TY - JOUR AU - Bräuer, Sebastian AU - Plenter, Florian AU - Klör, Benjamin AU - Monhof, Markus AU - Beverungen, Daniel AU - Becker, Jörg ID - 12929 JF - Business Research SN - 2198-3402 TI - Transactions for trading used electric vehicle batteries: theoretical underpinning and information systems design principles ER - TY - JOUR AU - Köthemann, Ronja AU - Weber, Nils AU - Lindner, Jörg K N AU - Meier, Cedrik ID - 12930 IS - 9 JF - Semiconductor Science and Technology SN - 0268-1242 TI - High-precision determination of silicon nanocrystals: optical spectroscopy versus electron microscopy VL - 34 ER - TY - CONF AU - Ajjour, Yamen AU - Alshomary, Milad AU - Wachsmuth, Henning AU - Stein, Benno ID - 12931 T2 - Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and 9th International Joint Conference on Natural Language Processing TI - Modeling Frames in Argumentation ER - TY - CONF AU - Götte, Thorsten AU - Hinnenthal, Kristian AU - Scheideler, Christian ID - 12944 T2 - Structural Information and Communication Complexity TI - Faster Construction of Overlay Networks ER - TY - CONF AU - Bäumer, Frederik Simon AU - Buff, Bianca ID - 12946 SN - 9789897583773 T2 - Proceedings of the 8th International Conference on Data Science, Technology and Applications TI - How to Boost Customer Relationship Management via Web Mining Benefiting from the Glass Customer’s Openness ER - TY - JOUR AB - Modern Boolean satisfiability solvers can emit proofs of unsatisfiability. There is substantial interest in being able to verify such proofs and also in using them for further computations. In this paper, we present an FPGA accelerator for checking resolution proofs, a popular proof format. Our accelerator exploits parallelism at the low level by implementing the basic resolution step in hardware, and at the high level by instantiating a number of parallel modules for proof checking. Since proof checking involves highly irregular memory accesses, we employ Hybrid Memory Cube technology for accelerator memory. The results show that while the accelerator is scalable and achieves speedups for all benchmark proofs, performance improvements are currently limited by the overhead of transitioning the proof into the accelerator memory. AU - Hansmeier, Tim AU - Platzner, Marco AU - Pantho, Md Jubaer Hossain AU - Andrews, David ID - 12967 IS - 11 JF - Journal of Signal Processing Systems SN - 1939-8018 TI - An Accelerator for Resolution Proof Checking based on FPGA and Hybrid Memory Cube Technology VL - 91 ER - TY - THES AU - Heindorf, Stefan ID - 15333 TI - Vandalism Detection in Crowdsourced Knowledge Bases ER - TY - GEN AB - n this paper, I review the empirical literature in the intersection of banks and corporate income taxation that emerged over the last two decades. To structure the included studies, I use a stakeholder approach and outline how corporate income taxation plays into the relation of banks and their four main stakeholders: bank regulators, customers, investors and tax authorities. My contribution to the literature is threefold: First, I contribute by providing, to the best of my knowledge, a first comprehensive review on this topic. Second, I point to areas for future research. Third, I deduce policy implications from the studies under review. In sum, the studies show that taxes distort banks’ pricing decisions, the relative attractiveness of debt and equity financing, the decision to report on or off the balance sheet and banks’ investment allocations. Empirical insights on how tax rules affect banks’ decision-making are helpful for policymakers to tailor suitable and sustainable tax legislation directed at banks. AU - Gawehn, Vanessa ID - 15367 KW - corporate income taxes KW - banks KW - stakeholder approach KW - decision-making process TI - Banks and Corporate Income Taxation: A Review ER - TY - CONF AB - Service Level Agreements are essential tools enabling clients and telco operators to specify required quality of service. The 5GTANGO NFV platform enables SLAs through policies and custom service lifecycle management components. This allows the operator to trigger certain