Refine
Document Type
- Article (reviewed) (73)
- Conference Proceeding (73)
- Article (unreviewed) (23)
- Patent (18)
- Contribution to a Periodical (11)
- Doctoral Thesis (11)
- Letter to Editor (11)
- Report (9)
- Book (1)
- Part of a Book (1)
- Moving Images (1)
- Other (1)
Conference Type
- Konferenzartikel (50)
- Konferenz-Abstract (16)
- Sonstiges (5)
- Konferenz-Poster (2)
Is part of the Bibliography
- yes (233) (remove)
Keywords
- RoboCup (12)
- Machine Learning (10)
- Deep Leaning (8)
- neuroprosthetics (7)
- Götz von Berlichingen (6)
- Blockchain (5)
- Herzrhythmusmodell (5)
- E-Fahrzeug (4)
- blockchain (4)
- machine learning (4)
Institute
- Fakultät Elektrotechnik, Medizintechnik und Informatik (EMI) (ab 04/2019) (233) (remove)
Open Access
- Open Access (233) (remove)
With the expansion of IoT devices in many aspects of our life, the security of such systems has become an important challenge. Unlike conventional computer systems, any IoT security solution should consider the constraints of these systems such as computational capability, memory, connectivity, and power consumption limitations. Physical Unclonable Functions (PUFs) with their special characteristics were introduced to satisfy the security needs while respecting the mentioned constraints. They exploit the uncontrollable and reproducible variations of the underlying component for security applications such as identification, authentication, and communication security. Since IoT devices are typically low cost, it is important to reuse existing elements in their hardware (for instance sensors, ADCs, etc.) instead of adding extra costs for the PUF hardware. Micro-electromechanical system (MEMS) devices are widely used in IoT systems as sensors and actuators. In this thesis, a comprehensive study of the potential application of MEMS devices as PUF primitives is provided. MEMS PUF leverages the uncontrollable variations in the parameters of MEMS elements to derive secure keys for cryptographic applications. Experimental and simulation results show that our proposed MEMS PUFs are capable of generating enough entropy for a complex key generation, while their responses show low fluctuations in different environmental conditions.
Keeping in mind that the PUF responses are prone to change in the presence of noise and environmental variations, it is critical to derive reliable keys from the PUF and to use the maximum entropy at the same time. In the second part of this thesis, we elaborate on different key generation schemes and their advantages and drawbacks. We propose the PUF output positioning (POP) and integer linear programming (ILP) methods, which are novel methods for grouping the PUF outputs in order to maximize the extracted entropy. To implement these methods, the key enrollment and key generation algorithms are presented. The proposed methods are then evaluated by applying on the responses of the MEMS PUF, where it can be practically shown that the proposed method outperforms other existing PUF key generation methods.
The final part of this thesis is dedicated to the application of the MEMS PUF as a security solution for IoT systems. We select the mutual authentication of IoT devices and their backend system, and propose two lightweight authentication protocols based on MEMS PUFs. The presented protocols undergo a comprehensive security analysis to show their eligibility to be used in IoT systems. As the result, the output of this thesis is a lightweight security solution based on MEMS PUFs, which introduces a very low overhead on the cost of the hardware.
This paper provides a comprehensive overview of approaches to the determination of isocontours and isosurfaces from given data sets. Different algorithms are reported in the literature for this purpose, which originate from various application areas, such as computer graphics or medical imaging procedures. In all these applications, the challenge is to extract surfaces with a specific isovalue from a given characteristic, so called isosurfaces. These different application areas have given rise to solution approaches that all solve the problem of isocontouring in their own way. Based on the literature, the following four dominant methods can be identified: the marching cubes algorithms, the tessellation-based algorithms, the surface nets algorithms and the ray tracing algorithms. With regard to their application, it can be seen that the methods are mainly used in the fields of medical imaging, computer graphics and the visualization of simulation results. In our work, we provide a broad and compact overview of the common methods that are currently used in terms of isocontouring with respect to certain criteria and their individual limitations. In this context, we discuss the individual methods and identify possible future research directions in the field of isocontouring.
