoretical concepts can be implemented and how CNLs can be embedded in knowledge representation tools so that they provide intuitive and powerful user interfaces that are accessible even to untrained users. Finally, I discuss how the understandability of CNLs can be evaluated. I argue that the understandability of CNLs cannot be assessed reliably with existing approaches, and for this reason I introduce a novel testing framework. Experiments based on this framework show that CNLs are not only easier to understand than comparable languages but also need less time to be learned and are preferred by users.

/pdf/controlled-english-for-knowledge-representation-5fw5uv6629.pdf

Controlled English for knowledge representation

http://www.johnbreslin.org/files/publications/20100622_cii_2010.pdf

Semantic Web computing in industry

Dengue infection is a mosquitoborne disease caused by dengue viruses, which are carried by several species of mosquito of the genus Aedes , principally Ae. aegypti . Dengue outbreaks are endemic in tropical and sub-tropical regions of the world, mainly in urban and sub-urban areas. The outbreak is one of the top 10 diseases causing the most deaths worldwide. According to the World Health Organization, dengue infection has increased 30-fold globally over the past five decades. About 50–100 million new infections occur annually in more than 80 countries. Many researchers are working on measures to prevent and control the spread. One avenue of research is collaboration between computer science and the epidemiology researchers in developing methods of predicting potential outbreaks of dengue infection. An important research objective is to develop models that enable, or enhance, forecasting of outbreaks of dengue, giving medical professionals the opportunity to develop plans for handling the outbreak, well in advance. Researchers have been gathering and analyzing data to better identify the relational factors driving the spread of the disease, as well as the development of a variety of methods of predictive modeling using statistical and mathematical analysis and machine learning. In this substantial review of the literature on the state of the art of research over the past decades, we identified six main issues to be explored and analyzed: 1) the available data sources; 2) data preparation techniques; 3) data representations; 4) forecasting models and methods; 5) dengue forecasting models evaluation approaches; and 6) future challenges and possibilities in forecasting modeling of dengue outbreaks. Our comprehensive exploration of the issues provides a valuable information foundation for new researchers in this important area of public health research and epidemiology.

Dengue Epidemics Prediction: A Survey of the State-of-the-Art Based on Data Science Processes

With the rapid growth in number and dimension of databases and database applications in business, administrative, industrial and other fields, it is necessary to examine the automatic extraction of knowledge from these large databases. Due to knowledge extraction from databases, these have become rich and safe sources for generating and verification of knowledge, and the knowledge discovery can be applied in software management, querying process, making decisions, process control and many other fields of interest. At the same time, there is a challenge in managing unstructured data. Among organizations with large concentration of unstructured information, there is a greater tendency to devote more resources to this kind of data. The acquisition of knowledge from unstructured data is often difficult and expensive. Some possible solutions on extracting useful information (knowledge) from unstructured data are provided. Knowledge extraction is the process of creation of knowledge from structured, unstructured and semi-structured data. The objective of this paper is to present the possibilities of extracting knowledge from unstructured and semi-structured data particularly. The theories and tools for knowledge extraction are the subject of the emerging field of knowledge discovery in databases (KDD). Definitions of KDD are provided and the general multistep KDD process is outlined. A brief summary of recent KDD real-world applications is also provided. Finally, the article enumerates challenges for future research and development in KDD systems.

Converting unstructured and semi-structured data into knowledge

The growing impact of Semantic Wikis deduces the importance of finding a strategy to store textual articles, semantic metadata and management data. Due to their different characteristics, each data type requires a specialized storing system, as inappropriate storing reduces performance, robustness, flexibility and scalability. Hence, it is important to identify a sophisticated strategy for storing and synchronizing different types of data structures in a way they provide the best mix of the previously mentioned properties. In this paper we compare fully structured, semi-structured and unstructured data and present their typical appliance. Moreover, we discuss how all data structures can be combined and stored for one application and consider three synchronization design alternatives to keep the distributed data storages consistent. Furthermore, we present the semantic wiki KiWi, which uses an RDF triplestore in combination with a relational database as basis for the persistence of data, and discuss its concrete implementation and design decisions.

/pdf/combining-unstructured-fully-structured-and-semi-structured-59v8ebn4z3.pdf

Combining Unstructured, Fully Structured and Semi-Structured Information in Semantic Wikis.