lifecycle management events for a service, and the network service developer to define how to execute such events (e.g., how to scale). In this demo we will demonstrate this unique 5GTANGO concept using an elastic proxy service supported by a high availability SLA enforced through a range of traffic regimes. AU - Soenen, Thomas AU - Vicens, Felipe AU - Bonnet, José AU - Parada, Carlos AU - Kapassa, Evgenia AU - Touloupou, Marious AU - Fotopulou, Eleni AU - Zafeiropoulos, Anastasios AU - Pol, Ana AU - Kolometsos, Stavros AU - Xilouris, George AU - Alemany, Pol AU - Vilalta, Ricard AU - Trakadas, Panos AU - Karkazis, Panos AU - Peuster, Manuel AU - Tavernier, Wouter ID - 15368 KW - 5G mobile communication KW - contracts KW - quality of service KW - telecommunication traffic KW - virtualisation KW - custom service lifecycle management components KW - lifecycle management events KW - network service developer KW - elastic proxy service KW - SLA-controlled proxy service KW - customisable MANO KW - operator policies KW - Service Level Agreements KW - unique 5G TANGO concept KW - 5G TANGO NFV platform KW - quality of service KW - traffic regimes KW - high availability SLA KW - Monitoring KW - Probes KW - Portals KW - Quality of service KW - Tools KW - Servers KW - Graphical user interfaces SN - 1573-0077 T2 - 2019 IFIP/IEEE Symposium on Integrated Network and Service Management (IM) TI - SLA-controlled Proxy Service Through Customisable MANO Supporting Operator Policies ER - TY - CONF AU - Müller, Marcel AU - Behnke, Daniel AU - Bök, Patrick-Benjamin AU - Peuster, Manuel AU - Schneider, Stefan Balthasar AU - Karl, Holger ID - 15369 T2 - IEEE 17th International Conference on Industrial Informatics (IEEE-INDIN) TI - 5G as Key Technology for Networked Factories: Application of Vertical-specific Network Services for Enabling Flexible Smart Manufacturing ER - TY - CONF AB - More and more management and orchestration approaches for (software) networks are based on machine learning paradigms and solutions. These approaches depend not only on their program code to operate properly, but also require enough input data to train their internal models. However, such training data is barely available for the software networking domain and most presented solutions rely on their own, sometimes not even published, data sets. This makes it hard, or even infeasible, to reproduce and compare many of the existing solutions. As a result, it ultimately slows down the adoption of machine learning approaches in softwarised networks. To this end, we introduce the "softwarised network data zoo" (SNDZoo), an open collection of software networking data sets aiming to streamline and ease machine learning research in the software networking domain. We present a general methodology to collect, archive, and publish those data sets for use by other researches and, as an example, eight initial data sets, focusing on the performance of virtualised network functions. AU - Peuster, Manuel AU - Schneider, Stefan Balthasar AU - Karl, Holger ID - 15371 T2 - IEEE/IFIP 15th International Conference on Network and Service Management (CNSM) TI - The Softwarised Network Data Zoo ER - TY - CONF AU - Nuriddinov, Askhat AU - Tavernier, Wouter AU - Colle, Didier AU - Pickavet, Mario AU - Peuster, Manuel AU - Schneider, Stefan Balthasar ID - 15372 T2 - IEEE Conference on Network Function Virtualization and Software Defined Networks (NFV-SDN) TI - Reproducible Functional Tests for Multi-scale Network Services ER - TY - CONF AB - Offloading packet processing tasks to programmable switches and/or to programmable network interfaces, so called “SmartNICs”, is one of the key concepts to prepare softwarized networks for the high traffic demands of the future. However, implementing network functions that make use of those offload- ing technologies is still challenging and usually requires the availability of specialized hardware. It becomes even harder if heterogeneous services, making use of different offloading and network virtualization technologies, should be developed. In this paper, we introduce FOP4 (Function Offloading