Refine
Year of publication
- 2015 (41) (remove)
Document Type
- Conference Proceeding (29)
- Article (3)
- Part of a Book (3)
- Part of Periodical (3)
- Contribution to a Periodical (2)
- Working Paper (1)
Is part of the Bibliography
- no (41)
Keywords
- Fachhochschule (2)
- Hochschule Ruhr West (2)
- Mülheim an der Ruhr (2)
- Zeitschrift (2)
- Data visualization (1)
- Framework (1)
- Image color analysis (1)
- Intercultural sharing (1)
- Knowledge sharing (1)
- Layout (1)
We present a novel approach of distributing matrix multiplications among GPU-equipped nodes in a cluster system. In this context we discuss the induced challenges and possible solutions. Additionally we state an algorithm which outperforms optimized GPU BLAS libraries for small matrices. Furthermore we provide a novel theoretical model for distributing algorithms within homogeneous computation systems with multiple hierarchies. In the context of this model we develop an algorithm which can find the optimal distribution parameters for each involved subalgorithm. We provide a detailed analysis of the algorithms space and time complexities and justify its use with a structured evaluation within a small GPU-equipped Beowulf cluster.
In the field of magnetic inductance tomography,
signal processing is a real challenge. This is due to the divergent
nature of magnetic fields. The sensitivity, i.e. the change in the
receiving signal by means of an electrically conductive sample
in a measuring volume depends strongly on the positioning
of the sample. Objects that are located near the transmitting
or receiving coils are very well locatable, where objects in
larger distance are hard to detect. In this paper an approach
is presented that improves the topology of the magnetic fields
in the ”magnetic induction tomography” (MIT) by changing
geometric constructions and current patterns of coils so far,
as to allow a sharper localization of objects within the space.
The aim is to level the distribution of the sensitivity in the
measuring volume, so that electrically conductive objects with
a larger distance between transmitting and receiving unit can
be detected with almost the same signal intensity as objects
close to the transmitting and receiving unit. The simulation tool
Comsolic is used for the geometric modeling making a finite
element analysis (FEA). The subsequent signal processing and
analysis of the simulation results are implemented in Matlabic .
Within this FEA the coil geometries and current patterns are
changed numerically, so that the minimum object size, that is
still detectable, is, compared to the known MIT, reduced and the
sensitivity of the system is improved. To validate the simulation in
Comsolic , first simulation results are compared with analytical
models and analyses.
Global software development changes the requirements in terms of soft competency and increases the complexity of social interaction by including intercultural aspects. While soft competency is often seen as crucial for the success of global software development projects, the concrete competence requirements remain unknown. Internationalization competency represents one of the first attempts to structure and describe the soft competence requirements for global software developers. Based on the diversity of tasks, competence requirements will differ among the various phases of software development. By conducting a survey on the importance of internationalization competences for the different phases of global software development, we identified differences in terms of competence importance and requirements in the phases. “Adaptability” (of one's working style) and “Cultural Awareness” were the main differences. “Cultural Awareness” distinguishes requirements engineering and software design from testing and implementation while “Adaptability” distinguishes implementation and software design from requirements engineering and testing.
This contribution demonstrates the efficient embedding of a single depth-camera into the automotive environment making mid-air gesture interaction for mobile applications viable in such a scenario. In this setting a new human-machine interface is implemented to give an idea of future improvements in automation processes in industrial applications. Our system is based on a data-driven approach by learning hand poses as well as gestures from a large database in order to apply them on mobile devices. We register any movement in a nearby driver area and crop data efficiently with the means of PCA transforming it into so-called feature vectors which present the input for our multi-layer perceptrons (MLPs). After MLP classification, the interpretation of user input is sent via WiFi to a tablet PC mounted into the car interior visualizing an infotainment system which the user is able to interact with. We demonstrate that by this setup hand gestures as well as hand poses are easily and efficiently interpretable insofar as that they become an intuitive and supplementary means of interaction for automotive HMI in mobile scenarios realizable in real-time.
We present a novel method to perform multi-class pattern classification with neural networks and test it on a challenging 3D hand gesture recognition problem. Our method consists of a standard one-against-all (OAA) classification, followed by another network layer classifying the resulting class scores, possibly augmented by the original raw input vector. This allows the network to disambiguate hard-to-separate classes as the distribution of class scores carries considerable information as well, and is in fact often used for assessing the confidence of a decision. We show that by this approach we are able to significantly boost our results, overall as well as for particular difficult cases, on the hard 10-class gesture classification task.
We present a system for efficient dynamic hand gesture recognition based on a single time-of-flight sensor. As opposed to other approaches, we simply rely on depth data to interpret user movement with the hand in mid-air. We set up a large database to train multilayer perceptrons (MLPs) which are subsequently used for classification of static hand poses that define the targeted dynamic gestures. In order to remain robust against noise and to balance the low sensor resolution, PCA is used for data cropping and highly descriptive features, obtainable in real-time, are presented. Our simple yet efficient definition of a dynamic hand gesture shows how strong results are achievable in an automotive environment allowing for interesting and sophisticated applications to be realized.
We present a novel hierarchical approach to multi-class classification which is generic in that it can be applied to different classification models (e.g., support vector machines, perceptrons), and makes no explicit assumptions about the probabilistic structure of the problem as it is usually done in multi-class classification. By adding a cascade of additional classifiers, each of which receives the previous classifier's output in addition to regular input data, the approach harnesses unused information that manifests itself in the form of, e.g., correlations between predicted classes. Using multilayer perceptrons as a classification model, we demonstrate the validity of this approach by testing it on a complex ten-class 3D gesture recognition task.
A light-weight real-time ap- plicable hand gesture recognition system for automotive applications
(2015)
We present a novel approach for improved hand-gesture recognition by a single time-of-flight(ToF) sensor in an automotive environment. As the sensor's lateral resolution is comparatively low, we employ a learning approach comprising multiple processing steps, including PCA-based cropping, the computation of robust point cloud descriptors and training of a Multilayer perceptron (MLP) on a large database of samples. A sophisticated temporal fusion technique boosts the overall robustness of recognition by taking into account data coming from previous classification steps. Overall results are very satisfactory when evaluated on a large benchmark set of ten different hand poses, especially when it comes to generalization on previously unknown persons.
We present a novel approach of distributing small-to mid-scale neural networks onto modern parallel architectures. In this context we discuss the induced challenges and possible solutions. We provide a detailed theoretical analysis with respect to space and time complexities and reinforce our computation model with evaluations which show a performance gain over state of the art approaches.