Semantic Wikis have demonstrated the power of combining Wikis with Semantic Web technology. The KiWi system goes beyond Semantic Wikis by providing a flexible and adaptable platform for building different kinds of Social Semantic Software, powered by Semantic Web technology. This article describes the main functionalities and components of the KiWi system with respect to the user interface and to the system architecture. A particular focus is given to what we call “content versatility”, i.e. the reuse of the same content in different kinds of social software applications. The article concludes with an overview of different applications we envision can be built on top of KiWi. 1 Motivation: From Semantic Wikis to KiWi Semantic Wikis have been under investigation in the research community since 2005 (see e.g. [1,2]). Although there are many different systems with many different properties, a common trait between all Semantic Wikis is that they aim to combine ordinary wiki content and technology with Semantic Web technologies, either in order to provide better wikis (“Semantic Web for Wikis”) or to ease the creation of Semantic Web data (“Wikis for the Semantic Web”) [3]. Many also see Semantic Wikis as the “Semantic Web in a Nutshell”, because – like Wikis show similar traits to the Web as a whole – Semantic Wikis share many properties and also problems with the envisioned Semantic Web. The EU-funded project KiWi (“Knowledge in a Wiki”) takes the Semantic Wiki approach to the next level by providing a platform that allows to build many different kinds of Social Semantic Software, based on the conviction that most social software follows the “Wiki Principles”. By “Wiki Principles”, we mean that the term “Wiki” does not refer to technology alone. It is more a new philosophy of working with Web content influenced by ideas in the OpenSource community. These principles have revolutionised the way we work with content in the (Social) Web: – Wikis allow anyone to edit: The core principle is that there are no access restrictions or strict hierarchies on the content of a wiki. Anyone can easily contribute his or her own knowledge, his or her own ideas, and his or her own content. 1 http://www.kiwi-project.eu – Wikis are easy to use: Anyone who is sufficiently familiar with the basic functionalities of word processing software (write, delete, save) has all the skills required to edit, correct and expand a wiki. – Wiki content is linkable: By allowing users to create links between words and as such between concepts, wikis also allow for the creation of semantic relations, i.e. of meaning. – Wikis support versioning: Never does information disappear on a wiki. If a page is edited, the previous version is still stored somewhere. This has an important psychological effect as it takes away the wiki writer’s block: the fear that something might get lost through editing. – Wikis support all media: Wikis are web-based. So whichever type of content you have, be it text, images, audio, spreadsheets, documents – anything that can be displayed in a web browser can be displayed in a wiki. And even if a file cannot be displayed in the browser itself, it can still be downloaded. This same philosophy is underlying not only Wikis (technically-speaking), but also a large array of other Social Software applications: e.g., a weblog or social networking platform can be seen as just a different user interface (and different way of using), but is otherwise very similar concerning the underlying principles and also technology. In the following, we describe how we realised the KiWi vision in the KiWi System, a generic Semantic Social Software platform based on the Wiki principles. We begin in Section 2 with introducing the concept of what we call “Content Versatility”: content with flexible structures that can be reused in different applications. In Section 3, we then describe KiWi Core Applications: the Wiki, the Dashboard, TagIT, the KiWi Search, and the KiWi Inspector. Section 4 is dedicated to the more technical aspects of the KiWi platform: the system architecture, the data model, the KiWi entity manager, and facading. We conclude this article with an outlook and summary in Section 5. 2 Content Versatility: Same Content, Different Views As we have already outlined in the introduction, what we call the “Wiki Principles” is actually applicable to many Social Software applications. It is therefore close at hand to build generic platforms for developing different kinds of Social Software. And indeed, there are several products already available that aim to deliver a platform that allows to combine wikis, weblogs, social networking, etc. Such platforms are for example Clearspace Community from Jive Software, Community Server from telligent, and Liferay Social Office from Liferay. However, all these systems only provide integration on the user interface level and still see wiki articles, blog posts, etc. as separate kinds of content that is visualised in a specific way. This has a number of serious disadvantages. For 2 http://www.jivesoftware.com/products/clearspace-community 3 http://communityserver.com/ 4 http://www.liferay.com/web/guest/products/social_office instance, something that started as a wiki article can never become a blog post, it will never be possible to attach comments to a wiki article if not foreseen in the data model, and new kinds of content (like our TagIT locations, cf. Section 3.3) cannot be added easily without also doing fundamental changes to the system. KiWi follows a completely different approach which we call “Content Versatility”. The underlying principle is that every piece of information is a combination of human-readable content and associated metadata, and that the same piece of information can be presented to the user in many different forms: as a wiki page, as a blog post, as a comment to a blog, as a photo, or even in a bubble in a map-based application. The decision how the information is displayed is taken based on the metadata of the content, and the context of the content and the user (e.g. metadata, user preferences, different applications). Metadata is represented using RDF and thus does not require a-priori schema definitions, so the data model of the system can be extended even at runtime. In KiWi, we call the smallest piece of information a “content item”. A content item is identified by a URI and consists of human-readable content in the form of XHTML and associated metadata in the form of RDF. The KiWi core system provides means to store, update, search, and query content items, and offers automatic versioning of all updates (content and metadata). Whereas core properties of a content item (like the content, the author, and the creation date) are represented in XML and persisted in a relational database, all other properties can be flexibly defined using RDF properties or relations. The URI of a content item is generated in such a way that it is possible to make a KiWi system part of the Linked Open Data cloud [4]. This allows to easily integrate KiWi content with other services on the Semantic Web. 3 KiWi Core Applications Content Versatility makes it possible to offer completely different views on the content inside the KiWi system without any modifications to the core system or data model. We call such views “KiWi Applications”, and they are one kind of extension offered by the KiWi system (others are currently: KiWi Services, KiWi Widgets, KiWi Actions, and Exporters/Importers). In the following, we describe the set of applications that are part of the KiWi System to illustrate how the Wiki Principles and Content Versatility are realised in KiWi. The applications have been selected based on the requirements identified in the two KiWi use cases and accompanying SNML projects; additional applications are conceivable and reasonable. Additional applications will be offered as separate packages in later stages of the project. KiWi applications share the same context, i.e. when the user browses a content item in the Wiki or Dashboard, she can switch to the TagIT application and view the same content item on a map or to the Inspector and get debugging information on the content item. Fig. 1. The KiWi Wiki: A Semantic Wiki built on top of KiWi

