Refine
Year of publication
- 2021 (75) (remove)
Document Type
- Conference Proceeding (75) (remove)
Conference Type
- Konferenzartikel (68)
- Konferenz-Abstract (6)
- Konferenz-Poster (1)
Language
- English (75) (remove)
Is part of the Bibliography
- yes (75)
Keywords
- Generative Adversarial Network (3)
- Machine Learning (3)
- neural networks (3)
- Education (2)
- Gamification (2)
- Stability (2)
- VR (2)
- cardiac ablation (2)
- convolutional neural networks (2)
- heart rhythm model (2)
Institute
- Fakultät Elektrotechnik, Medizintechnik und Informatik (EMI) (ab 04/2019) (46)
- IMLA - Institute for Machine Learning and Analytics (16)
- Fakultät Maschinenbau und Verfahrenstechnik (M+V) (10)
- Fakultät Medien (M) (ab 22.04.2021) (10)
- Fakultät Wirtschaft (W) (9)
- INES - Institut für nachhaltige Energiesysteme (6)
- ivESK - Institut für verlässliche Embedded Systems und Kommunikationselektronik (6)
- ACI - Affective and Cognitive Institute (4)
- POIM - Peter Osypka Institute of Medical Engineering (3)
- Zentrale Einrichtungen (1)
Open Access
- Closed Access (41)
- Open Access (34)
- Bronze (3)
- Grün (2)
- Diamond (1)
- Gold (1)
Disturbances of the cardiac conduction system causing reentry mechanisms above the atrioventricular (AV) node are induced by at least one accessory pathway with different conducting properties and refractory periods. This work aims to further develop the already existing and continuously expanding Offenburg heart rhythm model to visualise the most common supraventricular reentry tachycardias to provide a better understanding of the cause of the respective reentry mechanism.
The need for the logistics sector to timely respond to the increasing requirements of a globalised and digitalised world relies greatly on the com- petences and skills of its labour force. It becomes therefore essential to reinforce the cooperation between universities and business partners in the logistics and supply chain management fields across the European region and to build a logistics knowledge cluster supported by a communication and collaboration platform to foster continuous learning, skill acquisition and experience sharing anytime anywhere. In this paper we focus on designing the conceptual and technical framework for a communication and collaboration platform with the aim to establish the communication pipelines between the partner institutions, facilitating user interactions and exchange, leading to the creation of new knowledge and innovation in the logistics field. This framework is based on the requirements of the three main stakeholders: students, lecturers and companies, and consists of four functional areas defined according to the platform opera- tional requirements. A working prototype of the platform was developed using the Moodle learning management system and its core tools to determine its applicability and possible enhancement requirements. In the next stages of the project some additional tools like a knowledge base and the integration of the partners’ learning management systems to form the logistics knowledge cluster will be implemented.
The Go programming language is an increasingly popular language but some of its features lack a formal investigation. This article explains Go's resolution mechanism for overloaded methods and its support for structural subtyping by means of translation from Featherweight Go to a simple target language. The translation employs a form of dictionary passing known from type classes in Haskell and preserves the dynamic behavior of Featherweight Go programs.
Cryptographic protection of messages requires frequent updates of the symmetric cipher key used for encryption and decryption, respectively. Protocols of legacy IT security, like TLS, SSH, or MACsec implement rekeying under the assumption that, first, application data exchange is allowed to stall occasionally and, second, dedicated control messages to orchestrate the process can be exchanged. In real-time automation applications, the first is generally prohibitive, while the second may induce problematic traffic patterns on the network. We present a novel seamless rekeying approach, which can be embedded into cyclic application data exchanges. Although, being agnostic to the underlying real-time communication system, we developed a demonstrator emulating the widespread industrial Ethernet system PROFINET IO and successfully use this rekeying mechanism.
The transition from college to university can have a variety of psychological effects on students who need to cope with daily obligations by themselves in a new setting, which can result in loneliness and social isolation. Mobile technology, specifically mental health apps (MHapps), have been seen as promising solutions to assist university students who are facing these problems, however, there is little evidence around this topic. My research investigates how a mobile app can be designed to reduce social isolation and loneliness among university students. The Noneliness app is being developed to this end; it aims to create social opportunities through a quest-based gamified system in a secure and collaborative network of local users. Initial evaluations with the target audience provided evidence on how an app should be designed for this purpose. These results are presented and how they helped me to plan the further steps to reach my research goals. The paper is presented at MobileHCI 2020 Doctoral Consortium.
The following describes a new method for estimating the parameters of an interior permanent magnet synchronous machine (IPMSM). For the estimation of the parameters the current slopes caused by the switching of the inverter are used to determine the unknowns of the system equations of the electrical machine. The angle and current dependence of the machine parameters are linearized within a PWM cycle. By considering the different switching states of the inverter, several system equations can be derived and a solution can be found within one PWM cycle. The use of test signals and filter-based approaches is avoided. The derived algorithm is explained and validated with measurements on a test bench.