Ultra-low-power passive telemetry systems for industrial and biomedical applications have gained much popularity lately. The reduction of the power consumption and size of the circuits poses critical challenges in ultra-low-power circuit design. Biotelemetry applications like leakage detection in silicone breast implants require low-power-consuming small-size electronics. In this doctoral thesis, the design, simulation, and measurement of a programmable mixed-signal System-on-Chip (SoC) called General Application Passive Sensor Integrated Circuit (GAPSIC) is presented. Owing to the low power consumption, GAPSIC is capable of completely passive operation. Such a batteryless passive system has lower maintenance complexity and is also free from battery-related health hazards. With a die area of 4.92 mm² and a maximum analog power consumption of 592 µW, GAPSIC has one of the best figure-of-merits compared to similar state-of-the-art SoCs. Regarding possible applications, GAPSIC can read out and digitally transmit the signals of resistive sensors for pressure or temperature measurements. Additionally, GAPSIC can measure electrocardiogram (ECG) signals and conductivity.
The design of GAPSIC complies with the International Organization for Standardization (ISO) 15693/NFC (near field communication) 5 standard for radio frequency identification (RFID), corresponding to the frequency range of 13.56 MHz. A passive transponder developed with GAPSIC comprises of an external memory storage and very few other external components, like an antenna and sensors. The passive tag antenna and reader antenna use inductive coupling for communication and energy transfer, which enables passive operation. A passive tag developed with GAPSIC can communicate with an NFC compatible smart device or an ISO 15693 RFID reader. An external memory storage contains the programmable application-specific firmware.
As a mixed-signal SoC, GAPSIC includes both analog and digital circuitries. The analog block of GAPSIC includes a power management unit, an RFID/NFC communication unit, and a sensor readout unit. The digital block includes an integrated 32-bit microcontroller, developed by the Hochschule Offenburg ASIC design center, and digital peripherals. A 16-kilobyte random-access memory and a read-only 16-kilobyte memory constitute the GAPSIC internal memory. For the fabrication of GAPSIC, one poly, six-metal 0.18 µm CMOS process is used.
The design of GAPSIC includes two stages. In the first stage, a standalone RFID/NFC frontend chip with a power management unit, an RFID/NFC communication unit, a clock regenerator unit, and a field detector unit was designed. In the second stage, the rest of the functional blocks were integrated with the blocks of the RFID/NFC frontend chip for the final integration of GAPSIC. To reduce the power consumption, conventional low-power design techniques were applied extensively like multiple power supplies, and the operation of complementary metal-oxide-semiconductor (CMOS) transistors in the sub-threshold region of operation, as well as further innovative circuit designs.
An overvoltage protection circuit, a power rectifier, a bandgap reference circuit, and two low-dropout (LDO) voltage regulators constitute the power management unit of GAPSIC. The overvoltage protection circuit uses a novel method where three stacked transistor pairs shunt the extra voltage. In the power rectifier, four rectifier units are arranged in parallel, which is a unique approach. The four parallel rectifier units provide the optimal choice in terms of voltage drop and the area required.
The communication unit is responsible for RFID/NFC communication and incorporates demodulation and load modulation circuitry. The demodulator circuit comprises of an envelope detector, a high-pass filter, and a comparator. Following a new approach, the bandgap reference circuit itself acts as the load for the envelope detector circuit, which minimizes the circuit complexity and area. For the communication between the reader and the RFID/NFC tag, amplitude-shift keying (ASK) is used to modulate signals, where the smallest modulation index can be as low as 10%. A novel technique involving a comparator with a preset offset voltage effectively demodulates the ASK signal. With an effective die area of 0.7 mm² and power consumption of 107 µW, the standalone RFID/NFC frontend chip has the best figure-of-merits compared to the state-of-the-art frontend chips reported in the relevant literature. A passive RFID/NFC tag developed with the standalone frontend chip, as well as temperature and pressure sensors demonstrate the full passive operational capability of the frontend chip. An NFC reader device using a custom-built Android-based application software reads out the sensor data from the passive tag.
The sensor readout circuit consists of a channel selector with two differential and four single-ended inputs with a programmable-gain instrumentation amplifier. The entire sensor readout part remains deactivated when not in use. The internal memory stores the measured offset voltage of the instrumentation amplifier, where a firmware code removes the offset voltage from the measured sensor signal. A 12-bit successive approximation register (SAR) type analog-to-digital-converter (ADC) based on a charge redistribution architecture converts the measured sensor data to a digital value. The digital peripherals include a serial peripheral interface, four timers, RFID/NFC interfaces, sensor readout unit interfaces, and 12-bit SAR logic.
Two sets of studies with custom-made NFC tag antennas for biomedical applications were conducted to ascertain their compatibility with GAPSIC. The first study involved the link efficiency measurements of NFC tag antennas and an NFC reader antenna with porcine tissue. In a separate experiment, the effect of a ferrite compared to air core on the antenna-coupling factor was investigated. With the ferrite core, the coupling factor increased by four times.
