@phdthesis{Boehm2013,
  author    = {B{\"o}hm, Christoph},
  title     = {Enriching the Web of Data with topics and links},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-68624},
  school      = {Universit{\"a}t Potsdam},
  year      = {2013},
  abstract  = {This thesis presents novel ideas and research findings for the Web of Data - a global data space spanning many so-called Linked Open Data sources. Linked Open Data adheres to a set of simple principles to allow easy access and reuse for data published on the Web. Linked Open Data is by now an established concept and many (mostly academic) publishers adopted the principles building a powerful web of structured knowledge available to everybody. However, so far, Linked Open Data does not yet play a significant role among common web technologies that currently facilitate a high-standard Web experience. In this work, we thoroughly discuss the state-of-the-art for Linked Open Data and highlight several shortcomings - some of them we tackle in the main part of this work. First, we propose a novel type of data source meta-information, namely the topics of a dataset. This information could be published with dataset descriptions and support a variety of use cases, such as data source exploration and selection. For the topic retrieval, we present an approach coined Annotated Pattern Percolation (APP), which we evaluate with respect to topics extracted from Wikipedia portals. Second, we contribute to entity linking research by presenting an optimization model for joint entity linking, showing its hardness, and proposing three heuristics implemented in the LINked Data Alignment (LINDA) system. Our first solution can exploit multi-core machines, whereas the second and third approach are designed to run in a distributed shared-nothing environment. We discuss and evaluate the properties of our approaches leading to recommendations which algorithm to use in a specific scenario. The distributed algorithms are among the first of their kind, i.e., approaches for joint entity linking in a distributed fashion. Also, we illustrate that we can tackle the entity linking problem on the very large scale with data comprising more than 100 millions of entity representations from very many sources. Finally, we approach a sub-problem of entity linking, namely the alignment of concepts. We again target a method that looks at the data in its entirety and does not neglect existing relations. Also, this concept alignment method shall execute very fast to serve as a preprocessing for further computations. Our approach, called Holistic Concept Matching (HCM), achieves the required speed through grouping the input by comparing so-called knowledge representations. Within the groups, we perform complex similarity computations, relation conclusions, and detect semantic contradictions. The quality of our result is again evaluated on a large and heterogeneous dataset from the real Web. In summary, this work contributes a set of techniques for enhancing the current state of the Web of Data. All approaches have been tested on large and heterogeneous real-world input.},
  language  = {en}
}
@phdthesis{Kyprianidis2013,
  author    = {Kyprianidis, Jan Eric},
  title     = {Structure adaptive stylization of images and video},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-64104},
  school      = {Universit{\"a}t Potsdam},
  year      = {2013},
  abstract  = {In the early days of computer graphics, research was mainly driven by the goal to create realistic synthetic imagery. By contrast, non-photorealistic computer graphics, established as its own branch of computer graphics in the early 1990s, is mainly motivated by concepts and principles found in traditional art forms, such as painting, illustration, and graphic design, and it investigates concepts and techniques that abstract from reality using expressive, stylized, or illustrative rendering techniques. This thesis focuses on the artistic stylization of two-dimensional content and presents several novel automatic techniques for the creation of simplified stylistic illustrations from color images, video, and 3D renderings. Primary innovation of these novel techniques is that they utilize the smooth structure tensor as a simple and efficient way to obtain information about the local structure of an image. More specifically, this thesis contributes to knowledge in this field in the following ways. First, a comprehensive review of the structure tensor is provided. In particular, different methods for integrating the minor eigenvector field of the smoothed structure tensor are developed, and the superiority of the smoothed structure tensor over the popular edge tangent flow is demonstrated. Second, separable implementations of the popular bilateral and difference of Gaussians filters that adapt to the local structure are presented. These filters avoid artifacts while being computationally highly efficient. Taken together, both provide an effective way to create a cartoon-style effect. Third, a generalization of the Kuwahara filter is presented that avoids artifacts by adapting the shape, scale, and orientation of the filter to the local structure. This causes directional image features to be better preserved and emphasized, resulting in overall sharper edges and a more feature-abiding painterly effect. In addition to the single-scale variant, a multi-scale variant is presented, which is capable of performing a highly aggressive abstraction. Fourth, a technique that builds upon the idea of combining flow-guided smoothing with shock filtering is presented, allowing for an aggressive exaggeration and an emphasis of directional image features. All presented techniques are suitable for temporally coherent per-frame filtering of video or dynamic 3D renderings, without requiring expensive extra processing, such as optical flow. Moreover, they can be efficiently implemented to process content in real-time on a GPU.},
