Refine
H-BRS Bibliography
- yes (1148)
Departments, institutes and facilities
- Fachbereich Informatik (1148) (remove)
Document Type
- Conference Object (606)
- Article (265)
- Report (77)
- Part of a Book (50)
- Preprint (50)
- Book (monograph, edited volume) (32)
- Doctoral Thesis (22)
- Conference Proceedings (18)
- Research Data (11)
- Master's Thesis (7)
Year of publication
Keywords
- Virtual Reality (13)
- Robotics (12)
- Machine Learning (10)
- Usable Security (10)
- virtual reality (10)
- 3D user interface (7)
- Quality diversity (7)
- Augmented Reality (6)
- Lehrbuch (6)
- Navigation (6)
Neuromorphic computing aims to mimic the computational principles of the brain in silico and has motivated research into event-based vision and spiking neural networks (SNNs). Event cameras (ECs) capture local, independent changes in brightness, and offer superior power consumption, response latencies, and dynamic ranges compared to frame-based cameras. SNNs replicate neuronal dynamics observed in biological neurons and propagate information in sparse sequences of ”spikes”. Apart from biological fidelity, SNNs have demonstrated potential as an alternative to conventional artificial neural networks (ANNs), such as in reducing energy expenditure and inference time in visual classification. Although potentially beneficial for robotics, the novel event-driven and spike-based paradigms remain scarcely explored outside the domain of aerial robots.
To investigate the utility of brain-inspired sensing and data processing in a robotics application, we developed a neuromorphic approach to real-time, online obstacle avoidance on a manipulator with an onboard camera. Our approach adapts high-level trajectory plans with reactive maneuvers by processing emulated event data in a convolutional SNN, decoding neural activations into avoidance motions, and adjusting plans in a dynamic motion primitive formulation. We conducted simulated and real experiments with a Kinova Gen3 arm performing simple reaching tasks involving static and dynamic obstacles. Our implementation was systematically tuned, validated, and tested in sets of distinct task scenarios, and compared to a non-adaptive baseline through formalized quantitative metrics and qualitative criteria.
The neuromorphic implementation facilitated reliable avoidance of imminent collisions in most scenarios, with 84% and 92% median success rates in simulated and real experiments, where the baseline consistently failed. Adapted trajectories were qualitatively similar to baseline trajectories, indicating low impacts on safety, predictability and smoothness criteria. Among notable properties of the SNN were the correlation of processing time with the magnitude of perceived motions (captured in events) and robustness to different event emulation methods. Preliminary tests with a DAVIS346 EC showed similar performance, validating our experimental event emulation method. These results motivate future efforts to incorporate SNN learning, utilize neuromorphic processors, and target other robot tasks to further explore this approach.
An essential measure of autonomy in service robots designed to assist humans is adaptivity to the various contexts of human-oriented tasks. These robots may have to frequently execute the same action, but subject to subtle variations in task parameters that determine optimal behaviour. Such actions are traditionally executed by robots using pre-determined, generic motions, but a better approach could utilize robot arm maneuverability to learn and execute different trajectories that work best in each context.
In this project, we explore a robot skill acquisition procedure that allows incorporating contextual knowledge, adjusting executions according to context, and improvement through experience, as a step towards more adaptive service robots. We propose an apprenticeship learning approach to achieving context-aware action generalisation on the task of robot-to-human object hand-over. The procedure combines learning from demonstration, with which a robot learns to imitate a demonstrator’s execution of the task, and a reinforcement learning strategy, which enables subsequent experiential learning of contextualized policies, guided by information about context that is integrated into the learning process. By extending the initial, static hand-over policy to a contextually adaptive one, the robot derives and executes variants of the demonstrated action that most appropriately suit the current context. We use dynamic movement primitives (DMPs) as compact motion representations, and a model-based Contextual Relative Entropy Policy Search (C-REPS) algorithm for learning policies that can specify hand-over position, trajectory shape, and execution speed, conditioned on context variables. Policies are learned using simulated task executions, before transferring them to the robot and evaluating emergent behaviours.
We demonstrate the algorithm’s ability to learn context-dependent hand-over positions, and new trajectories, guided by suitable reward functions, and show that the current DMP implementation limits learning context-dependent execution speeds. We additionally conduct a user study involving participants assuming different postures and receiving an object from the robot, which executes hand-overs by either exclusively imitating a demonstrated motion, or selecting hand-over positions based on learned contextual policies and adapting its motion accordingly. The results confirm the hypothesized improvements in the robot’s perceived behaviour when it is context-aware and adaptive, and provide useful insights that can inform future developments.
An essential measure of autonomy in assistive service robots is adaptivity to the various contexts of human-oriented tasks, which are subject to subtle variations in task parameters that determine optimal behaviour. In this work, we propose an apprenticeship learning approach to achieving context-aware action generalization on the task of robot-to-human object hand-over. The procedure combines learning from demonstration and reinforcement learning: a robot first imitates a demonstrator’s execution of the task and then learns contextualized variants of the demonstrated action through experience. We use dynamic movement primitives as compact motion representations, and a model-based C-REPS algorithm for learning policies that can specify hand-over position, conditioned on context variables. Policies are learned using simulated task executions, before transferring them to the robot and evaluating emergent behaviours. We additionally conduct a user study involving participants assuming different postures and receiving an object from a robot, which executes hand-overs by either imitating a demonstrated motion, or adapting its motion to hand-over positions suggested by the learned policy. The results confirm the hypothesized improvements in the robot’s perceived behaviour when it is context-aware and adaptive, and provide useful insights that can inform future developments.
For many different applications, current information about the bandwidth-related metrics of the utilized connection is very useful as they directly impact the performance of throughput sensitive applications such as streaming servers, IPTV and VoIP applications. In literature, several tools have been proposed to estimate major bandwidth-related metrics such as capacity, available bandwidth and achievable throughput. The vast majority of these tools fall into one of Packet Pair (PP), Variable Packet Size (VPS), Self-Loading of Periodic Streams (SLoPS) or Throughput approaches. In this study, seven popular bandwidth estimation tools including nettimer, pathrate, pathchar, pchar, clink, pathload and iperf belonging to these four well-known estimation techniques are presented and experimentally evaluated in a controlled testbed environment. Differently from the rest of studies in literature, all tools have been uniformly classified and evaluated according to an objective and sophisticated classification and evaluation scheme. The performance comparison of the tools incorporates not only the estimation accuracy but also the probing time and overhead caused.
YAWL (Yet Another Workflow Language) is an open source Business Process Management System, first released in 2003. YAWL grew out of a university research environment to become a unique system that has been deployed worldwide as a laboratory environment for research in Business Process Management and as a productive system in other scientific domains.