Multiple Object Tracking (MOT) is a long-standing task in computer vision. Current approaches based on the tracking by detection paradigm either require some sort of domain knowledge or supervision to associate data correctly into tracks. In this work, we present a self-supervised multiple object tracking approach based on visual features and minimum cost lifted multicuts. Our method is based on straight-forward spatio-temporal cues that can be extracted from neighboring frames in an image sequences without supervision. Clustering based on these cues enables us to learn the required appearance invariances for the tracking task at hand and train an AutoEncoder to generate suitable latent representations. Thus, the resulting latent representations can serve as robust appearance cues for tracking even over large temporal distances where no reliable spatio-temporal features can be extracted. We show that, despite being trained without using the provided annotations, our model provides competitive results on the challenging MOT Benchmark for pedestrian tracking.
Most recently, the federal government in Germany published new climate goals in order reach climate neutrality by 2045. This paper demonstrates a path to a cost optimal energy supply system for the German power grid until the year 2050. With special regard to regionality, the system is based on yearly myopic optimization with the required energy system transformation measures and the associated system costs. The results point out, that energy storage systems (ESS) are fundamental for renewables integration in order to have a feasible energy transition. Moreover, the investment in storage technologies increased the usage of the solar and wind technologies. Solar energy investments were highly accompanied with the installation of short-term battery storage. Longer-term storage technologies, such as H2, were accompanied with high installations of wind technologies. The results pointed out that hydrogen investments are expected to overrule short-term batteries if their cost continues to decrease sharply. Moreover, with a strong presence of ESS in the energy system, biomass energy is expected to be completely ruled out from the energy mix. With the current emission reduction strategy and without a strong presence of large scale ESS into the system, it is unlikely that the Paris agreement 2° C target by 2050 will be achieved, let alone the 1.5° C.
Active participation of industrial enterprises in electricity markets - a generic modeling approach
(2021)
Industrial enterprises represent a significant portion of electricity consumers with the potential of providing demand-side energy flexibility from their production processes and on-site energy assets. Methods are needed for the active and profitable participation of such enterprises in the electricity markets especially with variable prices, where the energy flexibility available in their manufacturing, utility and energy systems can be assessed and quantified. This paper presents a generic model library equipped with optimal control for energy flexibility purposes. The components in the model library represent the different technical units of an industrial enterprise on material, media, and energy flow levels with their process constraints. The paper also presents a case study simulation of a steel-powder manufacturing plant using the model library. Its energy flexibility was assessed when the plant procured its electrical energy at fixed and variable electricity prices. In the simulated case study, flexibility use at dynamic prices resulted in a 6% cost reduction compared to a fixed-price scenario, with battery storage and the manufacturing system making the largest contributions to flexibility.
Additive manufacturing is a rapidly growing manufacturing process for which many new processes and materials are currently being developed. The biggest advantage is that almost any shape can be produced, while conventional manufacturing methods reach their limits. Furthermore, a lot of material is saved because the part is created in layers and only as much material is used as necessary. In contrast, in the case of machining processes, it is not uncommon for more than half of the material to be removed and disposed of. Recently, new additive manufacturing processes have been on the market that enables the manufacturing of components using the FDM process with fiber reinforcement. This opens up new possibilities for optimizing components in terms of their strength and at the same time increasing sustainability by reducing materials consumption and waste. Within the scope of this work, different types of test specimens are to be designed, manufactured and examined. The test specimens are tensile specimens, which are used both for standardized tensile tests and for examining a practical component from automotive engineering used in student project. This project is a vehicle designed to compete in the Shell Eco-marathon, one of the world’s largest energy efficiency competitions. The aim is to design a vehicle that covers a certain distance with as little fuel as possible. Accordingly, it is desirable to manufacture the components with the lowest possible weight, while still ensuring the required rigidity. To achieve this, the use of fiber-reinforced 3D-printed parts is particularly suitable due to the high rigidity. In particular, the joining technology for connecting conventionally and additively manufactured components is developed. As a result, the economic efficiency was assessed, and guidelines for the design of components and joining elements were created. In addition, it could be shown that the additive manufacturing of the component could be implemented faster and more sustainably than the previous conventional manufacturing.
In bimodal cochlear implant (CI) / hearing aid (HA) users a constant interaural time delay in the order of several milliseconds occurs due to differences in signal processing of the devices. For MED-EL CI systems in combination with different HA types, we have quantified the respective device delay mismatch (Zirn et al. 2015). In the current study, we investigate the effect of the device delay mismatch in simulated and actual bimodal listeners on sound localization accuracy.
To deal with the device delay mismatch in actual bimodal listeners we delayed the CI stimulation according to the measured HA processing delay and two other values. With all delay values highly significant improvements of the rms error in the localization task were observed compared to the test without the delay. The results help to narrow down the optimal patient-specific delay value.
IoT networks are increasingly used as entry points for cyberattacks, as often they offer low-security levels, as they may allow the control of physical systems and as they potentially also open the access to other IT networks and infrastructures. Existing intrusion detection systems (IDS) and intrusion prevention systems (IPS) mostly concentrate on legacy IT networks. Nowadays, they come with a high degree of complexity and adaptivity, including the use of artificial intelligence. It is only recently that these techniques are also applied to IoT networks. In this paper, we present a survey of machine learning and deep learning methods for intrusion detection, and we investigate how previous works used federated learning for IoT cybersecurity. For this, we present an overview of IoT protocols and potential security risks. We also report the techniques and the datasets used in the studied works, discuss the challenges of using ML, DL and FL for IoT cybersecurity and provide future insights.