Among the state-of-the-art SoCs published in recent scientific articles, GAPSIC is the only passive programmable SoC with a power management unit, an RFID/NFC communication interface, a sensor readout circuit, a 12-bit SAR ADC, and an integrated 32-bit microcontroller. This doctoral research includes the preliminary study of three passive RFID tags designed with discrete components for biomedical and industrial applications like measurements of temperature, pH, conductivity, and oxygen concentration, along with leakage detection in silicone breast implants. Besides its small size and low power consumption, GAPSIC is suitable for each of the biomedical and industrial applications mentioned above due to the integrated high-performance microcontroller, the robust programmable instrumentation amplifier, and the 12-bit analog-to-digital converter. Furthermore, the simulation and measurement data show that GAPSIC is well suited for the design of a passive tag to monitor arterial blood pressure in patients experiencing Peripheral Artery Disease (PAD), which is proposed in this doctoral thesis as an exemplary application of the developed system.
Artificial intelligence (AI), and in particular machine learning algorithms, are of increasing importance in many application areas but interpretability and understandability as well as responsibility, accountability, and fairness of the algorithms' results, all crucial for increasing the humans' trust into the systems, are still largely missing. Big industrial players, including Google, Microsoft, and Apple, have become aware of this gap and recently published their own guidelines for the use of AI in order to promote fairness, trust, interpretability, and other goals. Interactive visualization is one of the technologies that may help to increase trust in AI systems. During the seminar, we discussed the requirements for trustworthy AI systems as well as the technological possibilities provided by interactive visualizations to increase human trust in AI.
Introduction: Subjects with mild to moderate hearing loss today often receive hearing aids (HA) with open-fitting (OF). In OF, direct sound reaches the eardrums with minimal damping. Due to the required processing delay in digital HA, the amplified HA sound follows some milliseconds later. This process occurs in both ears symmetrically in bilateral HA provision and is likely to have no or minor detrimental effect on binaural hearing. However, the delayed and amplified sound are only present in one ear in cases of unilateral hearing loss provided with one HA. This processing alters interaural timing differences in the resulting ear signals.
Methods: In the present study, an experiment with normal-hearing subjects to investigate speech intelligibility in noise with direct and delayed sound was performed to mimic unilateral and bilateral HA provision with OF.
Results: The outcomes reveal that these delays affect speech reception thresholds (SRT) in the unilateral OF simulation when presenting speech and noise from different spatial directions. A significant decrease in the median SRT from –18.1 to –14.7 dB SNR is observed when typical HA processing delays are applied. On the other hand, SRT was independent of the delay between direct and delayed sound in the bilateral OF simulation.
Discussion: The significant effect emphasizes the development of rapid processing algorithms for unilateral HA provision.
This paper presents the new Deep Reinforcement Learning (DRL) library RL-X and its application to the RoboCup Soccer Simulation 3D League and classic DRL benchmarks. RL-X provides a flexible and easy-to-extend codebase with self-contained single directory algorithms. Through the fast JAX-based implementations, RL-X can reach up to 4.5x speedups compared to well-known frameworks like Stable-Baselines3.
The use of artificial intelligence continues to impact a broad variety of domains, application areas, and people. However, interpretability, understandability, responsibility, accountability, and fairness of the algorithms' results - all crucial for increasing humans' trust into the systems - are still largely missing. The purpose of this seminar is to understand how these components factor into the holistic view of trust. Further, this seminar seeks to identify design guidelines and best practices for how to build interactive visualization systems to calibrate trust.
With the rising necessity of explainable artificial intelligence (XAI), we see an increase in task-dependent XAI methods on varying abstraction levels. XAI techniques on a global level explain model behavior and on a local level explain sample predictions. We propose a visual analytics workflow to support seamless transitions between global and local explanations, focusing on attributions and counterfactuals on time series classification. In particular, we adapt local XAI techniques (attributions) that are developed for traditional datasets (images, text) to analyze time series classification, a data type that is typically less intelligible to humans. To generate a global overview, we apply local attribution methods to the data, creating explanations for the whole dataset. These explanations are projected onto two dimensions, depicting model behavior trends, strategies, and decision boundaries. To further inspect the model decision-making as well as potential data errors, a what-if analysis facilitates hypothesis generation and verification on both the global and local levels. We constantly collected and incorporated expert user feedback, as well as insights based on their domain knowledge, resulting in a tailored analysis workflow and system that tightly integrates time series transformations into explanations. Lastly, we present three use cases, verifying that our technique enables users to (1)~explore data transformations and feature relevance, (2)~identify model behavior and decision boundaries, as well as, (3)~the reason for misclassifications.
