Herzog, Otthein
Loading...
Preferred name
Herzog, Otthein
Official Name
Herzog, Otthein
16 results
Now showing 1 - 10 of 16
- Some of the metrics are blocked by yourconsent settings
Item type:Publication, Graphtransformation mit Ontologien(2008-09-02); ; ; In this document a new approach of graphtransformation is shown, which uses ontology reasoning within the graphtransformation process. With this approach it is possible to reduce the number of graphtransfotmation rules significant, according to the usecase. Further more this approach allows the usage of infinitive sets of edge markers within graphs and rules.doctoral thesis231 144 - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Interactive Multiagent Adaptation of Individual Classification Models for Decision Support(2019-07-02); ; ; An essential prerequisite for informed decision-making of intelligent agents is direct access to empirical knowledge for situation assessment. This contribution introduces an agent-oriented knowledge management framework for learning agents facing impediments in self-contained acquisition of classification models. The framework enables the emergence of dynamic knowledge networks among benevolent agents forming a community of practice in open multiagent systems. Agents in an advisee role are enabled to pinpoint learning impediments in terms of critical training cases and to engage in a goal-directed discourse with an advisor panel to overcome identified issues. The advisors provide arguments supporting and hence explaining those critical cases. Using such input as additional background knowledge, advisees can adapt their models in iterative relearning organized as a search through model space. An extensive empirical evaluation in two real-world domains validates the presented approach.doctoral thesis433 346 - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Relevanzbasierte Informationsbeschaffung für die informierte Entscheidungsfindung intelligenter Agenten(2011-09-23); ; ; This dissertation introduces relevance-based information acquisition for intelligent software agents based on Howard s information value theory and decision networks. Active information acquisition is crucial in domains with partial observability in order to establish situation awareness of autonomous systems for deliberate decisions. The new semi-myopic approach addresses the complexity challenge of decision-theoretic relevance computation by reducing the set of variables to be evaluated in the first place. Links in a decision network encode stochastic dependencies of variables. Through utility dependency analysis using Pearl s d-separation criterion, the set of relevant variables can be efficiently reduced to a proven minimum without actually computing information value. In addition to an implementation with detailed runtime performance analysis, the applicability of the approach is shown in the domain of intelligent logistics control.doctoral thesis723 422 - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Temporal Pattern Mining in Dynamic Environments(2007-05-30); ; ; In this work an approach is presented which applies unsupervised symbolic learning to a qualitative abstraction of dynamic scenes in order to create frequent temporal patterns and prediction rules. Having in mind rather complex situations with different objects of various types and relations and temporal interrelations of actions and events, the approach provides means to mine complex temporal patterns taking into account these aspects. It is an extension of the association rule mining algorithm Apriori and combines ideas from relational as well as sequential association rule mining approaches. Temporal interrelations between predicates of patterns are represented qualitatively by interval relations as, e.g., introduced by Allen and Freksa. Additionally, variable unification allows to connect variables of (different) predicates in a complex pattern in order to deal with relational data. As a third aspect, concept restrictions are learned for variables of a pattern.doctoral thesis464 258 - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Dynamisch adaptive Planung individualisierter Touren(2008-04-18); ; ; Living in a dynamic and mobile environment being "always on" and "always connected", surrounded by smart devices and intelligent sensors, makes the vision of "ambient assisted living" in everyday life appear desirable and feasible. WebServices and the Semantic Web provide the technical means to find and use virtually offered relevant every day services pursuing the vision of developing personalized service-roadmaps. With "personal information environments" (PIE) Isbell and Pierce bridge the gap between virtual and physical worlds. This dissertation proposes dynamic adaptive planning of individualized tours as part of a PIE, an augmented reality connected to the real world with the need to navigate therein. It shows itself as alternative for navigating through a vast variety of physical signs providing unfiltered information for everyone. Introducing Frankfurt Airport as one representative of the problem domain clarifies the multi-dimensional orientation problem in dynamic environments. This formally corresponds to solving instances of Trip-Planning-Problems as has been outlined by Godard. Thus the very subject of this work is adaptive tour planning, which yields optimal personalized configuration of services and at the same time a spatially optimized order of services - an optimal tour. One the one hand, the complexity of the problem results from the combination of configuration and tour planning. On the other hand, it is due to the task of continual replanning in dynamic environments. In the first main part of this dissertation a new planning method has been developed, that computes personalized tours under time constraints and optimizes tours for maximum use and with respect to spatial criteria like locality and proximity. A hierarchical method consistently expands minimal tours and traces down the task to navigation planning between areas and configuration planning inside areas. The method plans minimal consistent tours for mandatory stages instantiating plan schemata taking the user context into account and iteratively extends these tours by areas of maximum use. It is shown that the method reduces the exponential planning problem to computationally feasible parts. Further on, for these parts an optimal and exact solution for the Trip-Planning-Problem is provided. Correctness and the computational complexity of methods and algorithms are proved.Spatial prerequisites - the building and route model - are also provided as a service and user model.In the second main part of this dissertation a dynamic and adaptive planning method has been developed, which supports users executing their tour plans and intervenes as soon as the plan execution appears to fail or may be optimized because of improving preconditions. The method integrates adhoc appearing, probably more relevant services into an existing plan, detects increasing or decreasing time quota during execution and adapts a plan to altering preconditions. Proactive