An Empirical Investigation of Model-to-Model Distribution Shifts in Trained Convolutional Filters
(2021)
We present first empirical results from our ongoing investigation of distribution shifts in image data used for various computer vision tasks. Instead of analyzing the original training and test data, we propose to study shifts in the learned weights of trained models. In this work, we focus on the properties of the distributions of dominantly used 3x3 convolution filter kernels. We collected and publicly provide a data set with over half a billion filters from hundreds of trained CNNs, using a wide range of data sets, architectures, and vision tasks. Our analysis shows interesting distribution shifts (or the lack thereof) between trained filters along different axes of meta-parameters, like data type, task, architecture, or layer depth. We argue, that the observed properties are a valuable source for further investigation into a better understanding of the impact of shifts in the input data to the generalization abilities of CNN models and novel methods for more robust transfer-learning in this domain.
An Empirical Study of Explainable AI Techniques on Deep Learning Models For Time Series Tasks
(2021)
Decision explanations of machine learning black-box models are often generated by applying Explainable AI (XAI) techniques. However, many proposed XAI methods produce unverified outputs. Evaluation and verification are usually achieved with a visual interpretation by humans on individual images or text. In this preregistration, we propose an empirical study and benchmark framework to apply attribution methods for neural networks developed for images and text data on time series. We present a methodology to automatically evaluate and rank attribution techniques on time series using perturbation methods to identify reliable approaches.
A coordinated operation of decentralised micro-scale hybrid energy systems within a locally managed network such as a district or neighbourhood will play a significant role in the sector-coupled energy grid of the future. A quantitative analysis of the effects of the primary energy factors, energy conversion efficiencies, load profiles, and control strategies on their energy-economic balance can aid in identifying important trends concerning their deployment within such a network. In this contribution, an analysis of the operational data from five energy laboratories in the trinational Upper-Rhine region is evaluated and a comparison to a conventional reference system is presented. Ten exemplary data-sets representing typical operation conditions for the laboratories in different seasons and the latest information on their national energy strategies are used to evaluate the primary energy consumption, CO2 emissions, and demand-related costs. Various conclusions on the ecologic and economic feasibility of hybrid building energy systems are drawn to provide a toe-hold to the engineering community in their planning and development.
The applicability of characteristics of local magnetic fields for more precise determination of localization of subjects and/or objects in indoor environments, such as railway stations, airports, exhibition halls, showrooms, or shopping centers, is considered. An investigation has been carried out to find out whether and how low-cost magnetic field sensors and mobile robot platforms can be used to create maps that improve the accuracy and robustness of later navigation with smartphones or other devices.
The present work ties in with the problem of bicycle road assessment that is currently done using expensive special measuring vehicles. Our alternative approach for road condition assessment is to mount a sensor device on a bicycle which sends accelerometer and gyroscope data via WiFi to a classification server. There, a prediction model determines road type and condition based on the sensor data. For the classification task, we compare different machine learning methods with each other, whereby validation accuracies of 99% can be achieved with deep residual networks such as InceptionTime. The main contribution of this work with respect to comparable work is that we achieve excellent accuracies on a realistic dataset classifying road conditions into nine distinct classes that are highly relevant for practice.
Generative adversarial networks (GANs) provide state-of-the-art results in image generation. However, despite being so powerful, they still remain very challenging to train. This is in particular caused by their highly non-convex optimization space leading to a number of instabilities. Among them, mode collapse stands out as one of the most daunting ones. This undesirable event occurs when the model can only fit a few modes of the data distribution, while ignoring the majority of them. In this work, we combat mode collapse using second-order gradient information. To do so, we analyse the loss surface through its Hessian eigenvalues, and show that mode collapse is related to the convergence towards sharp minima. In particular, we observe how the eigenvalues of the are directly correlated with the occurrence of mode collapse. Finally, motivated by these findings, we design a new optimization algorithm called nudged-Adam (NuGAN) that uses spectral information to overcome mode collapse, leading to empirically more stable convergence properties.
Transformer models have recently attracted much interest from computer vision researchers and have since been successfully employed for several problems traditionally addressed with convolutional neural networks. At the same time, image synthesis using generative adversarial networks (GANs) has drastically improved over the last few years. The recently proposed TransGAN is the first GAN using only transformer-based architectures and achieves competitive results when compared to convolutional GANs. However, since transformers are data-hungry architectures, TransGAN requires data augmentation, an auxiliary super-resolution task during training, and a masking prior to guide the self-attention mechanism. In this paper, we study the combination of a transformer-based generator and convolutional discriminator and successfully remove the need of the aforementioned required design choices. We evaluate our approach by conducting a benchmark of well-known CNN discriminators, ablate the size of the transformer-based generator, and show that combining both architectural elements into a hybrid model leads to better results. Furthermore, we investigate the frequency spectrum properties of generated images and observe that our model retains the benefits of an attention based generator.