Refine
Year of publication
Document Type
- Conference Proceeding (105)
- Patent (13)
- Article (unreviewed) (8)
- Article (reviewed) (3)
- Contribution to a Periodical (3)
- Working Paper (3)
- Doctoral Thesis (2)
Conference Type
- Konferenzartikel (48)
- Konferenz-Abstract (32)
- Sonstiges (20)
- Konferenz-Poster (5)
Language
- English (137) (remove)
Is part of the Bibliography
- yes (137)
Keywords
- RoboCup (31)
- injury (9)
- Biomechanik (6)
- biomechanics (5)
- running (5)
- ACL (4)
- Machine Learning (4)
- Export (3)
- Mobile Learning (3)
- Robustness (3)
Institute
- Fakultät Elektrotechnik und Informationstechnik (E+I) (bis 03/2019) (48)
- Fakultät Maschinenbau und Verfahrenstechnik (M+V) (44)
- Fakultät Elektrotechnik, Medizintechnik und Informatik (EMI) (ab 04/2019) (31)
- IMLA - Institute for Machine Learning and Analytics (15)
- Fakultät Wirtschaft (W) (14)
- Fakultät Medien (M) (ab 22.04.2021) (6)
- IBMS - Institute for Advanced Biomechanics and Motion Studies (ab 16.11.2022) (5)
- CRT - Campus Research & Transfer (3)
- IfTI - Institute for Trade and Innovation (3)
- POIM - Peter Osypka Institute of Medical Engineering (3)
Open Access
- Bronze (137) (remove)
Virtual reality (VR) offers the opportunity to create virtual worlds that could replace real experiences. This research investigates the influence of user motivation, temporal distance and experience type on the satisfaction with the VR experience, and the degree of acceptance of a VR experience as a substitute for a real experience. The results suggest that the degree of acceptance of a VR experience as a substitute for a real experience is higher for passive VR experiences compared to active VR experiences. Furthermore, the results support the assumption that users are more satisfied with passive VR experiences.
Convolutional neural networks (CNN) define the state-of-the-art solution on many perceptual tasks. However, current CNN approaches largely remain vulnerable against adversarial perturbations of the input that have been crafted specifically to fool the system while being quasi-imperceptible to the human eye. In recent years, various approaches have been proposed to defend CNNs against such attacks, for example by model hardening or by adding explicit defence mechanisms. Thereby, a small “detector” is included in the network and trained on the binary classification task of distinguishing genuine data from data containing adversarial perturbations. In this work, we propose a simple and light-weight detector, which leverages recent findings on the relation between networks’ local intrinsic dimensionality (LID) and adversarial attacks. Based on a re-interpretation of the LID measure and several simple adaptations, we surpass the state-of-the-art on adversarial detection by a significant margin and reach almost perfect results in terms of F1-score for several networks and datasets. Sources available at: https://github.com/adverML/multiLID
TRIZ Inventive Principles
(2022)
The analysis of several thousand patents led to the conclusion that inventive engineering problems and technical contradictions in all kinds of industrial sectors could be solved by a limited number of basic Inventive Principles (Altshuller, 1984). The modern Theory of Inventive Problem Solving TRIZ (VDI 4521) contains 40 basic Inventive Principles (IP). These principles are simple to use or modify and can be easily integrated in brainstorming or daily engineer’s work. One established part of industrial practice is the composition of the specific groups of principles for solving different kinds of problems (Livotov, Petrov, 2011). Based on interdisciplinary experience of TRIZ application in the industrial companies in the last 25 years the a general order in the application of 40 Inventive Principles can be recommended for idea generation and problem solving (Livotov, Chandra, Mas'udah et al, 2019). This brochure presents an update of the 40 Inventive Principles extending the original version (Altshuller, 1984) with additional 70 sub-principles, resulting in the advanced set of 160 sub-principles, regarded as elementary inventive operators. These extended version of inventive principles finds its application in the AIDA Automatic IDEA & IP Generator https://www.tris-europe.com/eng/software/innovationssoftware.htm