When users in virtual reality cannot physically walk and self-motions are instead only visually simulated, spatial updating is often impaired. In this paper, we report on a study that investigated if HeadJoystick, an embodied leaning-based flying interface, could improve performance in a 3D navigational search task that relies on maintaining situational awareness and spatial updating in VR. We compared it to Gamepad, a standard flying interface. For both interfaces, participants were seated on a swivel chair and controlled simulated rotations by physically rotating. They either leaned (forward/backward, right/left, up/down) or used the Gamepad thumbsticks for simulated translation. In a gamified 3D navigational search task, participants had to find eight balls within 5 min. Those balls were hidden amongst 16 randomly positioned boxes in a dark environment devoid of any landmarks. Compared to the Gamepad, participants collected more balls using the HeadJoystick. It also minimized the distance travelled, motion sickness, and mental task demand. Moreover, the HeadJoystick was rated better in terms of ease of use, controllability, learnability, overall usability, and self-motion perception. However, participants rated HeadJoystick could be more physically fatiguing after a long use. Overall, participants felt more engaged with HeadJoystick, enjoyed it more, and preferred it. Together, this provides evidence that leaning-based interfaces like HeadJoystick can provide an affordable and effective alternative for flying in VR and potentially telepresence drones.
Robust Indoor Localization Using Optimal Fusion Filter For Sensors And Map Layout Information
(2014)
Airborne and spaceborne platforms are the primary data sources for large-scale forest mapping, but visual interpretation for individual species determination is labor-intensive. Hence, various studies focusing on forests have investigated the benefits of multiple sensors for automated tree species classification. However, transferable deep learning approaches for large-scale applications are still lacking. This gap motivated us to create a novel dataset for tree species classification in central Europe based on multi-sensor data from aerial, Sentinel-1 and Sentinel-2 imagery. In this paper, we introduce the TreeSatAI Benchmark Archive, which contains labels of 20 European tree species (i.e., 15 tree genera) derived from forest administration data of the federal state of Lower Saxony, Germany. We propose models and guidelines for the application of the latest machine learning techniques for the task of tree species classification with multi-label data. Finally, we provide various benchmark experiments showcasing the information which can be derived from the different sensors including artificial neural networks and tree-based machine learning methods. We found that residual neural networks (ResNet) perform sufficiently well with weighted precision scores up to 79 % only by using the RGB bands of aerial imagery. This result indicates that the spatial content present within the 0.2 m resolution data is very informative for tree species classification. With the incorporation of Sentinel-1 and Sentinel-2 imagery, performance improved marginally. However, the sole use of Sentinel-2 still allows for weighted precision scores of up to 74 % using either multi-layer perceptron (MLP) or Light Gradient Boosting Machine (LightGBM) models. Since the dataset is derived from real-world reference data, it contains high class imbalances. We found that this dataset attribute negatively affects the models' performances for many of the underrepresented classes (i.e., scarce tree species). However, the class-wise precision of the best-performing late fusion model still reached values ranging from 54 % (Acer) to 88 % (Pinus). Based on our results, we conclude that deep learning techniques using aerial imagery could considerably support forestry administration in the provision of large-scale tree species maps at a very high resolution to plan for challenges driven by global environmental change. The original dataset used in this paper is shared via Zenodo (https://doi.org/10.5281/zenodo.6598390, Schulz et al., 2022). For citation of the dataset, we refer to this article.
This paper presents the b-it-bots RoboCup@Work team and its current hardware and functional architecture for the KUKA youBot robot.We describe the underlying software framework and the developed capabilities required for operating in industrial environments including features such as reliable and precise navigation, flexible manipulation and robust object recognition.
A robot (e.g. mobile manipulator) that interacts with its environment to perform its tasks, often faces situations in which it is unable to achieve its goals despite perfect functioning of its sensors and actuators. These situations occur when the behavior of the object(s) manipulated by the robot deviates from its expected course because of unforeseeable ircumstances. These deviations are experienced by the robot as unknown external faults. In this work we present an approach that increases reliability of mobile manipulators against the unknown external faults. This approach focuses on the actions of manipulators which involve releasing of an object. The proposed approach, which is triggered after detection of a fault, is formulated as a three-step scheme that takes a definition of a planning operator and an example simulation as its inputs. The planning operator corresponds to the action that fails because of the fault occurrence, whereas the example simulation shows the desired/expected behavior of the objects for the same action. In its first step, the scheme finds a description of the expected behavior of the objects in terms of logical atoms (i.e. description vocabulary). The description of the simulation is used by the second step to find limits of the parameters of the manipulated object. These parameters are the variables that define the releasing state of the object.
Using randomly chosen values of the parameters within these limits, this step creates different examples of the releasing state of the object. Each one of these examples is labelled as desired or undesired according to the behavior exhibited by the object (in the simulation), when the object is released in the state corresponded by the example. The description vocabulary is also used in labeling the examples autonomously. In the third step, an algorithm (i.e. N-Bins) uses the labelled examples to suggest the state for the object in which releasing it avoids the occurrence of unknown external faults.
The proposed N-Bins algorithm can also be used for binary classification problems. Therefore, in our experiments with the proposed approach we also test its prediction ability along with the analysis of the results of our approach. The results show that under the circumstances peculiar to our approach, N-Bins algorithm shows reasonable prediction accuracy where other state of the art classification algorithms fail to do so. Thus, N-Bins also extends the ability of a robot to predict the behavior of the object to avoid unknown external faults. In this work we use simulation environment OPENRave that uses physics engine ODE to simulate the dynamics of rigid bodies.
A system that interacts with its environment can be much more robust if it is able to reason about the faults that occur in its environment, despite perfect functioning of its internal components. For robots, which interact with the same environment as human beings, this robustness can be obtained by incorporating human-like reasoning abilities in them. In this work we use naive physics to enable reasoning about external faults in robots. We propose an approach for diagnosing external faults that uses qualitative reasoning on naive physics concepts for diagnosis. These concepts are mainly individual properties of objects that define their state qualitatively. The reasoning process uses physical laws to generate possible states of the concerned object(s), which could result into a detected external fault. Since effective reasoning about any external fault requires the information of relevant properties and physical laws, we associate different properties and laws to different types of faults which can be detected by a robot. The underlying ontology of this association is proposed on the basis of studies conducted (by other researchers) on reasoning of physics novices about everyday physical phenomena. We also formalize some definitions of properties of objects into a small framework represented in First-Order logic. These definitions represent naive concepts behind the properties and are intended to be independent from objects and circumstances. The definitions in the framework illustrates our proposal of using different biased definitions of properties for different types of faults. In this work, we also present a brief review of important contributions in the area of naive/qualitative physics. These reviews help in understanding the limitations of naive/qualitative physics in general. We also apply our approach to simple scenarios to asses its limitations in particular. Since this work was done independent of any particular real robotic system, it can be seen as a theoretical proof of the concept of usefulness of naive physics for external fault reasoning in robotics.