  language  = {en}
}
@phdthesis{Yang2013,
  author    = {Yang, Haojin},
  title     = {Automatic video indexing and retrieval using video ocr technology},
  address   = {Potsdam},
  pages     = {182 S.},
  year      = {2013},
  language  = {en}
}
@phdthesis{Trapp2013,
  author    = {Trapp, Matthias},
  title     = {Interactive rendering techniques for focus+context visualization of 3D geovirtual environments},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-66824},
  school      = {Universit{\"a}t Potsdam},
  year      = {2013},
  abstract  = {This thesis introduces a collection of new real-time rendering techniques and applications for focus+context visualization of interactive 3D geovirtual environments such as virtual 3D city and landscape models. These environments are generally characterized by a large number of objects and are of high complexity with respect to geometry and textures. For these reasons, their interactive 3D rendering represents a major challenge. Their 3D depiction implies a number of weaknesses such as occlusions, cluttered image contents, and partial screen-space usage. To overcome these limitations and, thus, to facilitate the effective communication of geo-information, principles of focus+context visualization can be used for the design of real-time 3D rendering techniques for 3D geovirtual environments (see Figure). In general, detailed views of a 3D geovirtual environment are combined seamlessly with abstracted views of the context within a single image. To perform the real-time image synthesis required for interactive visualization, dedicated parallel processors (GPUs) for rasterization of computer graphics primitives are used. For this purpose, the design and implementation of appropriate data structures and rendering pipelines are necessary. The contribution of this work comprises the following five real-time rendering methods: • The rendering technique for 3D generalization lenses enables the combination of different 3D city geometries (e.g., generalized versions of a 3D city model) in a single image in real time. The method is based on a generalized and fragment-precise clipping approach, which uses a compressible, raster-based data structure. It enables the combination of detailed views in the focus area with the representation of abstracted variants in the context area. • The rendering technique for the interactive visualization of dynamic raster data in 3D geovirtual environments facilitates the rendering of 2D surface lenses. It enables a flexible combination of different raster layers (e.g., aerial images or videos) using projective texturing for decoupling image and geometry data. Thus, various overlapping and nested 2D surface lenses of different contents can be visualized interactively. • The interactive rendering technique for image-based deformation of 3D geovirtual environments enables the real-time image synthesis of non-planar projections, such as cylindrical and spherical projections, as well as multi-focal 3D fisheye-lenses and the combination of planar and non-planar projections. • The rendering technique for view-dependent multi-perspective views of 3D geovirtual environments, based on the application of global deformations to the 3D scene geometry, can be used for synthesizing interactive panorama maps to combine detailed views close to the camera (focus) with abstract views in the background (context). This approach reduces occlusions, increases the usage the available screen space, and reduces the overload of image contents. • The object-based and image-based rendering techniques for highlighting objects and focus areas inside and outside the view frustum facilitate preattentive perception. The concepts and implementations of interactive image synthesis for focus+context visualization and their selected applications enable a more effective communication of spatial information, and provide building blocks for design and development of new applications and systems in the field of 3D geovirtual environments.},
  language  = {en}
}
@phdthesis{Gros2013,
  author    = {Gros, Oliver},
  title     = {Computergest{\"u}tzte Wissensextraktion aus befundtexten der Pathologie},
  address   = {Potsdam},
  pages     = {170 S.},
  year      = {2013},
  language  = {de}
}
@phdthesis{Neumann2013,
  author    = {Neumann, Stefan},
  title     = {Modular timing analysis of component-based real-time embedded systems},
  address   = {Potsdam},
  pages     = {218 S.},
  year      = {2013},
  language  = {en}
}
@phdthesis{Phusanga2013,
  author    = {Phusanga, Dara},
  title     = {Derived algebraic systems},
  address   = {Potsdam},
  pages     = {81 S.},
  year      = {2013},
  language  = {en}
}
@phdthesis{Schaffner2013,
  author    = {Schaffner, Jan},
