Refine
H-BRS Bibliography
- yes (169) (remove)
Departments, institutes and facilities
- Fachbereich Informatik (64)
- Fachbereich Angewandte Naturwissenschaften (49)
- Institut für Technik, Ressourcenschonung und Energieeffizienz (TREE) (42)
- Fachbereich Ingenieurwissenschaften und Kommunikation (33)
- Fachbereich Wirtschaftswissenschaften (22)
- Institute of Visual Computing (IVC) (16)
- Institut für funktionale Gen-Analytik (IFGA) (11)
- Institut für Verbraucherinformatik (IVI) (10)
- Institut für Sicherheitsforschung (ISF) (8)
- Internationales Zentrum für Nachhaltige Entwicklung (IZNE) (7)
Document Type
- Article (73)
- Conference Object (63)
- Preprint (9)
- Doctoral Thesis (6)
- Part of a Book (5)
- Report (4)
- Book (monograph, edited volume) (3)
- Master's Thesis (3)
- Conference Proceedings (1)
- Research Data (1)
Year of publication
- 2019 (169) (remove)
Language
- English (169) (remove)
Keywords
- lignin (4)
- Navigation (3)
- work engagement (3)
- Aminoacylase (2)
- Design (2)
- Drosophila (2)
- Exergame (2)
- Extrusion blow molding (2)
- FPGA (2)
- Hyperspectral image (2)
Traffic sign recognition is an important component of many advanced driving assistance systems, and it is required for full autonomous driving. Computational performance is usually the bottleneck in using large scale neural networks for this purpose. SqueezeNet is a good candidate for efficient image classification of traffic signs, but in our experiments it does not reach high accuracy, and we believe this is due to lack of data, requiring data augmentation. Generative adversarial networks can learn the high dimensional distribution of empirical data, allowing the generation of new data points. In this paper we apply pix2pix GANs architecture to generate new traffic sign images and evaluate the use of these images in data augmentation. We were motivated to use pix2pix to translate symbolic sign images to real ones due to the mode collapse in Conditional GANs. Through our experiments we found that data augmentation using GAN can increase classification accuracy for circular traffic signs from 92.1% to 94.0%, and for triangular traffic signs from 93.8% to 95.3%, producing an overall improvement of 2%. However some traditional augmentation techniques can outperform GAN data augmentation, for example contrast variation in circular traffic signs (95.5%) and displacement on triangular traffic signs (96.7 %). Our negative results shows that while GANs can be naively used for data augmentation, they are not always the best choice, depending on the problem and variability in the data.
Change - shaping reality
(2019)
The media is considered to be the fourth pillar in a democratic country. It acts as an effective control mechanism to check the other branches of the government. But this is only consequential when the media functions in an independent and transparent fashion with trained and neutral professionals who are aware of the accountability and consequences of their work. All these factors together would further the country as a democratic institution. Traditionally, it was legacy media responsible for a one-to-many communication process. Their goal was to provide information to the citizens. But this changed with development in technology and the use of social media in daily life. The internet brought with it new media formats which are easily accessible but also unstructured. These lowered barriers of entry in the media enabled citizens to become active participants in the communication process. As a result, these citizens developed a different relationship with the already existing media wherein they were not only the receivers to information but also co-producers. Real-time information allows users to communicate with each other and in turn widely generate public opinion on internet platforms. A many-to-many communication style emerged. While on the one hand, this type of discourse could be an opportunity for citizens to exercise their fundamental freedom of speech and expression, it is on the other hand, proving to have a detrimental effect in two parts: Lack of neutrality, polarized views and pre-existing misconceptions on the part of citizens as well as algorithms and formation of echo-chambers on the part of technology. Some questions arise in this scenario about the capability of citizen journalists, the duties they should adhere to along with the enjoyment of their rights and freedoms, the risks involved in an unchecked method of communication and the effect of citizen journalism in the democratic process.
Background: Virtual reality combined with spherical treadmills is used across species for studying neural circuits underlying navigation.
New Method: We developed an optical flow-based method for tracking treadmil ball motion in real-time using a single high-resolution camera.
Results: Tracking accuracy and timing were determined using calibration data. Ball tracking was performed at 500 Hz and integrated with an open source game engine for virtual reality projection. The projection was updated at 120 Hz with a latency with respect to ball motion of 30 ± 8 ms.
Comparison: with Existing Method(s) Optical flow based tracking of treadmill motion is typically achieved using optical mice. The camera-based optical flow tracking system developed here is based on off-the-shelf components and offers control over the image acquisition and processing parameters. This results in flexibility with respect to tracking conditions – such as ball surface texture, lighting conditions, or ball size – as well as camera alignment and calibration.
Conclusions: A fast system for rotational ball motion tracking suitable for virtual reality animal behavior across different scales was developed and characterized.
Analytical pyrolysis
(2019)
Analytical pyrolysis deals with the structural identification and quantitation of pyrolysis products with the ultimate aim of establishing the identity of the original material and the mechanisms of its thermal decomposition. The pyrolytic process is carried out in a pyrolyzer interfaced with analytical instrumentation such as gas chromatography (GC), mass spectrometry (MS), gas chromatography coupled with mass spectrometry (GC/MS), or with Fourier-transform infrared spectroscopy (GC/FTIR). By measurement and identification of pyrolysis products, the molecular composition of the original sample can often be reconstructed.This book is the outcome of contributions by experts in the field of pyrolysis and includes applications of the analytical pyrolysis-GC/MS to characterize the structure of synthetic organic polymers and lignocellulosic materials as well as cellulosic pulps and isolated lignins, solid wood, waste particle board, and bio-oil. The thermal degradation of cellulose and biomass is examined by scanning electron micrography, FTIR spectroscopy, thermogravimetry (TG), differential thermal analysis, and TG/MS. The calorimetric determination of high heating values of different raw biomass, plastic waste, and biomass/plastic waste mixtures and their by-products resulting from pyrolysis is described.
