Stefan Zander

Expressing and reasoning on features of robot-centric workplaces using ontological semantics

This paper presents a novel ontology-based approach that uses Description Logics as a knowledge representation framework for the description, aggregation, propagation, and interlinkage of features pertaining to robots and robot-centric workplaces. We show how different classification systems for capabilities and components can be axiomatically linked together, how features can be propagated along compound components, and how complex features can be computed on the basis of combining role inclusion, role composition, and general concept inclusion axioms. In a second use case that is related to the logical deduction of potential hazards for a given workplace configuration, we show that the presented approach is applicable to similar modeling problems.

From AutomationML to ROS: A model-driven approach for software engineering of industrial robotics using ontological reasoning

One of the major investment for applying industrial robots in production resides in the software development, which is an interdisciplinary and heterogeneous engineering process. This paper presents a novel model-driven approach that uses AutomationML as modeling framework and ontological reasoning as inference framework for constructing robotic application using Robot Operating System (ROS). We show how different robotic components can be classified and modeled with AutomationML, how these components can be composed together to a production system, and how the AutomationML models can be processed semantically by utilizing Semantic Web technologies and ontological reasoning. By applying model-to-text transformation techniques, executable ROS code can be generated from the models that foster fast prototyping and the reuse of robotic software.

Enhancing the Utilization of IoT Devices Using Ontological Semantics and Reasoning

This research in progress work demonstrates how the formal, model-theoretic semantics of ontologies can be used for complementing the technical specifications of Internet of Things (IoT) devices with additional high-level information derived from domain ontologies in order to enhance utilization and interoperability. The presented approach substantiates the assumption that a more elaborated description about a devices capabilities and its features helps in integrating it in different system contexts and fosters interoperability among different IoT devices. We show how basic technical information represented as RDF data can be used to automatically classify IoT devices, how default capabilities can be deduced from these classifications, and how advanced features can be inferred using domain semantics and formal reasoning. The applicability of the presented approach in real world settings is demonstrated by a concrete example from an IoT use case.

Advancement of MOOCs with Learning Pathways

In this paper, educational and technical challenges in the field of Massive Open Online Courses (MOOCs), such as cultural adaptation, consideration of learning habits or the efficient construction of educational content, are outlined. We argue that learning pathways in combination with learner-centered metadata are optimal methods to meet those challenges and hence optimize learning efficiency and learning experience substantially by creating personalized learning recommendations and feedback. This is illustrated from a conceptual and technological perspective, as is currently in development in the EU-project INTUITEL. We believe that this approach not only opens up new possibilities for MOOCs, but also provides a variety of new dimensions for eLearning in general.

A Semantic MediaWiki-Based Approach for the Collaborative Development of Pedagogically Meaningful Learning Content Annotations

In this work, we present an approach that allows educational resources to be collaboratively authored and annotated with well-defined pedagogical semantics using Semantic MediaWiki as collaborative knowledge engineering tool. The approach allows for the exposition of pedagogically annotated learning content as Linked Open Data to enable its reuse across e-learning platforms and its adaptability in different educational contexts. We employ Web Didactics as knowledge organization concept and detail its manifestation in a Semantic MediaWiki system using import and mapping declarations. We also show how the inherent pedagogical semantics of Web Didactics can be retained when learning material is exported as RDF data. The advantage of the presented approach lies in addressing the constructivist view on educational models: The different roles involved in the content development process are not forced to adapt to new vocabularies but can continue using the terms and classification systems they are familiar with. Results of the usability test with computer scientists and education researchers are positive with significantly more positive results for computer scientists.

BigGIS: a continuous refinement approach to master heterogeneity and uncertainty in spatio-temporal big data (vision paper)

Geographic information systems (GIS) are important for decision support based on spatial data. Due to technical and economical progress an ever increasing number of data sources are available leading to a rapidly growing fast and unreliable amount of data that can be beneficial (1) in the approximation of multivariate and causal predictions of future values as well as (2) in robust and proactive decision-making processes. However, todays GIS are not designed for such big data demands and require new methodologies to effectively model uncertainty and generate meaningful knowledge. As a consequence, we introduce BigGIS, a predictive and prescriptive spatio-temporal analytics platform, that symbiotically combines big data analytics, semantic web technologies and visual analytics methodologies. We present a novel continuous refinement model and show future challenges as an intermediate result of a collaborative research project into big data methodologies for spatio-temporal analysis and design for a big data enabled GIS.