Pro- totyping with P4), a novel prototyping platform that allows to prototype heterogeneous software network scenarios, including container-based, P4-switch-based, and SmartNIC-based network functions. The presented work substantially extends our existing Containernet platform with the means to prototype offloading scenarios. Besides presenting the platform’s system design, we evaluate its scalability and show that it can run scenarios with more than 64 P4 switch or SmartNIC nodes on a single laptop. Finally, we presented a case study in which we use the presented platform to prototype an extended in-band network telemetry use case. AU - Moro, Daniele AU - Peuster, Manuel AU - Karl, Holger AU - Capone, Antonio ID - 15373 T2 - IEEE Conference on Network Function Virtualization and Software Defined Networks (NFV-SDN) TI - FOP4: Function Offloading Prototyping in Heterogeneous and Programmable Network Scenarios ER - TY - CONF AB - Emulation platforms supporting Virtual Network Functions (VNFs) allow developers to rapidly prototype network services. None of the available platforms, however, supports experimenting with programmable data planes to enable VNF offloading. In this demonstration, we show FOP4, a flexible platform that provides support for Docker-based VNFs, and VNF offloading, by means of P4-enabled switches. The platform provides interfaces to program the P4 devices and to deploy network functions. We demonstrate FOP4 with two complex example scenarios, demonstrating how developers can exploit data plane programmability to implement network functions. AU - Moro, Daniele AU - Peuster, Manuel AU - Karl, Holger AU - Capone, Antonio ID - 15374 T2 - IEEE Conference on Network Function Virtualization and Software Defined Networks (NFV-SDN) TI - Demonstrating FOP4: A Flexible Platform to Prototype NFV Offloading Scenarios ER - TY - CONF AU - Müller, Marcel AU - Behnke, Daniel AU - Bök, Patrick-Benjamin AU - Schneider, Stefan Balthasar AU - Peuster, Manuel AU - Karl, Holger ID - 15375 T2 - IEEE Conference on Network Function Virtualization and Software Defined Networks (NFV-SDN) TI - Putting NFV into Reality: Physical Smart Manufacturing Testbed ER - TY - CONF AU - Behnke, Daniel AU - Müller, Marcel AU - Bök, Patrick-Benjamin AU - Schneider, Stefan Balthasar AU - Peuster, Manuel AU - Karl, Holger ID - 15376 T2 - IEEE Conference on Network Function Virtualization and Software Defined Networks (NFV-SDN) TI - NFV-driven intrusion detection for smart manufacturing ER - TY - CONF AU - Berendes, Carsten Ingo ID - 15391 SN - 1865-1348 T2 - Business Information Systems Workshops TI - Towards Analyzing High Street Customer Trajectories - A Data-Driven Case Study ER - TY - JOUR AU - Jochen Baumeister ID - 15416 JF - Quick And Easy Journal Title TI - New Quick And Easy Publication - Will be edited by LibreCat team ER - TY - JOUR AU - An, YW AU - Lobacz, AD AU - Baumeister, Jochen AU - Rose, WC AU - Higginson, JS AU - Rosen, J AU - Swanik, CB ID - 15420 JF - J Athl Train SN - 1062-6050 TI - Negative Emotion and Joint-Stiffness Regulation Strategies After Anterior Cruciate Ligament Injury. ER - TY - JOUR AU - Vogt, Sarah AU - Skjæret-Maroni, N AU - Neuhaus, D AU - Baumeister, Jochen ID - 15421 JF - Int J Med Inform SN - 1386-5056 TI - Virtual reality interventions for balance prevention and rehabilitation after musculoskeletal lower limb impairments in young up to middle-aged adults: A comprehensive review on used technology, balance outcome measures and observed effects. VL - 126 ER - TY - CONF AU - Ho, Nam AU - Kaufmann, Paul AU - Platzner, Marco ID - 15422 T2 - World Congress on Nature and Biologically Inspired Computing (NaBIC) TI - Optimization of Application-specific L1 Cache Translation Functions of the LEON3 Processor ER - TY - GEN AU - Lehmann, Tim AU - Büchel, Daniel AU - Cockcroft, John AU - Louw, Quinette AU - Baumeister, Jochen ID - 15423 TI - Phase Coupling of Bilateral Motor Areas Decreases from Bipedal to Single Leg Stance ER - TY - JOUR AU - Gokeler, Alli AU - Neuhaus, D AU - Benjaminse, A AU - Grooms, DR AU - Baumeister, Jochen ID - 15425 IS - 6 JF - Sports Med SN - 0112-1642 TI - Principles of Motor Learning to Support Neuroplasticity After ACL Injury: Implications for Optimizing Performance and Reducing Risk of Second ACL Injury. VL - 49 ER - TY - JOUR AU - An, YW AU - DiTrani Lobacz, A AU - Lehmann, T AU - Baumeister, Jochen AU - Rose, WC AU - Higginson, JS AU - Rosen, J AU - Swanik, CB ID - 15426 IS - 2 JF - Scand J Med Sci Sports SN - 0905-7188 TI - Neuroplastic changes in anterior cruciate ligament reconstruction patients from neuromechanical decoupling. VL - 29 ER - TY - JOUR AU - Dingenen, B AU - Truijen, J AU - Bellemans, J AU - Gokeler, A ID - 15429 IS - 5 JF - Knee SN - 0968-0160 TI - Test-retest reliability and discriminative ability of forward, medial and rotational single-leg hop tests. VL - 26 ER - TY - THES AU - Yigitbas, Enes ID - 15430 TI - Model-Driven Engineering of Self-Adaptive User Interfaces ER - TY - CONF AB - Die Achse als einzige Verbindung zwischen Fahrzeugaufbau und Rad hat die Hauptaufgabe das Rad auf der Straße zuführen. Kinematisch betrachtet übernimmt die Radaufhängung, als Teil der Achse, die Funktion, zwischen Rad und Fahrzeugaufbaueinen vertikalen Freiheitsgrad zur Aufnahme von Fahrbahnunebenheiten zu realisieren. Die aus der RadhubundElastokinematik resultierenden Radstellungsänderungen bestimmen dabei maßgeblich die Fahrdynamik. Zur objektivenBeurteilung von Radaufhängungen ist eine genaue Charakterisierung der Radhub- und Elastokinematik erforderlich.Daher wurde zur Identifikation der kinematischen, elastokinematischen und dynamischen Radaufhängungseigenschaftenam Lehrstuhl für Dynamik und Mechatronik der Universität Paderborn ein Halbachsprüfstand entwickelt. Bei der Auslegungwurde Wert auf ein möglichst breites Einsatzspektrum gelegt. Es können verschiedene Typen von Einzelradaufhängungenin Serien- oder Prototypenkonfiguration am Prüfstand analysiert werden. Er ermöglicht eine Identifikation derdynamischen Radstellungsänderungen unter verschiedenen fahrdynamischen Lastfällen und regellosen Anregungen. AU - Schütte, Jan AU - Sextro, Walter AU - Kohl, Sergej ID - 15475 T2 - Fachtagung Mechatronik 2019 TI - Halbachsprüfstand zur kinematischen, elastokinematischen und dynamischen Charakterisierung von Radaufhängungen ER - TY - CONF AB - Stratix 10 FPGA cards have a good potential for the acceleration of HPC workloads since the Stratix 10 product line introduces devices with a large number of DSP and memory blocks. The high level synthesis of OpenCL codes can play a fundamental role for FPGAs in HPC, because it allows to implement different designs with lower development effort compared to hand optimized HDL. However, Stratix 10 cards are still hard to fully exploit using the Intel FPGA SDK for OpenCL. The implementation of designs with thousands of concurrent arithmetic operations often suffers from place and route problems that limit the maximum frequency or entirely prevent a successful synthesis. In order to overcome these issues for the implementation of the matrix multiplication, we formulate Cannon's matrix multiplication algorithm with regard to its efficient synthesis within the FPGA logic. We obtain a two-level block algorithm, where the lower level sub-matrices are multiplied using our Cannon's algorithm implementation. Following this design approach with multiple compute units, we are able to get maximum frequencies close to and above 300 MHz with high utilization of DSP and memory blocks. This allows for performance results above 1 TeraFLOPS. AU - Gorlani, Paolo AU - Kenter, Tobias AU - Plessl, Christian ID - 15478 T2 - Proceedings of the International Conference on Field-Programmable Technology (FPT) TI - OpenCL Implementation of Cannon's Matrix Multiplication Algorithm on Intel Stratix 10 FPGAs ER - TY - CONF AB - The continuous refinement of sensor technologies enables the manufacturing industry to capture increasing amounts of data during the production process. As processes take time to complete, sensors register large amounts of time-series-like data for each product. In order to make this data usable, a feature extraction is mandatory. In this work, we