and reactive plan monitoring strategies are introduced that continuously control preconditions during execution and act in advance with local corrections in order to defer expensive replanning tasks. In case of a user rejects a local correction, it is shown how replanning can be reduced to the incremental planning method introduced in the first main part. Comparing the results of the planning and replanning method of this dissertation with the results of an exact method shows that the method of planning maximum areas yields near optimal solutions and better solutions as far as the spatial optimization criteria are concerned.doctoral thesis278 201 - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Ein deformationsinvarianter Point-of-Interest-Detektor(2010-11-17); ; ; Interest point detectors are a common processing step in low-level computer vision. Current interest point detectors exhibit invariance against rotation, scaling, and affine twodimensional transformations. The thesis presents a new algorithm for interest point detection that is invariant against a larger set of transformations, i.e., deformations.doctoral thesis333 125 - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Automatic Classification of Seafloor Image Data by Geospatial Texture Descriptors(2014-12-19); ; ; A novel approach for automatic context-sensitive classification of spatially distributed image data is introduced. The proposed method targets applications of seafloor habitat mapping but is generally not limited to this domain or use case. Spatial context information is incorporated in a two-stage classification process, where in the second step a new descriptor for patterns of feature class occurrence according to a generically defined classification scheme is applied. The method is based on supervised machine learning, where numerous state-of-the-art approaches are applicable. The descriptor computation originates from texture analysis in digital image processing. Patterns of feature class occurrence are perceived as a texture-like phenomenon and the descriptors are therefore denoted by Geospatial Texture Descriptors. The proposed method was extensively validated based on a set of more than 4000 georeferenced video mosaics acquired at the Haakon Mosby Mud Volcano north-west of Norway recorded during cruise ARK XIX3b of the German research vessel Polarstern. The underlying classification scheme was derived from a scheme developed for manual annotation of the same dataset applied in the course of Jerosch [2006]. Features of interest are related to methane discharge at mud volcanoes, which are considered a significant source of methane emission. In the experimental evaluation, based on the prepared training and test data, a major improvement of the classification precision compared to local classification as well as classification based on the raw data from the local spatial context was achieved by the application of the proposed method. The classification precision was particularly improved for rarely occurring classes. In a further comparison with annotated data available from Jerosch [2006] the regional setting of the investigation area obtained by the application of the proposed method was found almost equivalent to the results of an experienced scientist.doctoral thesis356 153 - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Human-Computer Interfaces for Wearable Computers: A Systematic Approach to Development and Evaluation(2007-12-10); ; ; The research presented in this thesis examines user interfaces for wearable computers.Wearable computers are a special kind of mobile computers that can be worn on the body. Furthermore, they integrate themselves even more seamlessly into different activities than a mobile phone or a personal digital assistant can.The thesis investigates the development and evaluation of user interfaces for wearable computers. In particular, it presents fundamental research results as well as supporting software tools for wearable user interface development. The main contributions of the thesis are a new evaluation method for user interfaces of wearable computers and a model-driven software toolkit to ease interface development for application developers with limited human-computer interaction knowledge.The research presented in this thesis motivates and validates the research hypothesis that user interfaces for wearable computers are inherently different to stationary desktop interfaces as well as mobile computer interfaces and, therefore, have to be designed differently to make them usable without being a burden for humans.doctoral thesis582 186 - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Kennzahlenbasierte Steuerung, Koordination und Aktionsplanung in Multiagentensystemen(2017-06-29); ; ; To be of practical use, the implementation of flexible and modular agent-based cyber-physical systems (CPS) for real-world autonomous control applications in Industry 4.0 oftentimes requires the domain-specific software agents to adhere to the organization's overall qualitative and quantitative business goals, usually expressed in terms of numeric key performance indicators (KPI). In this thesis, a general software framework for multi-agent systems (MAS) and CPS is developed that facilitates the integration and configuration of KPI-related objectives into the agents' individual decision processes. It allows the user of an agent system to define new KPIs and associated multi-criteria goals and supports inter-agent coordination as well as detailed KPI-based action planning, all at runtime of the MAS. The domain-independent components of the proposed KPI framework are implemented as a Java programming library and evaluated in a simulated production planning and control scenario.doctoral thesis656 702 - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Video Abstracting at a Semantical Level(2018-02-02); ; ; One the most common form of a video abstract is the movie trailer. Contemporary movie trailers share a common structure across genres which allows for an automatic generation and also reflects the corresponding moviea s composition. In this thesis a system for the automatic generation of trailers is presented. In addition to action trailers, the system is able to deal with further genres such as Horror and comedy trailers, which were first manually analyzed in order to identify their basic structures. To simplify the modeling of trailers and the abstract generation itself a new video abstracting application was developed. This application is capable of performing all steps of the abstract generation automatically and allows for previews and manual optimizations. Based on this system, new abstracting models for horror and comedy trailers were created and the corresponding trailers have been automatically generated using the new abstracting models. In an evaluation the automatic trailers were compared to the original Trailers and showed a similar structure. However, the automatically generated trailers still do not exhibit the full perfection of the Hollywood originals as they lack intentional storylines across shots.doctoral thesis426 606