Mass Spectrometry: Pyrolysis
(2019)
Estimating the impact of successful completion of vocational education on employment outcomes
(2019)
Gas Chromatography
(2019)
Gas chromatography (GC) is one of the most important types of chromatography used in analytical chemistry for separating and analyzing chemical organic compounds. Today, gas chromatography is one of the most widespread investigation methods of instrumental analysis. This technique is used in the laboratories of chemical, petrochemical, and pharmaceutical industries, in research institutes, and also in clinical, environmental, and food and beverage analysis. This book is the outcome of contributions by experts in the field of gas chromatography and includes a short history of gas chromatography, an overview of derivatization methods and sample preparation techniques, a comprehensive study on pyrazole mass spectrometric fragmentation, and a GC/MS/MS method for the determination and quantification of pesticide residues in grape samples.
Data-Driven Robot Fault Detection and Diagnosis Using Generative Models: A Modified SFDD Algorithm
(2019)
This paper presents a modification of the data-driven sensor-based fault detection and diagnosis (SFDD) algorithm for online robot monitoring. Our version of the algorithm uses a collection of generative models, in particular restricted Boltzmann machines, each of which represents the distribution of sliding window correlations between a pair of correlated measurements. We use such models in a residual generation scheme, where high residuals generate conflict sets that are then used in a subsequent diagnosis step. As a proof of concept, the framework is evaluated on a mobile logistics robot for the problem of recognising disconnected wheels, such that the evaluation demonstrates the feasibility of the framework (on the faulty data set, the models obtained 88.6% precision and 75.6% recall rates), but also shows that the monitoring results are influenced by the choice of distribution model and the model parameters as a whole.
Tell Your Robot What To Do: Evaluation of Natural Language Models for Robot Command Processing
(2019)
The use of natural language to indicate robot tasks is a convenient way to command robots. As a result, several models and approaches capable of understanding robot commands have been developed, which however complicates the choice of a suitable model for a given scenario. In this work, we present a comparative analysis and benchmarking of four natural language understanding models - Mbot, Rasa, LU4R, and ECG. We particularly evaluate the performance of the models to understand domestic service robot commands by recognizing the actions and any complementary information in them in three use cases: the RoboCup@Home General Purpose Service Robot (GPSR) category 1 contest, GPSR category 2, and hospital logistics in the context of the ROPOD project.
In Sensor-based Fault Detection and Diagnosis (SFDD) methods, spatial and temporal dependencies among the sensor signals can be modeled to detect faults in the sensors, if the defined dependencies change over time. In this work, we model Granger causal relationships between pairs of sensor data streams to detect changes in their dependencies. We compare the method on simulated signals with the Pearson correlation, and show that the method elegantly handles noise and lags in the signals and provides appreciable dependency detection. We further evaluate the method using sensor data from a mobile robot by injecting both internal and external faults during operation of the robot. The results show that the method is able to detect changes in the system when faults are injected, but is also prone to detecting false positives. This suggests that this method can be used as a weak detection of faults, but other methods, such as the use of a structural model, are required to reliably detect and diagnose faults.
For robots acting - and failing - in everyday environments, a predictable behaviour representation is important so that it can be utilised for failure analysis, recovery, and subsequent improvement. Learning from demonstration combined with dynamic motion primitives is one commonly used technique for creating models that are easy to analyse and interpret; however, mobile manipulators complicate such models since they need the ability to synchronise arm and base motions for performing purposeful tasks. In this paper, we analyse dynamic motion primitives in the context of a mobile manipulator - a Toyota Human Support Robot (HSR)- and introduce a small extension of dynamic motion primitives that makes it possible to perform whole body motion with a mobile manipulator. We then present an extensive set of experiments in which our robot was grasping various everyday objects in a domestic environment, where a sequence of object detection, pose estimation, and manipulation was required for successfully completing the task. Our experiments demonstrate the feasibility of the proposed whole body motion framework for everyday object manipulation, but also illustrate the necessity for highly adaptive manipulation strategies that make better use of a robot's perceptual capabilities.
PosturePairsDB19
(2019)
The application of Raman and infrared (IR) microspectroscopy is leading to hyperspectral data containing complementary information concerning the molecular composition of a sample. The classification of hyperspectral data from the individual spectroscopic approaches is already state-of-the-art in several fields of research. However, more complex structured samples and difficult measuring conditions might affect the accuracy of classification results negatively and could make a successful classification of the sample components challenging. This contribution presents a comprehensive comparison in supervised pixel classification of hyperspectral microscopic images, proving that a combined approach of Raman and IR microspectroscopy has a high potential to improve classification rates by a meaningful extension of the feature space. It shows that the complementary information in spatially co-registered hyperspectral images of polymer samples can be accessed using different feature extraction methods and, once fused on the feature-level, is in general more accurately classifiable in a pattern recognition task than the corresponding classification results for data derived from the individual spectroscopic approaches.