@book{DraisbachNaumannSzottetal.2012,
  author    = {Draisbach, Uwe and Naumann, Felix and Szott, Sascha and Wonneberg, Oliver},
  title     = {Adaptive windows for duplicate detection},
  publisher = {Universit{\"a}tsverlag Potsdam},
  address   = {Potsdam},
  isbn      = {978-3-86956-143-1},
  issn      = {1613-5652},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-53007},
  publisher      = {Universit{\"a}t Potsdam},
  pages     = {41},
  year      = {2012},
  abstract  = {Duplicate detection is the task of identifying all groups of records within a data set that represent the same real-world entity, respectively. This task is difficult, because (i) representations might differ slightly, so some similarity measure must be defined to compare pairs of records and (ii) data sets might have a high volume making a pair-wise comparison of all records infeasible. To tackle the second problem, many algorithms have been suggested that partition the data set and compare all record pairs only within each partition. One well-known such approach is the Sorted Neighborhood Method (SNM), which sorts the data according to some key and then advances a window over the data comparing only records that appear within the same window. We propose several variations of SNM that have in common a varying window size and advancement. The general intuition of such adaptive windows is that there might be regions of high similarity suggesting a larger window size and regions of lower similarity suggesting a smaller window size. We propose and thoroughly evaluate several adaption strategies, some of which are provably better than the original SNM in terms of efficiency (same results with fewer comparisons).},
  language  = {en}
}
@book{PlattnerZeier2012,
  author    = {Plattner, Hasso and Zeier, Alexander},
  title     = {In-Memory Data Management},
  publisher = {Springer},
  address   = {Wiesbaden},
  isbn      = {978-3-8349-4378-1},
  publisher      = {Universit{\"a}t Potsdam},
  pages     = {200},
  year      = {2012},
  abstract  = {Nach 50 Jahren erfolgreicher Entwicklunghat die Business-IT einen neuenWendepunkt erreicht. Hier zeigen die Autoren erstmalig, wieIn-Memory Computing dieUnternehmensprozesse k{\"u}nftig ver{\"a}ndern wird. Bisher wurden Unternehmensdaten aus Performance-Gr{\"u}nden auf verschiedene Datenbanken verteilt: Analytische Datenresidieren in Data Warehouses und werden regelm{\"a}ßig mithilfe transaktionaler Systeme synchronisiert. Diese Aufspaltung macht flexibles Echtzeit-Reporting aktueller Daten unm{\"o}glich. Doch dank leistungsf{\"a}higerMulti-Core-CPUs, großer Hauptspeicher, Cloud Computing und immerbesserer mobiler Endger{\"a}te lassen die Unternehmen dieses restriktive Modell zunehmend hinter sich. Die Autoren stellen Techniken vor, die eine analytische und transaktionale Verarbeitung in Echtzeit erlauben und so dem Gesch{\"a}ftsleben neue Wege bahnen.},
  language  = {de}
}
@phdthesis{Brueckner2012,
  author    = {Br{\"u}ckner, Michael},
  title     = {Prediction games : machine learning in the presence of an adversary},
  publisher = {Universit{\"a}tsverlag Potsdam},
  address   = {Potsdam},
  isbn      = {978-3-86956-203-2},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-60375},
  school      = {Universit{\"a}t Potsdam},
  pages     = {x, 121},
  year      = {2012},
  abstract  = {In many applications one is faced with the problem of inferring some functional relation between input and output variables from given data. Consider, for instance, the task of email spam filtering where one seeks to find a model which automatically assigns new, previously unseen emails to class spam or non-spam. Building such a predictive model based on observed training inputs (e.g., emails) with corresponding outputs (e.g., spam labels) is a major goal of machine learning. Many learning methods assume that these training data are governed by the same distribution as the test data which the predictive model will be exposed to at application time. That assumption is violated when the test data are generated in response to the presence of a predictive model. This becomes apparent, for instance, in the above example of email spam filtering. Here, email service providers employ spam filters and spam senders engineer campaign templates such as to achieve a high rate of successful deliveries despite any filters. Most of the existing work casts such situations as learning robust models which are unsusceptible against small changes of the data generation process. The models are constructed under the worst-case assumption that these changes are performed such to produce the highest possible adverse effect on the performance of the predictive model. However, this approach is not capable to realistically model the true dependency between the model-building process and the process of generating future data. We therefore establish the concept of prediction games: We model the interaction between a learner, who builds the predictive model, and a data generator, who controls the process of data generation, as an one-shot game. The game-theoretic framework enables us to explicitly model the players' interests, their possible actions, their level of knowledge about each other, and the order at which they decide for an action. We model the players' interests as minimizing their own cost function which both depend on both players' actions. The learner's action is to choose the model parameters and the data generator's action is to perturbate the training data which reflects the modification of the data generation process with respect to the past data. We extensively study three instances of prediction games which differ regarding the order in which the players decide for their action. We first assume that both player choose their actions simultaneously, that is, without the knowledge of their opponent's decision. We