discuss and evaluate different network architectures, input pre-processing and cost functions regarding, among other aspects, their suitability for time series of different lengths. AU - Thiel, Christian AU - Steidl, Carolin AU - Henning, Bernd ID - 15488 KW - Dynamic Time Warping KW - Feature Extraction KW - Masking KW - Neural Networks SN - 978-3-9819376-0-2 T2 - 20. GMA/ITG-Fachtagung. Sensoren und Messsysteme 2019 TI - P2.9 Comparison of deep feature extraction techniques for varying-length time series from an industrial piercing press ER - TY - JOUR AB - ZusammenfassungTraining mit ergänzendem verzögertem Feedback zeigt sich zum Erlernen einer postoperativen Teilbelastung beim Gehen an Unterarmgehstützen effektiv. Insbesondere die Verwendung von Bandbreitenfeedback hat sich bei anderen Bewegungsaufgaben im Hinblick auf die Ausführungspräzision, -konstanz und -automatizität als vorteilhaft erwiesen. In einer Studie mit 31 jungen gesunden Erwachsenen untersuchten wir diese Parameter im Rahmen eines Feedbacktrainings während einer Teilbelastungsaufgabe und verglichen dabei eine Bandbreitenmethode mit einem 100 %-Feedback und einer Kontrollbedingung.Die in anderen Studien aufgezeigten Vorteile des Bandbreitenfeedbacks konnten in diesem Kontext für keinen der 3 Zielparameter gezeigt werden. Darüber hinaus ergeben sich aus den Daten 2 wichtige Hinweise für die rehabilitative Praxis: Zum einen konnten mit nur wenigen feedbackgestützten Übungsversuchen deutliche und zudem relativ behaltensstabile Reduktionen der Teilbelastung erreicht werden, zum anderen zeigte sich, dass das Teilbelastungsgehen einen hohen kognitiven Aufwand erfordert, der sich auch nach 2 umfangreichen Übungssitzungen nicht verringert und dazu führt, dass die Einhaltung der Teilbelastung bei Aufmerksamkeitsablenkung im Alltag beeinträchtigt sein könnte. AU - Krause, Daniel AU - Paschen, Linda AU - Vogt, Sarah ID - 15492 JF - B&G Bewegungstherapie und Gesundheitssport SN - 1613-0863 TI - Zur Gestaltung von Feedbackprozeduren zum Erlernen der postoperativen Teilbelastung beim Gehen mit Unterarmgehstützen im Kontext der Bewegungsautomatisierung ER - TY - CONF AU - Purrmann, Maren AU - Wünderlich, Nancy ID - 15532 T2 - Proceedings of the 2019 Frontiers in Service Conference TI - Value Co-Creation Patterns in Multi-Actor Service Interactions: A Framework for Collaborative Consumption Platforms ER - TY - CONF AU - Izu, Cruz AU - Schulte, Carsten AU - Aggarwal, Ashish AU - I. Cutts, Quintin AU - Duran, Rodrigo AU - Gutica, Mirela AU - Heinemann, Birte AU - Kraemer, Eileen AU - Lonati, Violetta AU - Mirolo, Claudio AU - Weeda, Renske ID - 15578 T2 - Proceedings of the 2019 (ACM) Conference on Innovation and Technology in Computer Science Education, Aberdeen, Scotland, UK, July 15-17, 2019 TI - Program Comprehension: Identifying Learning Trajectories for Novice Programmers ER - TY - CONF AU - Kapp, Florian AU - Schulte, Carsten ID - 15579 T2 - Informatik für alle, 18. GI-Fachtagung Informatik und Schule, (INFOS) 2019, 16.-18. September 2019, Dortmund TI - Einsatz von Jupyter Notebooks am Beispiel eines fiktiven Kriminalfalls ER - TY - CONF AU - Müller, Kathrin AU - Schulte, Carsten AU - Magenheim, Johannes ID - 15581 T2 - Informatik für alle, 18. GI-Fachtagung Informatik und Schule, (INFOS) 2019, 16.-18. September 2019, Dortmund TI - Zur Relevanz eines Prozessbereiches Interaktion und Exploration im Kontext informatischer Bildung im Primarbereich ER - TY - CONF AU - Schmidt, Ann-Katrin AU - Schulte, Carsten ID - 15583 T2 - Informatik für alle, 18. GI-Fachtagung Informatik und Schule, (INFOS) 2019, 16.