  title     = {Multi tenancy for cloud-based in-memory column databases : workload management and data placement},
  address   = {Potsdam},
  pages     = {135 S.},
  year      = {2013},
  language  = {en}
}
@phdthesis{Alsadeh2013,
  author    = {Alsadeh, Ahmad},
  title     = {Augmented secure neighbor discovery: aligning security, privacy and usability},
  address   = {Potsdam},
  pages     = {114 S.},
  year      = {2013},
  language  = {en}
}
@phdthesis{Hentschel2013,
  author    = {Hentschel, Uwe},
  title     = {Steuerung der Daten{\"u}bertragung in {\"o}ffentlichen zellularen Funknetzen im Kontext telemedizinischer Anwendung},
  address   = {Potsdam},
  pages     = {224 S.},
  year      = {2013},
  language  = {de}
}
@phdthesis{Albrecht2013,
  author    = {Albrecht, Alexander},
  title     = {Understanding and managing extract-transform-load systems},
  pages     = {107},
  year      = {2013},
  language  = {en}
}
@phdthesis{Haider2013,
  author    = {Haider, Peter},
  title     = {Prediction with Mixture Models},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-69617},
  school      = {Universit{\"a}t Potsdam},
  year      = {2013},
  abstract  = {Learning a model for the relationship between the attributes and the annotated labels of data examples serves two purposes. Firstly, it enables the prediction of the label for examples without annotation. Secondly, the parameters of the model can provide useful insights into the structure of the data. If the data has an inherent partitioned structure, it is natural to mirror this structure in the model. Such mixture models predict by combining the individual predictions generated by the mixture components which correspond to the partitions in the data. Often the partitioned structure is latent, and has to be inferred when learning the mixture model. Directly evaluating the accuracy of the inferred partition structure is, in many cases, impossible because the ground truth cannot be obtained for comparison. However it can be assessed indirectly by measuring the prediction accuracy of the mixture model that arises from it. This thesis addresses the interplay between the improvement of predictive accuracy by uncovering latent cluster structure in data, and further addresses the validation of the estimated structure by measuring the accuracy of the resulting predictive model. In the application of filtering unsolicited emails, the emails in the training set are latently clustered into advertisement campaigns. Uncovering this latent structure allows filtering of future emails with very low false positive rates. In order to model the cluster structure, a Bayesian clustering model for dependent binary features is developed in this thesis. Knowing the clustering of emails into campaigns can also aid in uncovering which emails have been sent on behalf of the same network of captured hosts, so-called botnets. This association of emails to networks is another layer of latent clustering. Uncovering this latent structure allows service providers to further increase the accuracy of email filtering and to effectively defend against distributed denial-of-service attacks. To this end, a discriminative clustering model is derived in this thesis that is based on the graph of observed emails. The partitionings inferred using this model are evaluated through their capacity to predict the campaigns of new emails. Furthermore, when classifying the content of emails, statistical information about the sending server can be valuable. Learning a model that is able to make use of it requires training data that includes server statistics. In order to also use training data where the server statistics are missing, a model that is a mixture over potentially all substitutions thereof is developed. Another application is to predict the navigation behavior of the users of a website. Here, there is no a priori partitioning of the users into clusters, but to understand different usage scenarios and design different layouts for them, imposing a partitioning is necessary. The presented approach simultaneously optimizes the discriminative as well as the predictive power of the clusters. Each model is evaluated on real-world data and compared to baseline methods. The results show that explicitly modeling the assumptions about the latent cluster structure leads to improved predictions compared to the baselines. It is beneficial to incorporate a small number of hyperparameters that can be tuned to yield the best predictions in cases where the prediction accuracy can not be optimized directly.},
  language  = {en}
}
@phdthesis{Holz2013,
  author    = {Holz, Christian},
  title     = {3D from 2D touch},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-67796},
  school      = {Universit{\"a}t Potsdam},
  year      = {2013},