Despite perfect functioning of its internal components, a robot can be unsuccessful in performing its tasks because of unforeseen situations. These situations occur when the behavior of the objects in the robot’s environment deviates from its expected values. For robots, such deviations are exhibited in the form of unknown external faults which prohibit them from performing their tasks successfully. In this work we propose to use naive physics knowledge to reason about such faults in the robotics domain. We propose an approach that uses naive physics concepts to find information about the situations which result in a detected unknown fault. The naive physics knowledge is represented by the physical properties of objects which are formalized in a logical framework. The proposed approach applies a qualitative version of physical laws to these properties for reasoning about the detected fault. By interpreting the reasoning results the robot finds the information about the situations which can cause the fault. We apply the proposed approach to the scenarios in which a robot performs manipulation tasks of picking and placing objects. Results of this application show that naive physics holds great promise for reasoning about unknown ex- ternal faults in robotics.
A plethora of architectural patterns and elements for developing service-oriented applications can be gathered from the state-of-the-art. Most of these approaches are merely applicable for single-tenant applications. However, less methodical support is provided for scenarios, in which multiple different tenants with varying requirements access the same application stack concurrently. In order to fill this gap, both novel and existing architectural patterns, architectural elements, as well as fundamental design decisions must be considered and integrated into a framework that leverages the devel- opment of multi-tenant application. This paper addresses this demand and presents the SOAdapt framework. It promotes the development of adaptable multi-tenant applications based on a service-oriented architecture that is capable of incorporating specific requirements of new tenants in a flexible manner.
A principal step towards solving diverse perception problems is segmentation. Many algorithms benefit from initially partitioning input point clouds into objects and their parts. In accordance with cognitive sciences, segmentation goal may be formulated as to split point clouds into locally smooth convex areas, enclosed by sharp concave boundaries. This goal is based on purely geometrical considerations and does not incorporate any constraints, or semantics, of the scene and objects being segmented, which makes it very general and widely applicable. In this work we perform geometrical segmentation of point cloud data according to the stated goal. The data is mapped onto a graph and the task of graph partitioning is considered. We formulate an objective function and derive a discrete optimization problem based on it. Finding the globally optimal solution is an NP-complete problem; in order to circumvent this, spectral methods are applied. Two algorithms that implement the divisive hierarchical clustering scheme are proposed. They derive graph partition by analyzing the eigenvectors obtained through spectral relaxation. The specifics of our application domain are used to automatically introduce cannot-link constraints in the clustering problem. The algorithms function in completely unsupervised manner and make no assumptions about shapes of objects and structures that they segment. Three publicly available datasets with cluttered real-world scenes and an abundance of box-like, cylindrical, and free-form objects are used to demonstrate convincing performance. Preliminary results of this thesis have been contributed to the International Conference on Autonomous Intelligent Systems (IAS-13).
A company's financial documents use tables along with text to organize the data containing key performance indicators (KPIs) (such as profit and loss) and a financial quantity linked to them. The KPI’s linked quantity in a table might not be equal to the similarly described KPI's quantity in a text. Auditors take substantial time to manually audit these financial mistakes and this process is called consistency checking. As compared to existing work, this paper attempts to automate this task with the help of transformer-based models. Furthermore, for consistency checking it is essential for the table's KPIs embeddings to encode the semantic knowledge of the KPIs and the structural knowledge of the table. Therefore, this paper proposes a pipeline that uses a tabular model to get the table's KPIs embeddings. The pipeline takes input table and text KPIs, generates their embeddings, and then checks whether these KPIs are identical. The pipeline is evaluated on the financial documents in the German language and a comparative analysis of the cell embeddings' quality from the three tabular models is also presented. From the evaluation results, the experiment that used the English-translated text and table KPIs and Tabbie model to generate table KPIs’ embeddings achieved an accuracy of 72.81% on the consistency checking task, outperforming the benchmark, and other tabular models.
In the fermentation process sugars are transformed into lactic acid. pH meters have traditionally been used for fermentation process monitoring based on acidity. More recently, near infrared (NIR) spectroscopy has proven to provide an accurate and non-invasive method to detect when the transformation of sugars into lactic acid is finished. The fermentation process when sugars are transformed into lactic acid. This research proposes the use of simplified NIR spectroscopy using multispectral optical sensors as a simpler and less expensive measure to end the fermentation process. The NIR spectrum of milk and yogurt is compared to find and extract features that can be used to design a simple sensor to monitor the yogurt fermentation process. Multispectral images in four selected wavebands within the NIR spectrum are captured and show different spectral remission characteristics for milk, yogurt and water, which support the selection of these wavebands for milk and yogurt classification.
Information reliability and automatic computation are two important aspects that are continuously pushing the Web to be more semantic. Information uploaded to the Web should be reusable and extractable automatically to other applications, platforms, etc. Several tools exist to explicitly markup Web content. The Web services may also have a positive role on the automatic processing of Web contents, especially when they act as flexible and agile agents. However, Web services themselves should be developed with semantics in mind. They should include and provide structured information to facilitate their use, reuse, composition, query, etc. In this chapter, the authors focus on evaluating state-of-the-art semantic aspects and approaches in Web services. Ultimately, this contributes to the goal of Web knowledge management, execution, and transfer.
Software testing in web services environment faces different challenges in comparison with testing in traditional software environments. Regression testing activities are triggered based on software changes or evolutions. In web services, evolution is not a choice for service clients. They have always to use the current updated version of the software. In addition test execution or invocation is expensive in web services and hence providing algorithms to optimize test case generation and execution is vital. In this environment, we proposed several approach for test cases' selection in web services' regression testing. Testing in this new environment should evolve to be included part of the service contract. Service providers should provide data or usage sessions that can help service clients reduce testing expenses through optimizing the selected and executed test cases.