The last decades have seen the evolution of industrial production into more sophisticated processes. The development of specialized, high-end machines has increased the importance of predictive maintenance of mechanical systems to produce high-quality goods and avoid machine breakdowns. Predictive maintenance has two main objectives: to classify the current status of a machine component and to predict the maintenance interval by estimating its remaining useful life (RUL). Nowadays, both objectives are covered by machine learning and deep learning approaches and require large training datasets that are often not available. One possible solution may be transfer learning, where the knowledge of a larger dataset is transferred to a smaller one. This thesis is primarily concerned with transfer learning for predictive maintenance for fault classification and RUL estimation. The first part presents the state-of-the-art machine learning techniques with a focus on techniques applicable to predictive maintenance tasks (Chapter 2). This is followed by a presentation of the machine tool background and current research that applies the previously explained machine learning techniques to predictive maintenance tasks (Chapter 3). One novelty of this thesis is that it introduces a new intermediate domain that represents data by focusing on the relevant information to allow the data to be used on different domains without losing relevant information (Chapter 4). The proposed solution is optimized for rotating elements. Therefore, the presented intermediate domain creates different layers by focusing on the fault frequencies of the rotating elements. Another novelty of this thesis is its semi and unsupervised transfer learning-based fault classification approach for different component types under different process conditions (Chapter 5). It is based on the intermediate domain utilized by a convolutional neural network (CNN). In addition, a novel unsupervised transfer learning loss function is presented based on the maximum mean discrepancy (MMD), one of the state-of-the-art algorithms. It extends the MMD by considering the intermediate domain layers; therefore, it is called layered maximum mean discrepancy (LMMD). Another novelty is an RUL estimation transfer learning approach for different component types based on the data of accelerometers with low sampling rates (Chapter 6). It applies the feature extraction concepts of the classification approach: the presented intermediate domain and the convolutional layers. The features are then used as input for a long short-term memory (LSTM) network. The transfer learning is based on fixed feature extraction, where the trained convolutional layers are taken over. Only the LSTM network has to be trained again. The intermediate domain supports this transfer learning type, as it should be similar for different component types. In addition, it enables the practical usage of accelerometers with low sampling rates during transfer learning, which is an absolute novelty. All presented novelties are validated in detailed case studies using the example of bearings (Chapter 7). In doing so, their superiority over state-of-the-art approaches is demonstrated.
Time Resolved Measurements of Soot Concentrations and Mean Particle Sizes during EUDC and ECE Cycles
(2002)
In this contribution, we present a novel 3D printed multi-material, electromagnetic vibration harvester. The harvester is based on a cantilever design and utilizes an embedded constantan wire within a matrix of polyethylene terephthalate glycol (PETG). A prototype has been manufactured with a combination of a fused filament fabrication (FFF) printer and a robot with a custom-made tool.
Sweaty has already participated several times in RoboCup soccer competitions (Adult Size). Now the work is focused coordinating the play of two robots. Moreover, we are working on stabilizing the gait by adding additional sensor information. An ongoing work is the optimization of the control strategy by balancing between impedance and position control. By minimizing the jerk, gait and overall gameplay should improve significantly.
Sweaty has already participated several times in RoboCup soccer competitions (Adult Size). Now the work is focused on stabilizing the gait. Moreover, we would like to overcome the constraints of a ZMP-algorithm that has a horizontal footplate as precondition for the simplification of the equations. In addition we would like to switch between impedance and position control with a fuzzy-like algorithm that might help to minimize jerks when Sweaty’s feet touch the ground.
Sweaty has already participated four times in RoboCup soccer competitions (Adult Size) and came second three times. While 2016 Sweaty needed a lot of luck to be finalist, 2017 Sweaty was a serious adversary in the preliminary rounds. In 2018 Sweaty showed up in the final with some lack of experience and room for improvements, but not without any chance. This paper describes the intended improvements of the humanoid adult size robot Sweaty in order to qualify for the RoboCup 2019 adult size competition.