LSane: Collaborative Validation and Enrichment of Heterogeneous Observation Streams

Abstract The increasing amount of publicly available data streams of environmental observation stations opens up new opportunities: domain experts are provided with an extensive amount of observations covering large areas with high density of environmental sensors, which could hardly ever be provided by a single organization. However, these opportunities come at the cost of new challenges regarding trustworthiness and comparability of such observations. In this paper, we address the challenges of semantic validation and enrichment of heterogeneous observation streams by exploiting collaboratively created and curated annotations. For this purpose, we introduce and discuss the Linked Stream Annotation Engine (LSane) to validate observation messages from heterogeneous sensors. We enrich these observation messages with provenance information derived from annotations. We present an implementation of LSane with messages from public and private environmental observation stations, which are mapped to explicit semantics, and validate and enrich the mapped messages based on annotations from the LSane collaboration platform.

Using a Semantic Simulation Framework for Teaching Machine Learning Agents

Abstract Autonomous virtual agents that operate in complex IoT environments and apply machine learning algorithms face two fundamental challenges: (i) they usually lack sufficient start-up knowledge and (ii) hence are incapable to adequately adjust their internal knowledge base and decision-making policies during runtime to meet specific user requirements and preferences. This is problematic in Ambient Assisted Living (AAL) and Health-Care (HC) scenarios, since an agent has to expediently operate from the beginning of its lifecycle and adequately address the target users’ needs; without prior user and environmental knowledge, this is not possible. The presented approach addresses these problems by providing a semantic use-case simulation framework that can be tailored to specific AAL and HC use cases. It builds upon a semantic knowledge representation framework to simulate device events and user activities based on semantic task and ambient descriptions. Through such a simulated environment, agents are provided with the ability to learn the best matching actions and to adjust their policies based on generated datasets. We demonstrate the practical applicability of the simulation framework through the evaluation of the chronic kidney disease pathway from the vCare EC project. Thereby, we proof that an agent that uses reinforcement learning (RL) is able to improve its performance during and after the training and thus makes optimal (activity) recommendations to a prospective patient.

Exploiting Linked Open Data for Enhancing MediaWiki-based Semantic Organizational Knowledge Bases

One of the main driving forces for the integration of Semantic Media Wiki systems in corporate contexts is their query construction capabilities on top of organization-specific vocabularies together with the possibility to directly embed query results in wiki pages. However, exploiting knowledge from external sources like other organizational knowledge bases or Linked Open Data as well as sharing knowledge in a meaningful way is difficult due to the lack of a common and shared schema definition. In this paper, we introduce Linked Data Wiki (LD-Wiki), an approach that combines the power of Linked Open Vocabularies and Data with established organizational semantic wiki systems for knowledge management. It supports suggestions for annotations from Linked Open Data sources for organizational knowledge bases in order to enrich them with background information from Linked Open Data. The inclusion of potentially uncertain, incomplete, inconsistent or redundant Linked Open Data within an organization’s knowledge base poses the challenge of interpreting such data correctly within the respective context. In our approach, we evaluate data provenance information in order to handle data from heterogeneous internal and external sources adequately and provide data consumers with the latest and best evaluated information according to a ranking system.

Agent-Based Assistance in Ambient Assisted Living Through Reinforcement Learning and Semantic Technologies

For impaired people, the conduction of certain daily life activities is problematic due to motoric and cognitive handicaps. For that reason, assistive agents in ambient assisted environments provide services that aim at supporting elderly and impaired people. However, these agents act in complex stochastic and indeterministic environments where the concrete effects of a performed action are usually unknown at design time. Furthermore, they have to perform varying tasks according to the user’s context and needs, wherefore an agent has to be flexible and able to recognize required capabilities in a certain situation in order to provide adequate, unobtrusive assistance. Hence, an expressive representation framework is required that relates user-specific impairments to required agent capabilities. This work presents an approach which (a) describes and links user impairments and capabilities using the formal, model-theoretic semantics expressed in OWL2 DL ontologies, (b) computes optimal policies through Reinforcement Learning and propagates these in an agent network. The presented approach improves the collaborative, personalized and adequate assistance of assistive agents and tailors the agent-based services to the user’s missing capabilities.