05 Fakultät Informatik, Elektrotechnik und Informationstechnik
Permanent URI for this collectionhttps://elib.uni-stuttgart.de/handle/11682/6
Browse
73 results
Search Results
Item Open Access Inferring object hypotheses based on feature motion from different sources(2015) Fuchs, SteffenPerception systems in robotics are typically closely tailored to the given task, e.g., in typical pick-and-place tasks the perception systems only recognizes the mugs that are supposed to be moved and the table the mugs are placed on. The obvious limitation of those systems is that for a new task a new vision system must be designed and implemented. This master's thesis proposes a method that allows to identify entities in the world based on motion of various features from various sources. This is without relying on strong prior assumptions and to provide an important piece towards a more general perception system. While entities are rigid bodies in the world, the sources can be anything that allows to track certain features over time in order to create trajectories. For example, these feature trajectories can be obtained from RGB and RGB-D sensors of a robot, from external cameras, or even the end effector of the robot (proprioception). The core conceptual elements are: the distance variance between trajectory pairs is computed to construct an affinity matrix. This matrix is then used as input for a divisive k-means algorithm in order to cluster trajectories into object hypotheses. In a final step these hypotheses are combined with previously observed hypotheses by computing the correlations between the current and the updated sets. This approach has been evaluated on both simulated and real world data. Generating simulated data provides an elegant way for a qualitative analysis of various scenarios. The real world data was obtained by tracking Shi-Tomasi corners using the Lucas-Kanade optical flow estimation of RGB image sequences and projecting the features into range image space.Item Open Access Lastbalancierungsverfahren für dynamische und heterogene Linked-Cell Molekülsimulation(2015) Hirschmann, SteffenIn dieser Arbeit wird die Lastbalancierung von Molekül- beziehungsweise Teilchensimulationen mit kurzreichweitigen Potenzialen betrachtet. Eine solche ist notwendig, um inhomogene Szenarien effizient über längere Zeiträume hinweg auf Parallelrechnern simulieren zu können. Hierzu werden die vorkommenden Arten von Last analysiert und in sogenannten Lastmodellen quantifiziert. Hierbei liegt der Fokus auf Rechen- und Kommunikationslasten. Anschließend wird das Problem der Lastbalancierung beschrieben. Es werden verschiedene in der Literatur bekannte Verfahren zur Lastbalancierung betrachtet, untersucht und evaluiert. Der Fokus liegt hierbei nicht auf einem einzelnen Anwendungsszenario, sondern auf der generellen Machbarkeit, den Eigenschaften und den Einschränkungen der jeweiligen Verfahren.Item Open Access Robust Quasi-Newton methods for partitioned fluid-structure simulations(2015) Scheufele, KlaudiusIn recent years, quasi-Newton schemes have proven to be a robust and efficient way for the coupling of partitioned multi-physics simulations in particular for fluid-structure interaction. The focus of this work is put on the coupling of partitioned fluid-structure interaction, where minimal interface requirements are assumed for the respective field solvers, thus treated as black box solvers. The coupling is done through communication of boundary values between the solvers. In this thesis a new quasi-Newton variant (IQN-IMVJ) based on a multi-vector update is investigated in combination with serial and parallel coupling systems. Due to implicit incorporation of passed information within the Jacobian update it renders the problem dependent parameter of retained previous time steps unnecessary. Besides, a whole range of coupling schemes are categorized and compared comprehensively with respect to robustness, convergence behaviour and complexity. Those coupling algorithms differ in the structure of the coupling, i.\,e., serial or parallel execution of the field solvers and the used quasi-Newton methods. A more in-depth analysis for a choice of coupling schemes is conducted for a set of strongly coupled FSI benchmark problems, using the in-house coupling library preCICE. The superior convergence behaviour and robust nature of the IQN-IMVJ method compared to well known state of the art methods such as the IQN-ILS method, is demonstrated here. It is confirmed that the multi-vector method works optimal without the need of tuning problem dependent parameters in advance. Furthermore, it appears to be especially suitable in conjunction with the parallel coupling system, in that it yields fairly similar results for parallel and serial coupling. Although we focus on FSI simulation, the considered coupling schemes are supposed to be equally applicable to various kinds of different volume- or surface-coupled problems.Item Open Access Cost optimization for data placement strategies in an analytical cloud service(2016) Saleem, Muhammad UsmanAnalyzing a large amount of business-relevant data in near-realtime in order to assist decision making became a crucial requirement for many businesses in the last years. Therefore, all major database system vendors offer solutions that assist customers in this requirement with systems that are specially tuned for accelerating analytical workloads. Before the decision is made to buy such a huge and expensive solution, customers are interested in getting a detailed workload