Competitions for Benchmarking: Task and Functionality Scoring Complete Performance Assessment
(2015)
LiDAR-based Indoor Localization with Optimal Particle Filters using Surface Normal Constraints
(2023)
Nowadays, we input text not only on stationary devices, but also on handheld devices while walking, driving, or commuting. Text entry on the move, which we term as nomadic text entry, is generally slower. This is partially due to the need for users to move their visual focus from the device to their surroundings for navigational purposes and back. To investigate if better feedback about users' surroundings on the device can improve performance, we present a number of new and existing feedback systems: textual, visual, textual & visual, and textual & visual via translucent keyboard. Experimental comparisons between the conventional and these techniques established that increased ambient awareness for mobile users enhances nomadic text entry performance. Results showed that the textual and the textual & visual via translucent keyboard conditions increased text entry speed by 14% and 11%, respectively, and reduced the error rate by 13% compared to the regular technique. The two methods also significantly reduced the number of collisions with obstacles.
In den letzten Jahren haben sich elektronische Zahlungssysteme als populäre Alternative zur klassischen Bargeldzahlung etabliert. Diese Zahlungssysteme bestehen in der Regel aus zwei elementaren Komponenten: einem Terminal und einer Kasse. Damit ist der Käufer eines Produktes in der Lage, seine Schuld gegenüber dem Verkäufer bargeldlos und elektronisch zu begleichen. Die dabei am Häufigsten anfallenden Geschäftsprozesse, das Buchen und das Stornieren von Zahlungsbelegen, werden hierbei als Transaktionen bezeichnet, da diese entweder vollständig gelingen oder im Fehlerfall ohne Auswirkungen bleiben müssen. In diesem Buch wird daher die Implementierung eines zuverlässigen Zahlungssystems mit einem TeleCash-Terminal dargestellt. Dabei werden in den geforderten Geschäftsprozessen die wichtigen Transaktionseigenschaften sichergestellt. Es werden dazu zunächst die Grundlagen von Transaktionen erarbeitet und ein geeignetes Transaktionskonzept entwickelt. Anschließend wird die konkrete Realisierung des Systems mit Hilfe der Java Transaction Services durchgeführt. Abschließend wird das entstandene System hinsichtlich seiner Transaktionseigenschaften untersucht.
Recent work in image captioning and scene-segmentation has shown significant results in the context of scene-understanding. However, most of these developments have not been extrapolated to research areas such as robotics. In this work we review the current state-ofthe- art models, datasets and metrics in image captioning and scenesegmentation. We introduce an anomaly detection dataset for the purpose of robotic applications, and we present a deep learning architecture that describes and classifies anomalous situations. We report a METEOR score of 16.2 and a classification accuracy of 97 %.
Current robot platforms are being employed to collaborate with humans in a wide range of domestic and industrial tasks. These environments require autonomous systems that are able to classify and communicate anomalous situations such as fires, injured persons, car accidents; or generally, any potentially dangerous situation for humans. In this paper we introduce an anomaly detection dataset for the purpose of robot applications as well as the design and implementation of a deep learning architecture that classifies and describes dangerous situations using only a single image as input. We report a classification accuracy of 97 % and METEOR score of 16.2. We will make the dataset publicly available after this paper is accepted.
In this paper we introduce the Perception for Autonomous Systems (PAZ) software library. PAZ is a hierarchical perception library that allow users to manipulate multiple levels of abstraction in accordance to their requirements or skill level. More specifically, PAZ is divided into three hierarchical levels which we refer to as pipelines, processors, and backends. These abstractions allows users to compose functions in a hierarchical modular scheme that can be applied for preprocessing, data-augmentation, prediction and postprocessing of inputs and outputs of machine learning (ML) models. PAZ uses these abstractions to build reusable training and prediction pipelines for multiple robot perception tasks such as: 2D keypoint estimation, 2D object detection, 3D keypoint discovery, 6D pose estimation, emotion classification, face recognition, instance segmentation, and attention mechanisms.
Emotion and gender recognition from facial features are important properties of human empathy. Robots should also have these capabilities. For this purpose we have designed special convolutional modules that allow a model to recognize emotions and gender with a considerable lower number of parameters, enabling real-time evaluation on a constrained platform. We report accuracies of 96% in the IMDB gender dataset and 66% in the FER-2013 emotion dataset, while requiring a computation time of less than 0.008 seconds on a Core i7 CPU. All our code, demos and pre-trained architectures have been released under an open-source license in our repository at https://github.com/oarriaga/face classification.
In this paper we propose an implement a general convolutional neural network (CNN) building framework for designing real-time CNNs. We validate our models by creating a real-time vision system which accomplishes the tasks of face detection, gender classification and emotion classification simultaneously in one blended step using our proposed CNN architecture. After presenting the details of the training procedure setup we proceed to evaluate on standard benchmark sets. We report accuracies of 96% in the IMDB gender dataset and 66% in the FER-2013 emotion dataset. Along with this we also introduced the very recent real-time enabled guided back-propagation visualization technique. Guided back-propagation uncovers the dynamics of the weight changes and evaluates the learned features. We argue that the careful implementation of modern CNN architectures, the use of the current regularization methods and the visualization of previously hidden features are necessary in order to reduce the gap between slow performances and real-time architectures. Our system has been validated by its deployment on a Care-O-bot 3 robot used during RoboCup@Home competitions. All our code, demos and pre-trained architectures have been released under an open-source license in our public repository.
AErOmAt Abschlussbericht
(2020)
Das Projekt AErOmAt hatte zum Ziel, neue Methoden zu entwickeln, um einen erheblichen Teil aerodynamischer Simulationen bei rechenaufwändigen Optimierungsdomänen einzusparen. Die Hochschule Bonn-Rhein-Sieg (H-BRS) hat auf diesem Weg einen gesellschaftlich relevanten und gleichzeitig wirtschaftlich verwertbaren Beitrag zur Energieeffizienzforschung geleistet. Das Projekt führte außerdem zu einer schnelleren Integration der neuberufenen Antragsteller in die vorhandenen Forschungsstrukturen.
The goal of this work is to develop an integration framework for a robotic software system which enables robotic learning by experimentation within a distributed and heterogeneous setting. To meet this challenge, the authors specified, defined, developed, implemented and tested a component-based architecture called XPERSIF. The architecture comprises loosely-coupled, autonomous components that offer services through their well-defined interfaces and form a service-oriented architecture. The Ice middleware is used in the communication layer. Additionally, the successful integration of the XPERSim simulator into the system has enabled simultaneous quasi-realtime observation of the simulation by numerous, distributed users.