  abstract  = {While interaction with computers used to be dominated by mice and keyboards, new types of sensors now allow users to interact through touch, speech, or using their whole body in 3D space. These new interaction modalities are often referred to as "natural user interfaces" or "NUIs." While 2D NUIs have experienced major success on billions of mobile touch devices sold, 3D NUI systems have so far been unable to deliver a mobile form factor, mainly due to their use of cameras. The fact that cameras require a certain distance from the capture volume has prevented 3D NUI systems from reaching the flat form factor mobile users expect. In this dissertation, we address this issue by sensing 3D input using flat 2D sensors. The systems we present observe the input from 3D objects as 2D imprints upon physical contact. By sampling these imprints at very high resolutions, we obtain the objects' textures. In some cases, a texture uniquely identifies a biometric feature, such as the user's fingerprint. In other cases, an imprint stems from the user's clothing, such as when walking on multitouch floors. By analyzing from which part of the 3D object the 2D imprint results, we reconstruct the object's pose in 3D space. While our main contribution is a general approach to sensing 3D input on 2D sensors upon physical contact, we also demonstrate three applications of our approach. (1) We present high-accuracy touch devices that allow users to reliably touch targets that are a third of the size of those on current touch devices. We show that different users and 3D finger poses systematically affect touch sensing, which current devices perceive as random input noise. We introduce a model for touch that compensates for this systematic effect by deriving the 3D finger pose and the user's identity from each touch imprint. We then investigate this systematic effect in detail and explore how users conceptually touch targets. Our findings indicate that users aim by aligning visual features of their fingers with the target. We present a visual model for touch input that eliminates virtually all systematic effects on touch accuracy. (2) From each touch, we identify users biometrically by analyzing their fingerprints. Our prototype Fiberio integrates fingerprint scanning and a display into the same flat surface, solving a long-standing problem in human-computer interaction: secure authentication on touchscreens. Sensing 3D input and authenticating users upon touch allows Fiberio to implement a variety of applications that traditionally require the bulky setups of current 3D NUI systems. (3) To demonstrate the versatility of 3D reconstruction on larger touch surfaces, we present a high-resolution pressure-sensitive floor that resolves the texture of objects upon touch. Using the same principles as before, our system GravitySpace analyzes all imprints and identifies users based on their shoe soles, detects furniture, and enables accurate touch input using feet. By classifying all imprints, GravitySpace detects the users' body parts that are in contact with the floor and then reconstructs their 3D body poses using inverse kinematics. GravitySpace thus enables a range of applications for future 3D NUI systems based on a flat sensor, such as smart rooms in future homes. We conclude this dissertation by projecting into the future of mobile devices. Focusing on the mobility aspect of our work, we explore how NUI devices may one day augment users directly in the form of implanted devices.},
  language  = {en}
}
@phdthesis{Scheffler2013,
  author    = {Scheffler, Thomas},
  title     = {Privacy enforcement with data owner-defined policies},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-67939},
  school      = {Universit{\"a}t Potsdam},
  year      = {2013},
  abstract  = {This thesis proposes a privacy protection framework for the controlled distribution and use of personal private data. The framework is based on the idea that privacy policies can be set directly by the data owner and can be automatically enforced against the data user. Data privacy continues to be a very important topic, as our dependency on electronic communication maintains its current growth, and private data is shared between multiple devices, users and locations. The growing amount and the ubiquitous availability of personal private data increases the likelihood of data misuse. Early privacy protection techniques, such as anonymous email and payment systems have focused on data avoidance and anonymous use of services. They did not take into account that data sharing cannot be avoided when people participate in electronic communication scenarios that involve social interactions. This leads to a situation where data is shared widely and uncontrollably and in most cases the data owner has no control over further distribution and use of personal private data. Previous efforts to integrate privacy awareness into data processing workflows have focused on the extension of existing access control frameworks with privacy aware functions or have analysed specific individual problems such as the expressiveness of policy languages. So far, very few implementations of integrated privacy protection mechanisms exist and can be studied to prove their effectiveness for privacy protection. Second level issues that stem from practical application of the implemented mechanisms, such as usability, life-time data management and changes in trustworthiness have received very little attention so far, mainly because they require actual implementations to be studied. Most existing privacy protection schemes silently assume that it is the privilege of the data user to define the contract under which personal private data is released. Such an approach simplifies policy management and policy enforcement for the data user, but leaves the data owner with a binary decision to submit or withhold his or her personal data based on the provided policy. We wanted to empower the data owner to