analysis in order to estimate potential benefits. Therefore, a more agile solution is desirable having lower barriers to entry that allows customers to assess analytical solutions for their workloads and lets data scientists experiment with available data on test systems before rolling out valuable analytical reports on a production system. In such a scenario where separate systems are deployed for handling transactional workloads of daily customers business and conducting business analytics on either a cloud service or a dedicated accelerator appliance, data management and placement strategies are of high importance. Multiple approaches exist for keeping the data set in-sync and guaranteeing data coherence with unique characteristics regarding important metrics that impact query performance, such as the latency when data will be propagated, achievable throughputs for larger data volumes, or the amount of required CPU to detect and deploy data changes. So the important heuristics are analyzed and evolved in order to develop a general model for data placement and maintenance strategies. Based on this theoretical model, a prototype is also implemented that predicts these metrics.Item Open Access Distributed graph processing and partitioning for spatiotemporal queries in the context of camera networks(2015) Maaß, SteffenThis work presents a scalable, distributed architecture for processing spatiotemporal queries in the context of camera networks based on a graph structure. With the ever-increasing presence of cameras and the emergence of camera-networks, e.g., in the context of campus security, it becomes increasingly important to provide a robust and scalable architecture to store and retrieve detected events. In this work a distributed graph processing engine will be presented which is well suited for read and write tasks in the environment of spatiotemporal image-similarity based workloads. The key ideas presented in this work are the architecture of a scalable graph processing system well-suited for processing spatio-temporal queries and the design of a distributed and robust vertex-partitioning strategy for the graph which is being defined by the spatiotemporal attributes of the stored events. The work will show multiple lightweight heuristics for partitioning the graph among the nodes participating in the system, focusing on load-balancing between workers and high edge-locality for vertices. The system and the partitioning strategies will be evaluated, showing that the system scales with the number of workers and the problem size and is able to answer proportionally more queries per second. It will also be shown that the lightweight heuristics for partitioning the graph produce a relatively good balancing of the vertices on the worker-nodes and can be executed in an online-fashion, resulting in similar performance when compared to a traditional hash-partitioning while providing far superior edge-locality.Item Open Access Optimized acquisition of spatially distributed phenomena in public sensing systems(2011) Stachowiak, JaroslawNowadays, an increasing number of popular consumer electronics is shipped with a variety of sensors. The usage of these as a wireless sensing platform, where users are the key architectural component, and ubiquitous access to communication infrastructure has established a new application area called public sensing. We present an opportunistic public sensing system that allows for a flexible and efficient acquisition of sensor readings. This work considers the usage of smartphones as a sensor network in a model-driven sensor data acquisition. We focus on efficiency of query dissemination to mobile nodes, while retaining high effectiveness regarding defined sensing quality of collected data. We adopted and extended an existing geographic routing protocol to design an efficient com- munication system that executes model-driven data acquisition and is robust to changing sensors availability. We use in-network processing paradigm to efficiently distribute queries to mobile nodes and to collect results afterwards. The developed approach was simulated using OMNeT++ network simulator. To verify implemented algorithms and test the overall system performance, we run simulations in different scenarios and evaluate them using adequate cov- erage metrics. Moreover, we verify our intuitive extension to adopted routing protocol and show that it can have a strong impact on the efficiency of protocol in question.Item Open Access Design and implementation of TOSCA Service Templates for provisioning and executing bone simulation in cloud environments(2015) Dehghanipour, MarziehRecent years have shown an increasing trend to move applications and services into cloud infrastructures. Cloud-based applications typically consist of distributed components which are connected and communicate with each other. Automating the deployment and management of these components is one of the major challenges in IT world. The OASIS TOSCA standard provides a meta-model for describing the structure of composite cloud-based applications, which provides automation for deployment and management of these applications. TOSCA-based applications may be executed via the OpenTOSCA (a run-time environment for TOSCA-based applications) environment, which has been developed by the University of Stuttgart. Simulation applications deal with heterogeneous and huge data sources. Adequate data management and data provisioning for these applications are some of the most significant challenges for simulation