Adapting plans to changes in the environment by finding alternatives and taking advantage of opportunities is a common human behavior. The need for such behavior is often rooted in the uncertainty produced by our incomplete knowledge of the environment. While several existing planning approaches deal with such issues, artificial agents still lack the robustness that humans display in accomplishing their tasks. In this work, we address this brittleness by combining Hierarchical Task Network planning, Description Logics, and the notions of affordances and conceptual similarity. The approach allows a domestic service robot to find ways to get a job done by making substitutions. We show how knowledge is modeled, how the reasoning process is used to create a constrained planning problem, and how the system handles cases where plan generation fails due to missing/unavailable objects. The results of the evaluation for two tasks in a domestic service domain show the viability of the approach in finding and making the appropriate goal transformations.
Humans exhibit flexible and robust behavior in achieving their goals. We make suitable substitutions for objects, actions, or tools to get the job done. When opportunities that would allow us to reach our goals with less effort arise, we often take advantage of them. Robots are not nearly as robust in handling such situations. Enabling a domestic service robot to find ways to get a job done by making substitutions is the goal of our work. In this paper, we highlight the challenges faced in our approach to combine Hierarchical Task Network planning, Description Logics, and the notions of affordances and conceptual similarity. We present open questions in modeling the necessary knowledge, creating planning problems, and enabling the system to handle cases where plan generation fails due to missing/unavailable objects.
XPERSIF: a software integration framework & architecture for robotic learning by experimentation
(2008)
The integration of independently-developed applications into an efficient system, particularly in a distributed setting, is the core issue addressed in this work. Cooperation between researchers across various field boundaries in order to solve complex problems has become commonplace. Due to the multidisciplinary nature of such efforts, individual applications are developed independent of the integration process. The integration of individual applications into a fully-functioning architecture is a complex and multifaceted task. This thesis extends a component-based architecture, previously developed by the authors, to allow the integration of various software applications which are deployed in a distributed setting. The test bed for the framework is the EU project XPERO, the goal of which is robot learning by experimentation. The task at hand is the integration of the required applications, such as planning of experiments, perception of parametrized features, robot motion control and knowledge-based learning, into a coherent cognitive architecture. This allows a mobile robot to use the methods involved in experimentation in order to learn about its environment. To meet the challenge of developing this architecture within a distributed, heterogeneous environment, the authors specified, defined, developed, implemented and tested a component-based architecture called XPERSIF. The architecture comprises loosely-coupled, autonomous components that offer services through their well-defined interfaces and form a service-oriented architecture. The Ice middleware is used in the communication layer. Its deployment facilitates the necessary refactoring of concepts. One fully specified and detailed use case is the successful integration of the XPERSim simulator which constitutes one of the kernel components of XPERO.The results of this work demonstrate that the proposed architecture is robust and flexible, and can be successfully scaled to allow the complete integration of the necessary applications, thus enabling robot learning by experimentation. The design supports composability, thus allowing components to be grouped together in order to provide an aggregate service. Distributed simulation enabled real time tele-observation of the simulated experiment. Results show that incorporating the XPERSim simulator has substantially enhanced the speed of research and the information flow within the cognitive learning loop.
In this paper, we present XPERSim, a 3D simulator built on top of open source components that enables users to quickly and easily construct an accurate and photo-realistic simulation for robots of arbitrary morphology and their environments. While many existing robot simulators provide a good dynamics simulation, they often lack the high quality visualization that is now possible with general-purpose hardware. XPERSim achieves such visualization by using the Object-Oriented Graphics Rendering Engine 3D (Ogre) engine to render the simulation whose dynamics are calculated using the Open Dynamics Engine (ODE). Through XPERSim’s integration into a component-based software integration framework used for robotic learning by experimentation, XPERSIF, and the use of the scene-oriented nature of the Ogre engine, the simulation is distributed to numerous users that include researchers and robotic components, thus enabling simultaneous, quasi-realtime observation of the multiple-camera simulations.
Representing 3D surfaces as level sets of continuous functions over R3 is the common denominator of neural implicit representations, which recently enabled remarkable progress in geometric deep learning and computer vision tasks. In order to represent 3D motion within this framework, it is often assumed (either explicitly or implicitly) that the transformations which a surface may undergo are homeomorphic: this is not necessarily true, for instance, in the case of fluid dynamics. In order to represent more general classes of deformations, we propose to apply this theoretical framework as regularizers for the optimization of simple 4D implicit functions (such as signed distance fields). We show that our representation is capable of capturing both homeomorphic and topology-changing deformations, while also defining correspondences over the continuously-reconstructed surfaces.
Recent advances in Natural Language Processing have substantially improved contextualized representations of language. However, the inclusion of factual knowledge, particularly in the biomedical domain, remains challenging. Hence, many Language Models (LMs) are extended by Knowledge Graphs (KGs), but most approaches require entity linking (i.e., explicit alignment between text and KG entities). Inspired by single-stream multimodal Transformers operating on text, image and video data, this thesis proposes the Sophisticated Transformer trained on biomedical text and Knowledge Graphs (STonKGs). STonKGs incorporates a novel multimodal architecture based on a cross encoder that uses the attention mechanism on a concatenation of input sequences derived from text and KG triples, respectively. Over 13 million so-called text-triple pairs, coming from PubMed and assembled using the Integrated Network and Dynamical Reasoning Assembler (INDRA), were used in an unsupervised pre-training procedure to learn representations of biomedical knowledge in STonKGs. By comparing STonKGs to an NLP- and a KG-baseline (operating on either text or KG data) on a benchmark consisting of eight fine-tuning tasks, the proposed knowledge integration method applied in STonKGs was empirically validated. Specifically, on tasks with a comparatively small dataset size and a larger number of classes, STonKGs resulted in considerable performance gains, beating the F1-score of the best baseline by up to 0.083. Both the source code as well as the code used to implement STonKGs are made publicly available so that the proposed method of this thesis can be extended to many other biomedical applications.
The majority of biomedical knowledge is stored in structured databases or as unstructured text in scientific publications. This vast amount of information has led to numerous machine learning-based biological applications using either text through natural language processing (NLP) or structured data through knowledge graph embedding models (KGEMs). However, representations based on a single modality are inherently limited. To generate better representations of biological knowledge, we propose STonKGs, a Sophisticated Transformer trained on biomedical text and Knowledge Graphs. This multimodal Transformer uses combined input sequences of structured information from KGs and unstructured text data from biomedical literature to learn joint representations. First, we pre-trained STonKGs on a knowledge base assembled by the Integrated Network and Dynamical Reasoning Assembler (INDRA) consisting of millions of text-triple pairs extracted from biomedical literature by multiple NLP systems. Then, we benchmarked STonKGs against two baseline models trained on either one of the modalities (i.e., text or KG) across eight different classification tasks, each corresponding to a different biological application. Our results demonstrate that STonKGs outperforms both baselines, especially on the more challenging tasks with respect to the number of classes, improving upon the F1-score of the best baseline by up to 0.083. Additionally, our pre-trained model as well as the model architecture can be adapted to various other transfer learning applications. Finally, the source code and pre-trained STonKGs models are available at https://github.com/stonkgs/stonkgs and https://huggingface.co/stonkgs/stonkgs-150k.