express his or her privacy preferences through privacy policies that follow the so-called Owner-Retained Access Control (ORAC) model. ORAC has been proposed by McCollum, et al. as an alternate access control mechanism that leaves the authority over access decisions by the originator of the data. The data owner is given control over the release policy for his or her personal data, and he or she can set permissions or restrictions according to individually perceived trust values. Such a policy needs to be expressed in a coherent way and must allow the deterministic policy evaluation by different entities. The privacy policy also needs to be communicated from the data owner to the data user, so that it can be enforced. Data and policy are stored together as a Protected Data Object that follows the Sticky Policy paradigm as defined by Mont, et al. and others. We developed a unique policy combination approach that takes usability aspects for the creation and maintenance of policies into consideration. Our privacy policy consists of three parts: A Default Policy provides basic privacy protection if no specific rules have been entered by the data owner. An Owner Policy part allows the customisation of the default policy by the data owner. And a so-called Safety Policy guarantees that the data owner cannot specify disadvantageous policies, which, for example, exclude him or her from further access to the private data. The combined evaluation of these three policy-parts yields the necessary access decision. The automatic enforcement of privacy policies in our protection framework is supported by a reference monitor implementation. We started our work with the development of a client-side protection mechanism that allows the enforcement of data-use restrictions after private data has been released to the data user. The client-side enforcement component for data-use policies is based on a modified Java Security Framework. Privacy policies are translated into corresponding Java permissions that can be automatically enforced by the Java Security Manager. When we later extended our work to implement server-side protection mechanisms, we found several drawbacks for the privacy enforcement through the Java Security Framework. We solved this problem by extending our reference monitor design to use Aspect-Oriented Programming (AOP) and the Java Reflection API to intercept data accesses in existing applications and provide a way to enforce data owner-defined privacy policies for business applications.},
  language  = {en}
}
@phdthesis{Dawoud2013,
  author    = {Dawoud, Wesam},
  title     = {Scalability and performance management of internet applications in the cloud},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-68187},
  school      = {Universit{\"a}t Potsdam},
  year      = {2013},
  abstract  = {Cloud computing is a model for enabling on-demand access to a shared pool of computing resources. With virtually limitless on-demand resources, a cloud environment enables the hosted Internet application to quickly cope when there is an increase in the workload. However, the overhead of provisioning resources exposes the Internet application to periods of under-provisioning and performance degradation. Moreover, the performance interference, due to the consolidation in the cloud environment, complicates the performance management of the Internet applications. In this dissertation, we propose two approaches to mitigate the impact of the resources provisioning overhead. The first approach employs control theory to scale resources vertically and cope fast with workload. This approach assumes that the provider has knowledge and control over the platform running in the virtual machines (VMs), which limits it to Platform as a Service (PaaS) and Software as a Service (SaaS) providers. The second approach is a customer-side one that deals with the horizontal scalability in an Infrastructure as a Service (IaaS) model. It addresses the trade-off problem between cost and performance with a multi-goal optimization solution. This approach finds the scale thresholds that achieve the highest performance with the lowest increase in the cost. Moreover, the second approach employs a proposed time series forecasting algorithm to scale the application proactively and avoid under-utilization periods. Furthermore, to mitigate the interference impact on the Internet application performance, we developed a system which finds and eliminates the VMs suffering from performance interference. The developed system is a light-weight solution which does not imply provider involvement. To evaluate our approaches and the designed algorithms at large-scale level, we developed a simulator called (ScaleSim). In the simulator, we implemented scalability components acting as the scalability components of Amazon EC2. The current scalability implementation in Amazon EC2 is used as a reference point for evaluating the improvement in the scalable application performance. ScaleSim is fed with realistic models of the RUBiS benchmark extracted from the real environment. The workload is generated from the access logs of the 1998 world cup website. The results show that optimizing the scalability thresholds and adopting proactive scalability can mitigate 88\% of the resources provisioning overhead impact with only a 9\% increase in the cost.},
  language  = {en}
}