applications. SIMPL is a framework which provides a generic approach for data management and data provisioning in simulation applications. SIMPL frees users to deal with any low-level details of data sources and corresponding data management operations. Both the TOSCA standard and the SIMPL framework are based on workflows. The first goal of this master's thesis is to combine the TOSCA standard with the SIMPL framework in order to enable the generic data provisioning and data management approach offered by SIMPL as an integral part of the TOSCA standard. A further and main part of this work is to design and implement TOSCA Service Templates for provisioning and executing bone simulations in cloud environments. Different variants of a TOSCA Service Template realizing a bone simulation in a cloud-native way have to be developed and implemented. In other words, a SaaS solution for PANDAS bone simulation is provided in the scope of this master's thesis with the help of TOSCA and SIMPL technologies.Item Open Access Kooperative Vorhersage der minimalen Anwendungsausführungszeit(2016) Kuhn, JulianCode Offloading Frameworks verbessern durch Auslagern von Programmteilen - auch Offloadingkandidaten genannt - auf Server die Leistung oder den Energieverbrauch von Geräten mit limitierten Ressourcen. Offloadingkandidaten werden dann ausgelagert, wenn mit Inbetrachtnahme der Übertragung des Kandidaten eine Einsparung im Vergleich zur rein lokalen Ausführung vorliegt. Die Entscheidung, ob Offloading stattfindet, hängt stark von der Ausführungszeit des Kandidaten ab. Im Fall von Methoden kann die Ausführungszeit je nach aktueller Parameterkonfiguration stark variieren. Da es in vielen Fällen unpraktikabel ist, für jede Parameterkombination Aufzeichnungen durchzuführen, ist die Verwendung von einfachen, historienbasierten Modellen zur Bestimmung der Ausführungszeit ungeeignet. Eine möglichst genaue Angabe der Ausführungszeit wird aber benötigt, um die Offloadingentscheidung korrekt zu treffen. Ziel der Arbeit war, die Vorhersage von Ausführungszeiten mit Hilfe von Machine Learning Modellen anhand verschiedener Testanwendungen- und Szenarien im Kontext des Code Off-loadings zu untersuchen. Außerdem wurde ein kooperativer Systementwurf vorgestellt und implementiert, der zur Verwaltung von Datensätzen, Vorhersagemodellen und deren Erstellung, sowie zur Vorhersage von Ausführungszeiten verwendet werden kann. Der Entwurf erweitert dabei bestehende Offloadingframeworks. Es konnte festgestellt werden, dass sich Machine Learning Algorithmen zur Vorhersage und insbesondere zum Verbessern der Offloadingentscheidung eignen.Item Open Access Reliability solutions for a smart digital factory using: (1) RFID based CEP; (2) Image processing based error detection; (3) RFID based HCI(2011) Badr, EidNew technologies have a great influence on the production process in modern factories. Introducing new techniques and methods is crucial to optimize and enhance the working of factories. However, ensuring a reliable and correct integration requires complete evaluation and assessment. In this thesis I utilize RFID systems and image processing to develop and implement real time solutions to enhance and optimize the production and assembly processes. Solutions include: RFID based CEP to detect production error, image processing based errors detection to detect post-assembly errors, and RFID based HCI to help workers in assembling products. Errors that are detected using RFID are: sequence errors, synchronization errors, pre-assembly order errors, part-product mismatch error, and missing parts errors. Errors that are detected using image processing are: incorrect part position errors and missing parts errors. RFID based HCI consists of a tool to help workers at assembly points to correctly assemble parts to their products using visual instruction. I have constructed prototypes for all the solutions. As well, I have deployed them in the Lernfabrik(learning factory) which is a real manufacturing environment for practising the production and assembly processes for trainees and students. Under the optimal settings of the RFID readers and tags, the system detects all types of errors reliably in real time. The image processing algorithm detects errors with 100% accuracy in real and normal lighting conditions of the Lernfabrik.Item Open Access Automatic splitting in data-parallel complex event processing systems(2016) Sanwald, TimParallel Complex Event Processing (CEP) systems handle today’s heavy loaded event streams from smart homes, network traffic systems or stock trading systems by distributing the incoming event stream to several pattern detection systems. The correct splitting is currently done by CEP experts which ensure the consistent splitting without generating false-positive or false-negative complex events in comparison with centralized CEP systems. In this work an approach is developed which automatically generates a splitting model from the pattern definition which ensures the consistent distribution without generating false positives or false negatives. This approach enables a parallel CEP system to be configured and used the same way as a centralized CEP system. Further, a method which combines window based splitting and key based splitting is presented to reduce the network load and the CPU load on pattern detection operators. The functionality of the automatic splitting and the optimization is validated with common CEP scenarios based on generated and real world data to ensure a wide applicability of the approach.