MOTIVATION
The majority of biomedical knowledge is stored in structured databases or as unstructured text in scientific publications. This vast amount of information has led to numerous machine learning-based biological applications using either text through natural language processing (NLP) or structured data through knowledge graph embedding models (KGEMs). However, representations based on a single modality are inherently limited.
RESULTS
To generate better representations of biological knowledge, we propose STonKGs, a Sophisticated Transformer trained on biomedical text and Knowledge Graphs (KGs). This multimodal Transformer uses combined input sequences of structured information from KGs and unstructured text data from biomedical literature to learn joint representations in a shared embedding space. First, we pre-trained STonKGs on a knowledge base assembled by the Integrated Network and Dynamical Reasoning Assembler (INDRA) consisting of millions of text-triple pairs extracted from biomedical literature by multiple NLP systems. Then, we benchmarked STonKGs against three baseline models trained on either one of the modalities (i.e., text or KG) across eight different classification tasks, each corresponding to a different biological application. Our results demonstrate that STonKGs outperforms both baselines, especially on the more challenging tasks with respect to the number of classes, improving upon the F1-score of the best baseline by up to 0.084 (i.e., from 0.881 to 0.965). Finally, our pre-trained model as well as the model architecture can be adapted to various other transfer learning applications.
AVAILABILITY
We make the source code and the Python package of STonKGs available at GitHub (https://github.com/stonkgs/stonkgs) and PyPI (https://pypi.org/project/stonkgs/). The pre-trained STonKGs models and the task-specific classification models are respectively available at https://huggingface.co/stonkgs/stonkgs-150k and https://zenodo.org/communities/stonkgs.
SUPPLEMENTARY INFORMATION
Supplementary data are available at Bioinformatics online.
ProtSTonKGs: A Sophisticated Transformer Trained on Protein Sequences, Text, and Knowledge Graphs
(2022)
While most approaches individually exploit unstructured data from the biomedical literature or structured data from biomedical knowledge graphs, their union can better exploit the advantages of such approaches, ultimately improving representations of biology. Using multimodal transformers for such purposes can improve performance on context dependent classication tasks, as demonstrated by our previous model, the Sophisticated Transformer Trained on Biomedical Text and Knowledge Graphs (STonKGs). In this work, we introduce ProtSTonKGs, a transformer aimed at learning all-encompassing representations of protein-protein interactions. ProtSTonKGs presents an extension to our previous work by adding textual protein descriptions and amino acid sequences (i.e., structural information) to the text- and knowledge graph-based input sequence used in STonKGs. We benchmark ProtSTonKGs against STonKGs, resulting in improved F1 scores by up to 0.066 (i.e., from 0.204 to 0.270) in several tasks such as predicting protein interactions in several contexts. Our work demonstrates how multimodal transformers can be used to integrate heterogeneous sources of information, paving the foundation for future approaches that use multiple modalities for biomedical applications.
Target meaning representations for semantic parsing tasks are often based on programming or query languages, such as SQL, and can be formalized by a context-free grammar. Assuming a priori knowledge of the target domain, such grammars can be exploited to enforce syntactical constraints when predicting logical forms. To that end, we assess how syntactical parsers can be integrated into modern encoder-decoder frameworks. Specifically, we implement an attentional SEQ2SEQ model that uses an LR parser to maintain syntactically valid sequences throughout the decoding procedure. Compared to other approaches to grammar-guided decoding that modify the underlying neural network architecture or attempt to derive full parse trees, our approach is conceptually simpler, adds less computational overhead during inference and integrates seamlessly with current SEQ2SEQ frameworks. We present preliminary evaluation results against a recurrent SEQ2SEQ baseline on GEOQUERY and ATIS and demonstrate improved performance while enforcing grammatical constraints.
In this contribution a machine vision inspection system is presented which is designed as a length measuring sensor. It is developed to be applied to a range of heat shrink tubes, varying in length, diameter and color. The challenges of this task were the precision and accuracy demands as well as the real-time applicability of the entire approach since it should be realized in regular industrial line production. In production, heat shrink tubes are cut to specific sizes from a continuous tube. A multi-measurement strategy has been developed, which measures each individual tube segment several times with sub pixel accuracy while being in the visual field. The developed approach allows for a contact-free and fully automatic control of 100% of produced heat shrink tubes according to the given requirements with a measuring precision of 0.1mm. Depending on the color, length and diameter of the tubes considered, a true positive rate of 99.99% to 100% has been reached at a true negative rate of > 99.7.
Diese Arbeit beschäftigt sich mit der Effizienz der Seitenkanal-Kryptanalyse. In Teil II dieser Arbeit demonstrieren wir, wie die Laufzeit der wichtigsten Analysewerkzeuge mit Hilfe der CUDA Plattform erheblich gesteigert werden kann. Zweitens untersuchen wir neue Ansätze der profilierenden Seitenkanal-Kryptanalyse. Der Forschungszweig des maschinellen Lernens kann für deutliche Verbesserungen adaptiert werden, wurde jedoch wenig dahingehend untersucht. In Teil III dieser Arbeit präsentieren wir zwei neue Methoden, die einige Gemeinsamkeiten jedoch auch einige Unterschiede aufbieten, sodass sich Prüfergebnisse in einem vollständigeren Bild zeigen lassen. Darüber hinaus schlagen wir in Teil IV eine Seitenkanalanwendung zum Schutz geistigen Eigentums (IP) vor. In Teil V beschäftigen wir uns tiefergehend mit praktischer Seitenkanal-Kryptanalyse, indem wir Attacken auf einen Sicherheitsmikrokontroller durchführen, der Anwendung in einer, in Deutschland weit verbreiteten, EC Karte findet.
Object-Based Trace Model for Automatic Indicator Computation in the Human Learning Environments
(2021)
This paper proposes a traces model in the form of an object or class model (in the UML sense) which allows the automatic calculation of indicators of various kinds and independently of the computer environment for human learning (CEHL). The model is based on the establishment of a trace-based system that encompasses all the logic of traces collecting and indicators calculation. It is im-plemented in the form of a trace database. It is an important contribution in the field of the exploitation of the traces of apprenticeship in a CEHL because it pro-vides a general formalism for modeling the traces and allowing the calculation of several indicators at the same time. Also, with the inclusion of calculated indica-tors as potential learning traces, our model provides a formalism for classifying the various indicators in the form of inheritance relationships, which promotes the reuse of indicators already calculated. Economically, the model can allow organi-zations with different learning platforms to invest only in one traces Management System. At the social level, it can allow a better sharing of trace databases be-tween the various research institutions in the field of CEHL.