identify conditions under which this Nash prediction game has a meaningful solution, that is, a unique Nash equilibrium, and derive algorithms that find the equilibrial prediction model. As a second case, we consider a data generator who is potentially fully informed about the move of the learner. This setting establishes a Stackelberg competition. We derive a relaxed optimization criterion to determine the solution of this game and show that this Stackelberg prediction game generalizes existing prediction models. Finally, we study the setting where the learner observes the data generator's action, that is, the (unlabeled) test data, before building the predictive model. As the test data and the training data may be governed by differing probability distributions, this scenario reduces to learning under covariate shift. We derive a new integrated as well as a two-stage method to account for this data set shift. In case studies on email spam filtering we empirically explore properties of all derived models as well as several existing baseline methods. We show that spam filters resulting from the Nash prediction game as well as the Stackelberg prediction game in the majority of cases outperform other existing baseline methods.},
  language  = {en}
}
@book{KrauseGiese2012,
  author    = {Krause, Christian and Giese, Holger},
  title     = {Quantitative modeling and analysis of service-oriented real-time systems using interval probabilistic timed automata},
  publisher = {Universit{\"a}tsverlah Potsdam},
  address   = {Potsdam},
  isbn      = {978-3-86956-171-4},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-57845},
  publisher      = {Universit{\"a}t Potsdam},
  pages     = {45},
  year      = {2012},
  abstract  = {One of the key challenges in service-oriented systems engineering is the prediction and assurance of non-functional properties, such as the reliability and the availability of composite interorganizational services. Such systems are often characterized by a variety of inherent uncertainties, which must be addressed in the modeling and the analysis approach. The different relevant types of uncertainties can be categorized into (1) epistemic uncertainties due to incomplete knowledge and (2) randomization as explicitly used in protocols or as a result of physical processes. In this report, we study a probabilistic timed model which allows us to quantitatively reason about nonfunctional properties for a restricted class of service-oriented real-time systems using formal methods. To properly motivate the choice for the used approach, we devise a requirements catalogue for the modeling and the analysis of probabilistic real-time systems with uncertainties and provide evidence that the uncertainties of type (1) and (2) in the targeted systems have a major impact on the used models and require distinguished analysis approaches. The formal model we use in this report are Interval Probabilistic Timed Automata (IPTA). Based on the outlined requirements, we give evidence that this model provides both enough expressiveness for a realistic and modular specifiation of the targeted class of systems, and suitable formal methods for analyzing properties, such as safety and reliability properties in a quantitative manner. As technical means for the quantitative analysis, we build on probabilistic model checking, specifically on probabilistic time-bounded reachability analysis and computation of expected reachability rewards and costs. To carry out the quantitative analysis using probabilistic model checking, we developed an extension of the Prism tool for modeling and analyzing IPTA. Our extension of Prism introduces a means for modeling probabilistic uncertainty in the form of probability intervals, as required for IPTA. For analyzing IPTA, our Prism extension moreover adds support for probabilistic reachability checking and computation of expected rewards and costs. We discuss the performance of our extended version of Prism and compare the interval-based IPTA approach to models with fixed probabilities.},
  language  = {en}
}
@book{GieseHildebrandtNeumannetal.2012,
  author    = {Giese, Holger and Hildebrandt, Stephan and Neumann, Stefan and W{\"a}tzoldt, Sebastian},
  title     = {Industrial case study on the integration of SysML and AUTOSAR with triple graph grammars},
  publisher = {Universit{\"a}tsverlag Potsdam},
  address   = {Potsdam},
  isbn      = {978-3-86956-191-2},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-60184},
  publisher      = {Universit{\"a}t Potsdam},
  pages     = {vi, 51},
  year      = {2012},
  abstract  = {During the overall development of complex engineering systems different modeling notations are employed. For example, in the domain of automotive systems system engineering models are employed quite early to capture the requirements and basic structuring of the entire system, while software engineering models are used later on to describe the concrete software architecture. Each model helps in addressing the specific design issue with appropriate notations and at a suitable level of abstraction. However, when we step forward from system design to the software design, the engineers have to ensure that all decisions captured in the system design model are correctly transferred to the software engineering model. Even worse, when changes occur later on in either model, today the consistency has to be reestablished in a cumbersome manual step. In this report, we present in an extended version of [Holger Giese, Stefan Neumann, and Stephan Hildebrandt. Model Synchronization at Work: Keeping SysML and AUTOSAR Models Consistent. In Gregor Engels, Claus Lewerentz, Wilhelm Sch{\"a}fer, Andy Sch{\"u}rr, and B. Westfechtel, editors, Graph Transformations and Model Driven Enginering - Essays Dedicated to Manfred Nagl on the Occasion of his 65th Birthday, volume 5765 of Lecture