/pdf/kiwi-a-platform-for-semantic-social-software-7y5lg658vp.pdf

KiWi - A Platform for Semantic Social Software.

Semantic Wikis have demonstrated the power of combining Wikis with Semantic Web technology. The KiWi system goes beyond Semantic Wikis by providing a flexible and adaptable platform for building different kinds of Social Semantic Software, powered by Semantic Web technology. While the KiWi project itself is primarily focussed on the knowledge management domain, this demonstration shows how KiWi aspects like the Wiki Principles and Content Versatility can be used to build completely different kinds of Social Software applications. The first application we show is an "ordinary" Semantic Wiki system preloaded with content from a online news site. The second application called TagIT is a map-based system where locations and routes on a map can be "tagged" by users with textual descriptions, SKOS categories, and multimedia material. Both applicatons are built on top of the same KiWi platform and actually share the same content.

KiWi - A Platform for Semantic Social Software (Demonstration).

The combination of semantic technologies and social software has become more and more popular in the last few years as can be seen by the emergence of Semantic Wikis or the popularity of vocabularies such as FOAF or SIOC. The KiWi project is based upon these principles and offers features required for Social Media applications such as versioning, (semantic) tagging, rich text editing, easy linking, rating and commenting, as well as advanced "smart" services such as recommendation, rule-based reasoning, information extraction, intelligent search and querying, a sophisticated social reputation system, vocabulary management, and rich visualization. KiWi can be used both, as a platform for building custom Semantic Media applications, and as a Semantic Social Index, integrating content and data from a variety of different sources, e.g. Wikis, blogs and content management systems in an enterprise internet. Third-party applications can access the KiWi System using simple-to-use web services. The demo presents the whole functionality of the Open Source development platform KiWi in its final version within one integrated project management scenario. Furthermore it shows different KiWi-based Social Media projects to illustrate its various fields of application.

Stephanie Stroka

Papers

Combining Unstructured, Fully Structured and Semi-Structured Information in Semantic Wikis.

KiWi - A Platform for Semantic Social Software.

KiWi - A Platform for Semantic Social Software (Demonstration).

KiWi - a platform for building semantic social media applications

D6.4 Implementation: Project Knowledge Management