-18. September 2019, Dortmund TI - Das RetiBNE Café ER - TY - CONF AU - Augustine, John AU - Hinnenthal, Kristian AU - Kuhn, Fabian AU - Scheideler, Christian AU - Schneider, Philipp ID - 15627 SN - 9781611975994 T2 - Proceedings of the Fourteenth Annual ACM-SIAM Symposium on Discrete Algorithms TI - Shortest Paths in a Hybrid Network Model ER - TY - CONF AU - Wilke, Adrian AU - Magenheim, Johannes ID - 15720 T2 - IEEE Global Engineering Education Conference, EDUCON 2019, Dubai, United Arab Emirates, April 8-11, 2019 TI - Critical Incidents for Technology Enhanced Learning in Vocational Education and Training ER - TY - BOOK AU - Köller, Olaf AU - Magenheim, Johannes AU - Molitor, Heike AU - Pfenning, Uwe AU - Ramseger, J{\ AU - Steffensky, Mirjam AU - Wiesmüller, Christian AU - Winther, Esther AU - Wollring, Bernd ID - 15721 TI - Zieldimensionen für Multiplikatorinnen und Multiplikatoren früher MINT-Bildung ER - TY - JOUR AU - Ojha, Deepak AU - Kaliannan, Naveen Kumar AU - Kühne, Thomas D. ID - 15724 IS - 1 JF - Communications Chemistry SN - 2399-3669 TI - Time-dependent vibrational sum-frequency generation spectroscopy of the air-water interface VL - 2 ER - TY - JOUR AU - Ohto, Tatsuhiko AU - Dodia, Mayank AU - Xu, Jianhang AU - Imoto, Sho AU - Tang, Fujie AU - Zysk, Frederik AU - Kühne, Thomas D. AU - Shigeta, Yasuteru AU - Bonn, Mischa AU - Wu, Xifan AU - Nagata, Yuki ID - 15738 JF - The Journal of Physical Chemistry Letters SN - 1948-7185 TI - Accessing the Accuracy of Density Functional Theory through Structure and Dynamics of the Water–Air Interface VL - 10 ER - TY - JOUR AU - Azadi, Sam AU - Kühne, Thomas D. ID - 15739 JF - Physical Review B SN - 2469-9950 TI - Unconventional phase III of high-pressure solid hydrogen VL - 100 ER - TY - JOUR AU - Guc, Maxim AU - Kodalle, Tim AU - Kormath Madam Raghupathy, Ramya AU - Mirhosseini, Hossein AU - Kühne, Thomas D. AU - Becerril-Romero, Ignacio AU - Pérez-Rodríguez, Alejandro AU - Kaufmann, Christian A. AU - Izquierdo-Roca, Victor ID - 15740 JF - The Journal of Physical Chemistry C SN - 1932-7447 TI - Vibrational Properties of RbInSe2: Raman Scattering Spectroscopy and First-Principle Calculations VL - 124 ER - TY - JOUR AB - In many cyber–physical systems, we encounter the problem of remote state estimation of geo- graphically distributed and remote physical processes. This paper studies the scheduling of sensor transmissions to estimate the states of multiple remote, dynamic processes. Information from the different sensors has to be transmitted to a central gateway over a wireless network for monitoring purposes, where typically fewer wireless channels are available than there are processes to be monitored. For effective estimation at the gateway, the sensors need to be scheduled appropriately, i.e., at each time instant one needs to decide which sensors have network access and which ones do not. To address this scheduling problem, we formulate an associated Markov decision process (MDP). This MDP is then solved using a Deep Q-Network, a recent deep reinforcement learning algorithm that is at once scalable and model-free. We compare our scheduling algorithm to popular scheduling algorithms such as round-robin and reduced-waiting-time, among others. Our algorithm is shown to significantly outperform these algorithms for many example scenario AU - Leong, Alex S. AU - Ramaswamy, Arunselvan AU - Quevedo, Daniel E. AU - Karl, Holger AU - Shi, Ling ID - 15741 JF - Automatica SN - 0005-1098 TI - Deep reinforcement learning for wireless sensor scheduling in cyber–physical systems ER - TY - GEN AU - Otte, Oliver ID - 15746 TI - Outsourced Decryption of Attribute-based Ciphertexts ER - TY - GEN AU - Wördenweber, Nico Christof ID - 15747 TI - On the Security of the Rouselakis-Waters Ciphertext-Policy Attribute-Based Encryption Scheme in the Random Oracle Model ER - TY - CONF AB - Connectionist temporal classification (CTC) is a sequence-level loss that has been successfully applied to train recurrent neural network (RNN) models for automatic speech recognition. However, one major weakness of CTC is the conditional independence assumption that makes it difficult for the model to learn label dependencies. In this paper, we propose stimulated CTC, which uses stimulated learning to help CTC models learn label dependencies implicitly by using an auxiliary RNN to generate the appropriate stimuli. This stimuli comes in the form of an additional stimulation loss term which encourages the model to learn said label dependencies. The auxiliary network is only used during training and the inference model has the same structure as