Notes in Computer Science, pages 555-579. Springer Berlin / Heidelberg, 2010.] how model synchronization and consistency rules can be applied to automate this task and ensure that the different models are kept consistent. We also introduce a general approach for model synchronization. Besides synchronization, the approach consists of tool adapters as well as consistency rules covering the overlap between the synchronized parts of a model and the rest. We present the model synchronization algorithm based on triple graph grammars in detail and further exemplify the general approach by means of a model synchronization solution between system engineering models in SysML and software engineering models in AUTOSAR which has been developed for an industrial partner. In the appendix as extension to [19] the meta-models and all TGG rules for the SysML to AUTOSAR model synchronization are documented.},
  language  = {en}
}
@phdthesis{Sawade2012,
  author    = {Sawade, Christoph},
  title     = {Active evaluation of predictive models},
  publisher = {Universit{\"a}tsverlag Potsdam},
  address   = {Potsdam},
  isbn      = {978-3-86956-255-1},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-65583},
  school      = {Universit{\"a}t Potsdam},
  pages     = {ix, 157},
  year      = {2012},
  abstract  = {The field of machine learning studies algorithms that infer predictive models from data. Predictive models are applicable for many practical tasks such as spam filtering, face and handwritten digit recognition, and personalized product recommendation. In general, they are used to predict a target label for a given data instance. In order to make an informed decision about the deployment of a predictive model, it is crucial to know the model's approximate performance. To evaluate performance, a set of labeled test instances is required that is drawn from the distribution the model will be exposed to at application time. In many practical scenarios, unlabeled test instances are readily available, but the process of labeling them can be a time- and cost-intensive task and may involve a human expert. This thesis addresses the problem of evaluating a given predictive model accurately with minimal labeling effort. We study an active model evaluation process that selects certain instances of the data according to an instrumental sampling distribution and queries their labels. We derive sampling distributions that minimize estimation error with respect to different performance measures such as error rate, mean squared error, and F-measures. An analysis of the distribution that governs the estimator leads to confidence intervals, which indicate how precise the error estimation is. Labeling costs may vary across different instances depending on certain characteristics of the data. For instance, documents differ in their length, comprehensibility, and technical requirements; these attributes affect the time a human labeler needs to judge relevance or to assign topics. To address this, the sampling distribution is extended to incorporate instance-specific costs. We empirically study conditions under which the active evaluation processes are more accurate than a standard estimate that draws equally many instances from the test distribution. We also address the problem of comparing the risks of two predictive models. The standard approach would be to draw instances according to the test distribution, label the selected instances, and apply statistical tests to identify significant differences. Drawing instances according to an instrumental distribution affects the power of a statistical test. We derive a sampling procedure that maximizes test power when used to select instances, and thereby minimizes the likelihood of choosing the inferior model. Furthermore, we investigate the task of comparing several alternative models; the objective of an evaluation could be to rank the models according to the risk that they incur or to identify the model with lowest risk. An experimental study shows that the active procedure leads to higher test power than the standard test in many application domains. Finally, we study the problem of evaluating the performance of ranking functions, which are used for example for web search. In practice, ranking performance is estimated by applying a given ranking model to a representative set of test queries and manually assessing the relevance of all retrieved items for each query. We apply the concepts of active evaluation and active comparison to ranking functions and derive optimal sampling distributions for the commonly used performance measures Discounted Cumulative Gain and Expected Reciprocal Rank. Experiments on web search engine data illustrate significant reductions in labeling costs.},
  language  = {en}
}
@article{Frank2012,
  author    = {Frank, Mario},
  title     = {Axiom relevance decision engine : technical report},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-72128},
  year      = {2012},
  abstract  = {This document presents an axiom selection technique for classic first order theorem proving based on the relevance of axioms for the proof of a conjecture. It is based on unifiability of predicates and does not need statistical information like symbol frequency. The scope of the technique is the reduction of the set of axioms and the increase of the amount of provable conjectures in a given time. Since the technique generates a subset of the axiom set, it can be used as a preprocessor for automated theorem proving. This technical report describes the conception, implementation and evaluation of ARDE. The selection method, which is based on a breadth-first graph search by unifiability of predicates, is a weakened form of the connection calculus and uses specialised variants or unifiability to speed up the selection. The implementation of the concept is evaluated with comparison to the results of the world championship of theorem provers of the year 2012 (CASC J6). It is shown that both the theorem prover leanCoP which uses the connection calculus and E which uses equality reasoning, can benefit from the selection approach. Also, the evaluation shows that the concept is applyable for theorem proving problems with thousands of formulae and that the selection is independent from the calculus used by the theorem prover.},