Telepresence robots allow users to be spatially and socially present in remote environments. Yet, it can be challenging to remotely operate telepresence robots, especially in dense environments such as academic conferences or workplaces. In this paper, we primarily focus on the effect that a speed control method, which automatically slows the telepresence robot down when getting closer to obstacles, has on user behaviors. In our first user study, participants drove the robot through a static obstacle course with narrow sections. Results indicate that the automatic speed control method significantly decreases the number of collisions. For the second study we designed a more naturalistic, conference-like experimental environment with tasks that require social interaction, and collected subjective responses from the participants when they were asked to navigate through the environment. While about half of the participants preferred automatic speed control because it allowed for smoother and safer navigation, others did not want to be influenced by an automatic mechanism. Overall, the results suggest that automatic speed control simplifies the user interface for telepresence robots in static dense environments, but should be considered as optionally available, especially in situations involving social interactions.
The Render Cache [1,2] allows the interactive display of very large scenes, rendered with complex global illumination models, by decoupling camera movement from the costly scene sampling process. In this paper, the distributed execution of the individual components of the Render Cache on a PC cluster is shown to be a viable alternative to the shared memory implementation.As the processing power of an entire node can be dedicated to a single component, more advanced algorithms may be examined. Modular functional units also lead to increased flexibility, useful in research as well as industrial applications.We introduce a new strategy for view-driven scene sampling, as well as support for multiple camera viewpoints generated from the same cache. Stereo display and a CAVE multi-camera setup have been implemented.The use of the highly portable and inter-operable CORBA networking API simplifies the integration of most existing pixel-based renderers. So far, three renderers (C++ and Java) have been adapted to function within our framework.
Suppose we have n keys, n access probabilities for the keys, and n+1 access probabilities for the gaps between the keys. Let h_min(n) be the minimal height of a binary search tree for n keys. We consider the problem to construct an optimal binary search tree with near minimal height, i.e.\ with height h <= h_min(n) + Delta for some fixed Delta. It is shown, that for any fixed Delta optimal binary search trees with near minimal height can be constructed in time O(n^2). This is as fast as in the unrestricted case. So far, the best known algorithms for the construction of height-restricted optimal binary search trees have running time O(L n^2), whereby L is the maximal permitted height. Compared to these algorithms our algorithm is at least faster by a factor of log n, because L is lower bounded by log n.
Herein we report an update to ACPYPE, a Python3 tool that now properly converts AMBER to GROMACS topologies for force fields that utilize nondefault and nonuniform 1–4 electrostatic and nonbonded scaling factors or negative dihedral force constants. Prior to this work, ACPYPE only converted AMBER topologies that used uniform, default 1–4 scaling factors and positive dihedral force constants. We demonstrate that the updated ACPYPE accurately transfers the GLYCAM06 force field from AMBER to GROMACS topology files, which employs non-uniform 1–4 scaling factors as well as negative dihedral force constants. Validation was performed using β-d-GlcNAc through gas-phase analysis of dihedral energy curves and probability density functions. The updated ACPYPE retains all of its original functionality, but now allows the simulation of complex glycomolecular systems in GROMACS using AMBER-originated force fields. ACPYPE is available for download at https://github.com/alanwilter/acpype.
Human butyrylcholinesterase (BChE) is a glycoprotein capable of bioscavenging toxic compounds such as organophosphorus (OP) nerve agents. For commercial production of BChE, it is practical to synthesize BChE in non-human expression systems, such as plants or animals. However, the glycosylation profile in these systems is significantly different from the human glycosylation profile, which could result in changes in BChE's structure and function. From our investigation, we found that the glycan attached to ASN241 is both structurally and functionally important due to its close proximity to the BChE tetramerization domain and the active site gorge. To investigate the effects of populating glycosylation site ASN241, monomeric human BChE glycoforms were simulated with and without site ASN241 glycosylated. Our simulations indicate that the structure and function of human BChE are significantly affected by the absence of glycan 241.
Updating a shared data structure in a parallel program is usually done with some sort of high-level synchronization operation to ensure correctness and consistency. However, underlying synchronization instructions in a processor architecture are costly and rather limited in their scalability on larger multi-core/multi-processors systems. In this paper, we examine work queue operations where such costly atomic update operations are replaced with non-atomic modifiers (simple read+write). In this approach, we trade the exact amount of work with atomic operations against doing more and redundant work but without atomic operations and without violating the correctness of the algorithm. We show results for the application of this idea to the concrete scenario of parallel Breadth First Search (BFS) algorithms for undirected graphs on two large NUMA shared memory system with up to 64 cores.
Updating a shared data structure in a parallel program is usually done with some sort of high-level synchronization operation to ensure correctness and consistency. The realization of such high-level synchronization operations is done with appropriate low-level atomic synchronization instructions that the target processor architecture provides. These instructions are costly and often limited in their scalability on larger multi-core / multi-processor systems. In this paper, a technique is discussed that replaces atomic updates of a shared data structure with ordinary and cheaper read/write operations. The necessary conditions are specified that must be fulfilled to ensure overall correctness of the program despite missing synchronization. The advantage of this technique is the reduction of access costs as well as more scalability due to elided atomic operations. But on the other side, possibly more work has to be done caused by missing synchronization. Therefore, additional work is traded against costly atomic operations. A practical application is shown with level-synchronous parallel Breadth-First Search on an undirected graph where two vertex frontiers are accessed in parallel. This application scenario is also used for an evaluation of the technique. Tests were done on four different large parallel systems with up to 64-way parallelism. It will be shown that for the graph application examined the amount of additional work caused by missing synchronization is neglectible and the performance is almost always better than the approach with atomic operations.
Abschlussbericht zum BMBF-Fördervorhaben Enabling Infrastructure for HPC-Applications (EI-HPC)
(2020)
In this paper, a set of micro-benchmarks is proposed to determine basic performance parameters of single-node mainstream hardware architectures for High Performance Computing. Performance parameters of recent processors, including those of accelerators, are determined. The investigated systems are Intel server processor architectures as well as the two accelerator lines Intel Xeon Phi and Nvidia graphic processors. Results show similarities for some parameters between all architectures, but significant differences for others.
