Search our Publications

Results

Viktor Losing, Barbara Hammer, Heiko Wersing, "Incremental On-line learning: A review and comparison of state of the art algorithms", Neurocomputing, vol. 275, pp. 1261-1274, 2017.

Abstract

Recently, incremental and on-line learning gained more attention especially in the context of big data and learning from data streams, conflicting with the traditional assumption of complete data availability. Even though a variety of different methods are available, it often remains unclear which of them is suit- able for a specific task and how they perform in comparison to each other. We analyze the key properties of seven popular increme...



Download Bibtex file Download PDF

Emily Nutwell, Nikola Aulig, Duane Detwiler, "Topology Optimization of a Bumper Beam System Considering a Nonlinear Design Requirement ", NAFEMS World Congress 2017, 2017.

Abstract

Methods of topology optimization are used to generate an optimal layout of material within a defined design space subject to single or multiple load cases. These methods are increasingly utilized in the field of concept design for automotive development. A vehicle’s bumper system is often subjected to loading conditions which require the structure to be efficient at absorbing energy. While an optimal bumper system maximizes energy absorbed du...



Download Bibtex file Download PDF

Mikael Kaandorp, Stefan Menzel, Sebastian Schmitt, "An Aerodynamic Perspective on Shape Deformation Methods ", 18th AIAA/ISSMO Multidisciplinary Analysis and Optimization Conference, 2017.

Abstract

Shape deformation methods are commonly used for aerodynamic design optimization of physical bodies. These methods promise a good trade-off between high design variations and a minimal set of optimization parameters. Free-form deformation and deformations based on radial basis functions are among the current state-of-the-art linear deformation methods. Recently, both methods have been analyzed on their capabilities in a simulation-based design opt...



Download Bibtex file Download PDF

Florian Damerow, Tim Puphal, Yuda Li, Julian Eggert, "Risk-based Driver Assistance for Approaching Intersections of Limited Visibility", International Conference on Vehicular Electronics and Safety 2017, pp. 178-184, 2017.

Abstract

This work addresses the general problem of risk evaluation in traffic scenarios for the case of limited observability of the scene due to a restricted sensory coverage. Here we especially concentrate on intersection scenarios, which are visually difficult to access. To distinguish the area of sight, we employ publicly available digital map data which includes, besides the general road geometry, information about buildings potentially blocking t...



Download Bibtex file Download PDF

Martin Heckmann, Dennis Orth, Heiko Wersing, Dorothea Kolossa, "Situated speech-based Driver Assistant Systems: The development of a personalized left-turning assistant", ATZ - Automobiltechnische Zeitschrift, 2017.

Abstract

We recently developed the concept of ``Assistance on Demand''. This describes an advanced driver assistance system (ADAS) which supports the driver in an inner city scenario only if they ask for assistance. A key element is the control of the ADAS via speech which allows the driver to flexibly formulate his requests for assistance while the situation develops. Our application scenario is turning left at unsignalized urban intersections. After the...



Download Bibtex file Download PDF

Mathias Franzius, Mark Dunn, Roman Dirnberger, Nils Einecke, "Embedded Robust Visual Obstacle Detection on Autonomous Lawn Mowers", IEEE Conference on Computer Vision and Pattern Recognition Workshops, 2017.

Abstract

Autonomous lawn mowers have become a solid product over the past years. Yet, they lack intelligent functions like obstacle recognition and avoidance or robust mapping and localization. One reason for these missing capabilities are the challenging situations encountered outdoors. Furthermore, the intelligent functions need to be robust enough that they do not need any expert intervention whatsoever. This makes functions based on image processing p...



Download Bibtex file Per Mail Request

Viktor Losing, Barbara Hammer, Heiko Wersing, "SAM: How to Deal with Diverse Drift Types", International Joint Conference on Artificial Intelligence, 2017.

Abstract

Data Mining in non-stationary data streams is particularly relevant in the context of Internet of Things and Big Data. Its challenges arise from fundamentally different drift types violating assumptions of data independence or stationarity. Available methods often struggle with certain forms of drift or require unavailable a priori task knowledge. We propose the Self Adjusting Memory (SAM) model for the k Nearest Neighbor (kNN) algorithm. SAM-kN...



Download Bibtex file Download PDF

Jennifer Kreger, Lydia Fischer, Stephan Hasler, Thomas Weisswange, Ute Bauer-Wersing, "A priori reliability prediction with meta-learning based on context information", International Conference on Artificial Neural Networks (ICANN), 2017.

Abstract

Machine learning systems are used in a wide variability of tasks, where reliability is very important. Often from the output of these systems their reliability cannot directly be deduced. We propose an approach to predict the reliability of a machine learning system externally. We tackle this by using an additional machine learning component we call meta-learner. This meta-learner can use the original input as well as supplementary context inf...



Download Bibtex file Download PDF

Andreas Richter, Stefan Menzel, Mario Botsch, "Preference-guided Adaptation of Deformation Representations for Evolutionary Design Optimization", IEEE Congress on Evolutionary Computation, pp. 2110-2119, 2017.

Abstract

A dynamic industrial design optimization requires high-quality optimization algorithms as well as adaptive representations to find the global solution for a given problem. For adapting the representation to changing environments or to new input we utilize the concept of evolvability, which in our interpretation consists of three criteria: variability, regularity, and improvement potential, where regularity and improvement potential characterize ...



Download Bibtex file Download PDF

Xiaofen Lu, Stefan Menzel, Ke Tang, Xin Yao, "Cooperative Co-evolution based Design Optimisation: A Concurrent Engineering Perspective", IEEE Transactions on Evolutionary Computation, 2017.

Abstract

As a well-known engineering practice, concurrent engineering (CE) considers all elements involved in a product’s life cycle from the early stages of product development, and emphasises executing all design tasks simultaneously. As a result, there exist various complex design problems in CE, which usually have many design parameters or require different disciplinary knowledge to solve them. To address these problems and enable concurrent design,...



Download Bibtex file Per Mail Request

1 2 3 4 ... 95

Search