  language  = {en}
}
@book{BeckerGiese2012,
  author    = {Becker, Basil and Giese, Holger},
  title     = {Cyber-physical systems with dynamic structure : towards modeling and verification of inductive invariants},
  publisher = {Universit{\"a}tsverlag Potsdam},
  address   = {Potsdam},
  isbn      = {978-3-86956-217-9},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-62437},
  publisher      = {Universit{\"a}t Potsdam},
  pages     = {iv, 27},
  year      = {2012},
  abstract  = {Cyber-physical systems achieve sophisticated system behavior exploring the tight interconnection of physical coupling present in classical engineering systems and information technology based coupling. A particular challenging case are systems where these cyber-physical systems are formed ad hoc according to the specific local topology, the available networking capabilities, and the goals and constraints of the subsystems captured by the information processing part. In this paper we present a formalism that permits to model the sketched class of cyber-physical systems. The ad hoc formation of tightly coupled subsystems of arbitrary size are specified using a UML-based graph transformation system approach. Differential equations are employed to define the resulting tightly coupled behavior. Together, both form hybrid graph transformation systems where the graph transformation rules define the discrete steps where the topology or modes may change, while the differential equations capture the continuous behavior in between such discrete changes. In addition, we demonstrate that automated analysis techniques known for timed graph transformation systems for inductive invariants can be extended to also cover the hybrid case for an expressive case of hybrid models where the formed tightly coupled subsystems are restricted to smaller local networks.},
  language  = {en}
}
@book{AlbrechtNaumann2012,
  author    = {Albrecht, Alexander and Naumann, Felix},
  title     = {Understanding cryptic schemata in large extract-transform-load systems},
  publisher = {Universit{\"a}tsverlag Potsdam},
  address   = {Potsdam},
  isbn      = {978-3-86956-201-8},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-61257},
  publisher      = {Universit{\"a}t Potsdam},
  pages     = {19},
  year      = {2012},
  abstract  = {Extract-Transform-Load (ETL) tools are used for the creation, maintenance, and evolution of data warehouses, data marts, and operational data stores. ETL workflows populate those systems with data from various data sources by specifying and executing a DAG of transformations. Over time, hundreds of individual workflows evolve as new sources and new requirements are integrated into the system. The maintenance and evolution of large-scale ETL systems requires much time and manual effort. A key problem is to understand the meaning of unfamiliar attribute labels in source and target databases and ETL transformations. Hard-to-understand attribute labels lead to frustration and time spent to develop and understand ETL workflows. We present a schema decryption technique to support ETL developers in understanding cryptic schemata of sources, targets, and ETL transformations. For a given ETL system, our recommender-like approach leverages the large number of mapped attribute labels in existing ETL workflows to produce good and meaningful decryptions. In this way we are able to decrypt attribute labels consisting of a number of unfamiliar few-letter abbreviations, such as UNP_PEN_INT, which we can decrypt to UNPAID_PENALTY_INTEREST. We evaluate our schema decryption approach on three real-world repositories of ETL workflows and show that our approach is able to suggest high-quality decryptions for cryptic attribute labels in a given schema.},
  language  = {en}
}
@book{BauckmannAbedjanLeseretal.2012,
  author    = {Bauckmann, Jana and Abedjan, Ziawasch and Leser, Ulf and M{\"u}ller, Heiko and Naumann, Felix},
  title     = {Covering or complete? : Discovering conditional inclusion dependencies},
  publisher = {Universit{\"a}tsverlag Potsdam},
  address   = {Potsdam},
  isbn      = {978-3-86956-212-4},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-62089},
  publisher      = {Universit{\"a}t Potsdam},
  pages     = {34},
  year      = {2012},
  abstract  = {Data dependencies, or integrity constraints, are used to improve the quality of a database schema, to optimize queries, and to ensure consistency in a database. In the last years conditional dependencies have been introduced to analyze and improve data quality. In short, a conditional dependency is a dependency with a limited scope defined by conditions over one or more attributes. Only the matching part of the instance must adhere to the dependency. In this paper we focus on conditional inclusion dependencies (CINDs). We generalize the definition of CINDs, distinguishing covering and completeness conditions. We present a new use case for such CINDs showing their value for solving complex data quality tasks. Further, we define quality measures for conditions inspired by precision and recall. We propose efficient algorithms that identify covering and completeness conditions conforming to given quality thresholds. Our algorithms choose not only the condition values but also the condition attributes automatically. Finally, we show that our approach efficiently provides meaningful and helpful results for our use case.},
  language  = {en}
}