Level-Synchronous Parallel Breadth-First Search Algorithms For Multicore and Multiprocessor Systems
(2014)
Breadth-First Search (BFS) is a graph traversal technique used in many applications as a building block, e.g.,~to systematically explore a search space. For modern multicore processors and as application graphs get larger, well-performing parallel algorithms are favourable. In this paper, we systematically evaluate an important class of parallel BFS algorithms and discuss programming optimization techniques for their implementation. We concentrate our discussion on level-synchronous algorithms for larger multicore and multiprocessor systems. In our results, we show that for small core counts many of these algorithms show rather similar behaviour. But, for large core counts and large graphs, there are considerable differences in performance and scalability influenced by several factors. This paper gives advice, which algorithm should be used under which circumstances.
The SpMV operation -- the multiplication of a sparse matrix with a dense vector -- is used in many simulations in natural and engineering sciences as a computational kernel. This kernel is quite performance critical as it is used, e.g.,~in a linear solver many times in a simulation run. Such performance critical kernels of a program may be optimized on certain levels, ranging from using a rather coarse grained and comfortable single compiler optimization switch down to utilizing architecural features by explicitly using special instructions on an assembler level. This paper discusses a selection of such program optimization techniques in this spectrum applied to the SpMV operation. The achievable performance gain as well as the additional programming effort are discussed. It is shown that low effort optimizations can improve the performance of the SpMV operation compared to a basic implementation. But further than that, more complex low level optimizations have a higher impact on the performance, although changing the original program and the readability / maintainability of a program significantly.
SpMV Runtime Improvements with Program Optimization Techniques on Different Abstraction Levels
(2016)
The multiplication of a sparse matrix with a dense vector is a performance critical computational kernel in many applications, especially in natural and engineering sciences. To speed up this operation, many optimization techniques have been developed in the past, mainly focusing on the data layout for the sparse matrix. Strongly related to the data layout is the program code for the multiplication. But even for a fixed data layout with an accommodated kernel, there are several alternatives for program optimizations. This paper discusses a spectrum of program optimization techniques on different abstraction layers for six different sparse matrix data format and kernels. At the one end of the spectrum, compiler options can be used that hide from the programmer all optimizations done by the compiler internally. On the other end of the spectrum, a multiplication kernel can be programmed that use highly sophisticated intrinsics on an assembler level that ask for a programmer with a deep understanding of processor architectures. These special instructions can be used to efficiently utilize hardware features in processors like vector units that have the potential to speed up sparse matrix computations. The paper compares the programming effort and required knowledge level for certain program optimizations in relation to the gained runtime improvements.
In Sensor-based Fault Detection and Diagnosis (SFDD) methods, spatial and temporal dependencies among the sensor signals can be modeled to detect faults in the sensors, if the defined dependencies change over time. In this work, we model Granger causal relationships between pairs of sensor data streams to detect changes in their dependencies. We compare the method on simulated signals with the Pearson correlation, and show that the method elegantly handles noise and lags in the signals and provides appreciable dependency detection. We further evaluate the method using sensor data from a mobile robot by injecting both internal and external faults during operation of the robot. The results show that the method is able to detect changes in the system when faults are injected, but is also prone to detecting false positives. This suggests that this method can be used as a weak detection of faults, but other methods, such as the use of a structural model, are required to reliably detect and diagnose faults.
Using Visual and Auditory Cues to Locate Out-of-View Objects in Head-Mounted Augmented Reality
(2021)
We present an interactive system that uses ray tracing as a rendering technique. The system consists of a modular Virtual Reality framework and a cluster-based ray tracing rendering extension running on a number of Cell Broadband Engine-based servers. The VR framework allows for loading rendering plugins at runtime. By using this combination it is possible to simulate interactively effects from geometric optics, like correct reflections and refractions.
RoCKIn@Work was focused on benchmarks in the domain of industrial robots. Both task and functionality benchmarks were derived from real world applications. All of them were part of a bigger user story painting the picture of a scaled down real world factory scenario. Elements used to build the testbed were chosen from common materials in modern manufacturing environments. Networked devices, machines controllable through a central software component, were also part of the testbed and introduced a dynamic component to the task benchmarks. Strict guidelines on data logging were imposed on participating teams to ensure gathered data could be automatically evaluated. This also had the positive effect that teams were made aware of the importance of data logging, not only during a competition but also during research as useful utility in their own laboratory. Tasks and functionality benchmarks are explained in detail, starting with their use case in industry, further detailing their execution and providing information on scoring and ranking mechanisms for the specific benchmark.
While humans can effortlessly pick a view from multiple streams, automatically choosing the best view is a challenge. Choosing the best view from multi-camera streams poses a problem regarding which objective metrics should be considered. Existing works on view selection lack consensus about which metrics should be considered to select the best view. The literature on view selection describes diverse possible metrics. And strategies such as information-theoretic, instructional design, or aesthetics-motivated fail to incorporate all approaches. In this work, we postulate a strategy incorporating information-theoretic and instructional design-based objective metrics to select the best view from a set of views. Traditionally, information-theoretic measures have been used to find the goodness of a view, such as in 3D rendering. We adapted a similar measure known as the viewpoint entropy for real-world 2D images. Additionally, we incorporated similarity penalization to get a more accurate measure of the entropy of a view, which is one of the metrics for the best view selection. Since the choice of the best view is domain-dependent, we chose demonstration-based training scenarios as our use case. The limitation of our chosen scenarios is that they do not include collaborative training and solely feature a single trainer. To incorporate instructional design considerations, we included the trainer’s body pose, face, face when instructing, and hands visibility as metrics. To incorporate domain knowledge we included predetermined regions’ visibility as another metric. All of those metrics are taken into account to produce a parameterized view recommendation approach for demonstration-based training. An online study using recorded multi-camera video streams from a simulation environment was used to validate those metrics. Furthermore, the responses from the online study were used to optimize the view recommendation performance with a normalized discounted cumulative gain (NDCG) value of 0.912, which shows good performance with respect to matching user choices.
Zentrale Archivierung und verteilte Kommunikation digitaler Bilddaten in der Pneumokoniosevorsorge
(2010)
Pneumokoniose-Vorsorgeuntersuchungen erfordern die Befundung einer Röntgenthoraxaufnahme nach ILO-Staublungenklassifikation. Inzwischen werden die benötigten Aufnahmen bereits in großem Umfang digital angefertigt und kommuniziert. Hierdurch entstehen neue Anforderungen an verwendete Technik und Workflow-Mechanismen, um einen effizienten Ablauf von Untersuchung, Befundung und Dokumentation zu gewährleisten.