TY - CHAP A1 - Gschossmann, Andreas A1 - Jobst, Simon A1 - Mottok, Jürgen A1 - Bierl, Rudolf T1 - A Measure of Confidence of Artificial Neural Network Classifiers T2 - ARCS Workshop 2019; 32nd International Conference on Architecture of Computing Systems, 20-21 May 2019, Copenhagen, Denmark N2 - Confidence in results of an Artificial Neural Networks (ANNs) is increased by preferring to reject data, that is not trustful, instead of risking a misclassification. For this purpose a model is proposed that is able to recognize data, which differs significantly from the training data, during inference. The proposed model observes all activations of the hidden layers, as well as input and output layers of an ANN in a grey-box view. To make ANNs more robust in safety critical applications, this model can be used to reject flawed data, that is suspected to decrease the accuracy of the model. If this information is logged during inference, it can be used to improve the model, by training it specifically with the missing information. An experiment on the MNIST dataset is conducted and its results are discussed. Y1 - 2019 UR - https://ieeexplore.ieee.org/document/8836211 SP - 153 EP - 157 PB - VDE-Verlag CY - Berlin ER - TY - CHAP A1 - Schmidhuber, Stefan A1 - Deubzer, Michael A1 - Mader, Ralph A1 - Niemetz, Michael A1 - Mottok, Jürgen T1 - Towards the Derivation of Guidelines for the Deployment of Real-Time Tasks on a Multicore Processor T2 - 4th International Symposium on Model-Based Safety and Assessment (IMBSA 2014), Munich, Germany, October 27-29, 2014, Proceedings N2 - The deployment of automotive software on a multicore processor includes the task of mapping executables to cores. Given the number of possible solutions, integrators have to solve a complex problem. Considering multiple, often conflicting goals like minimizing task response times and memory consumption, complexity further increased with the advent of multicore processors. We present a model-based approach for deriving design rules supporting integrators with statically mapping tasks to a multicore ECU. First, an evolutionary algorithm is used to sample the design space. For each sample, a model-based analysis is performed, resulting in the required fitness values according to the system metric objectives. Finally, subsets of the sample population are used to derive deployment guidelines by evaluating similarities between highly ranked solutions. This reduces the number of solutions to be considered by the integrators by orders of magnitude. In a case-study, we demonstrate the developed approach on an artificial automotive engine management system. KW - Real-time systems KW - embedded multicore systems KW - runnable partitioning KW - task-to-core mapping KW - software integration KW - design space exploration KW - evolutionary algorithm Y1 - 2014 SN - 978-3-319-12213-7 U6 - https://doi.org/10.1007/978-3-319-12214-4_12 SP - 152 EP - 165 PB - Springer CY - Munich ER - TY - CHAP A1 - Krämer, Stefan A1 - Raab, Peter A1 - Mottok, Jürgen A1 - Racek, Stanislav T1 - Comparison of Enhanced Markov Models and Discrete Event Simulation – for evaluation of probabilistic Faults in safety-critical real-time task sets T2 - Proceedings of EUROMICRO DSD 2014 - 17th Euromicro Conference on Digital System Design N2 - In this paper we present simulation and model based approaches for evaluating and validating the temporal and safety relevant properties of software intensive safety-critical real-time embedded systems. A high level reliability model of a safe task execution is described by a continuous-time Markov process, enhanced by the modeling of execution times. It is shown that the behavior - regarding real-time and safety metrics - of this theoretical model can be transferred into an abstract system timing model, which then can be analyzed by a discrete event simulation approach. The verification of the discrete event simulation by Markov models offers the possibility of a holistic approach for reliability analysis combined with schedulability analysis of complex safety-critical multicore real-time systems by the discrete event simulation. KW - Model KW - Stochastic simulation KW - reliability analysis KW - safe software processing KW - real-time operating system KW - multicore scheduling KW - discrete event simulation KW - fault injection Y1 - 2014 U6 - https://doi.org/10.1109/DSD.2014.42 SP - 591 EP - 598 ER - TY - CHAP A1 - Alfranseder, Martin A1 - Deubzer, Michael A1 - Justus, Benjamin A1 - Mottok, Jürgen A1 - Siemers, Christian T1 - An Efficient Spin-Lock Based Multi-Core Resource Sharing Protocol T2 - 33rd IEEE International Performance, Computing, and Communications Conference (IPCCC), Austin (TX), USA, 5-7 December 2014 N2 - We present in this paper a new lock-based resource sharing protocol PWLP (Preemptable Waiting Locking Protocol) for embedded multi-core processors. It is based on the busy-wait model and works with non-preemptive critical sections while task may be preempted by tasks with a higher priority when waiting for resources. Our protocol can be applied in partitioned as well as global scheduling scenarios, in which task-fix, job-fix or dynamically assigned priorities may be used. Furthermore, the PWLP permits nested requests to shared resources. Finally, we present a case study based on event-based simulations in which the FMLP (Flexible Multiprocessor Locking Protocol) and the proposed PWLP are compared. Y1 - 2014 U6 - https://doi.org/10.1109/PCCC.2014.7017090 ER - TY - CHAP A1 - Alfranseder, Martin A1 - Krapf, Tobias A1 - Mader, Ralph A1 - Niemetz, Michael A1 - Mottok, Jürgen A1 - Siemers, Christian T1 - An Efficient Partitioning Strategy for Runnables in Weakly Dependent Tasks on Embedded Multi-Core Systems T2 - Embedded real-time software and systems (ERTS² 2014), Feb 2014, Toulouse, France N2 - With multi-core controllers entering the area of automotive control ECUs, strategies for parallelizing the control- algorithms come into focus. This paper deals with a special part of automotive powertrain software, called state transitions. Since dependencies between runnables executed there are weak, the transitions provide a good basis for parallelization. We present a strategy of how to distribute efficiently the execution of runnables to different cores while taking care of inner and outer dependencies. The strategy is accompanied by two case studies demonstrating the performance of the concept. The first one is carried out to find the most efficient strategies of parallelize state transitions based on randomly generated, simulated state transitions. In the second one, the developed partitioning strategies are applied to a real software project for an automotive powertrain system. Y1 - 2014 ER - TY - CHAP A1 - Helm, C. A1 - Deubzer, Michael A1 - Mottok, Jürgen ED - Ivanov, Artem ED - Bicker, Marc ED - Patzelt, Peter T1 - Analyse der Echtzeiteigenschaften von Multicore Speicherarchitekturen in Eingebetteten Systemen mittels einer konfigurierbaren Simulationssoftware T2 - 4. Landshuter Symposium Mikrosystemtechnik : Mikrosystemtechnik als Schlüsseltechnologie der Systemintegration, Tagungsband zum Symposium 12./13. März 2014, Hochschule Landshut Y1 - 2014 SN - 978-3-9812696-5-9 SP - 109 EP - 117 CY - Landshut ER - TY - CHAP A1 - Lalo, Erjola A1 - Schmidhuber, Stefan A1 - Deubzer, Michael A1 - Mottok, Jürgen T1 - Extended Task Priority and Preemptability Optimization in Real-Time Multi-Core Embedded Systems T2 - 4th Applied Research Conference, 5th July 2014, Ingolstadt Y1 - 2014 SN - 978-3-8440-2875-1 SP - 90 EP - 95 CY - Ingolstadt ER - TY - CHAP A1 - Thiel, P. A1 - Hackl, Magnus A1 - Mottok, Jürgen T1 - Designing efficient Node.js applications – Approaching useful patterns T2 - 4th Applied Research Conference, 5th July 2014, Ingolstadt Y1 - 2014 SN - 978-3-8440-2875-1 SP - 40 EP - 46 PB - Shaker CY - Aachen ER - TY - CHAP A1 - Hackl, Magnus A1 - Thiel, Patrik A1 - Mottok, Jürgen T1 - Not Only SQL – a comparison to traditional RDBMS T2 - 4th Applied Research Conference (ARC 2014), 5th July 2014, Ingolstadt Y1 - 2014 SN - 978-3-8440-2875-1 PB - Shaker CY - Aachen ER - TY - CHAP A1 - Raab, Peter A1 - Mottok, Jürgen T1 - Modellbasierte Zuverlässigkeitsanalysen von arithmetischen Operationen in einem Prozessorsystem T2 - Proceedings of safe.tech 2014, 20. und 21. Mai 2014, München Y1 - 2014 ER -