a standard CTC model. The proposed stimulated CTC model achieves about 35% relative character error rate improvements on a synthetic gesture keyboard recognition task and over 30% relative word error rate improvements on the Librispeech automatic speech recognition tasks over a baseline model trained with CTC only. AU - Heymann, Jahn AU - Khe Chai Sim, Bo Li ID - 15812 T2 - ICASSP 2019, Brighton, UK TI - Improving CTC Using Stimulated Learning for Sequence Modeling ER - TY - CONF AB - Despite the strong modeling power of neural network acoustic models, speech enhancement has been shown to deliver additional word error rate improvements if multi-channel data is available. However, there has been a longstanding debate whether enhancement should also be carried out on the ASR training data. In an extensive experimental evaluation on the acoustically very challenging CHiME-5 dinner party data we show that: (i) cleaning up the training data can lead to substantial error rate reductions, and (ii) enhancement in training is advisable as long as enhancement in test is at least as strong as in training. This approach stands in contrast and delivers larger gains than the common strategy reported in the literature to augment the training database with additional artificially degraded speech. Together with an acoustic model topology consisting of initial CNN layers followed by factorized TDNN layers we achieve with 41.6% and 43.2% WER on the DEV and EVAL test sets, respectively, a new single-system state-of-the-art result on the CHiME-5 data. This is a 8% relative improvement compared to the best word error rate published so far for a speech recognizer without system combination. AU - Zorila, Catalin AU - Boeddeker, Christoph AU - Doddipatla, Rama AU - Haeb-Umbach, Reinhold ID - 15816 T2 - ASRU 2019, Sentosa, Singapore TI - An Investigation Into the Effectiveness of Enhancement in ASR Training and Test for Chime-5 Dinner Party Transcription ER - TY - GEN AU - Leutnant, Matthias ID - 15819 TI - Experimentelle Untersuchung des SEM-Algorithmus ER - TY - CONF AB - In the field of software analysis a trade-off between scalability and accuracy always exists. In this respect, Android app analysis is no exception, in particular, analyzing large or many apps can be challenging. Dealing with many small apps is a typical challenge when facing micro-benchmarks such as DROIDBENCH or ICC-BENCH. These particular benchmarks are not only used for the evaluation of novel tools but also in continuous integration pipelines of existing mature tools to maintain and guarantee a certain quality-level. Considering this latter usage it becomes very important to be able to achieve benchmark results as fast as possible. Hence, benchmarks have to be optimized for this purpose. One approach to do so is app merging. We implemented the Android Merge Tool (AMT) following this approach and show that its novel aspects can be used to produce scaled up and accurate benchmarks. For such benchmarks Android app analysis tools do not suffer from the scalability-accuracy trade-off anymore. We show this throughout detailed experiments on DROIDBENCH employing three different analysis tools (AMANDROID, ICCTA, FLOWDROID). Benchmark execution times are largely reduced without losing benchmark accuracy. Moreover, we argue why AMT is an advantageous successor of the state-of-the-art app merging tool (APKCOMBINER) in analysis lift-up scenarios. AU - Pauck, Felix AU - Zhang, Shikun ID - 15838 KW - Program Analysis KW - Android App Analysis KW - Taint Analysis KW - App Merging KW - Benchmark SN - 9781728141367 T2 - 2019 34th IEEE/ACM International Conference on Automated Software Engineering Workshop (ASEW) TI - Android App Merging for Benchmark Speed-Up and Analysis Lift-Up ER - TY - JOUR AU - Camberg, Alan Adam AU - Tröster, Thomas AU - Bohner, F. AU - Tölle, J. ID - 15875 JF - IOP Conference Series: Materials Science and Engineering SN - 1757-899X TI - Predicting plasticity and fracture of severe pre-strained EN AW-5182 by Yld2000 yield locus and Hosford-Coulomb fracture model in sheet forming applications VL - 651 ER -