Modern CNNs are learning the weights of vast numbers of convolutional operators. In this paper, we raise the fundamental question if this is actually necessary. We show that even in the extreme case of only randomly initializing and never updating spatial filters, certain CNN architectures can be trained to surpass the accuracy of standard training. By reinterpreting the notion of pointwise ($1\times 1$) convolutions as an operator to learn linear combinations (LC) of frozen (random) spatial filters, we are able to analyze these effects and propose a generic LC convolution block that allows tuning of the linear combination rate. Empirically, we show that this approach not only allows us to reach high test accuracies on CIFAR and ImageNet but also has favorable properties regarding model robustness, generalization, sparsity, and the total number of necessary weights. Additionally, we propose a novel weight sharing mechanism, which allows sharing of a single weight tensor between all spatial convolution layers to massively reduce the number of weights.
Following the traditional paradigm of convolutional neural networks (CNNs), modern CNNs manage to keep pace with more recent, for example transformer-based, models by not only increasing model depth and width but also the kernel size. This results in large amounts of learnable model parameters that need to be handled during training. While following the convolutional paradigm with the according spatial inductive bias, we question the significance of \emph{learned} convolution filters. In fact, our findings demonstrate that many contemporary CNN architectures can achieve high test accuracies without ever updating randomly initialized (spatial) convolution filters. Instead, simple linear combinations (implemented through efficient 1×1 convolutions) suffice to effectively recombine even random filters into expressive network operators. Furthermore, these combinations of random filters can implicitly regularize the resulting operations, mitigating overfitting and enhancing overall performance and robustness. Conversely, retaining the ability to learn filter updates can impair network performance. Lastly, although we only observe relatively small gains from learning 3×3 convolutions, the learning gains increase proportionally with kernel size, owing to the non-idealities of the independent and identically distributed (\textit{i.i.d.}) nature of default initialization techniques.
We have developed a methodology for the systematic generation of a large image dataset of macerated wood references, which we used to generate image data for nine hardwood genera. This is the basis for a substantial approach to automate, for the first time, the identification of hardwood species in microscopic images of fibrous materials by deep learning. Our methodology includes a flexible pipeline for easy annotation of vessel elements. We compare the performance of different neural network architectures and hyperparameters. Our proposed method performs similarly well to human experts. In the future, this will improve controls on global wood fiber product flows to protect forests.
Fix your downsampling ASAP! Be natively more robust via Aliasing and Spectral Artifact free Pooling
(2023)
Convolutional neural networks encode images through a sequence of convolutions, normalizations and non-linearities as well as downsampling operations into potentially strong semantic embeddings. Yet, previous work showed that even slight mistakes during sampling, leading to aliasing, can be directly attributed to the networks' lack in robustness. To address such issues and facilitate simpler and faster adversarial training, [12] recently proposed FLC pooling, a method for provably alias-free downsampling - in theory. In this work, we conduct a further analysis through the lens of signal processing and find that such current pooling methods, which address aliasing in the frequency domain, are still prone to spectral leakage artifacts. Hence, we propose aliasing and spectral artifact-free pooling, short ASAP. While only introducing a few modifications to FLC pooling, networks using ASAP as downsampling method exhibit higher native robustness against common corruptions, a property that FLC pooling was missing. ASAP also increases native robustness against adversarial attacks on high and low resolution data while maintaining similar clean accuracy or even outperforming the baseline.
Motivated by the recent trend towards the usage of larger receptive fields for more context-aware neural networks in vision applications, we aim to investigate how large these receptive fields really need to be. To facilitate such study, several challenges need to be addressed, most importantly: (i) We need to provide an effective way for models to learn large filters (potentially as large as the input data) without increasing their memory consumption during training or inference, (ii) the study of filter sizes has to be decoupled from other effects such as the network width or number of learnable parameters, and (iii) the employed convolution operation should be a plug-and-play module that can replace any conventional convolution in a Convolutional Neural Network (CNN) and allow for an efficient implementation in current frameworks. To facilitate such models, we propose to learn not spatial but frequency representations of filter weights as neural implicit functions, such that even infinitely large filters can be parameterized by only a few learnable weights. The resulting neural implicit frequency CNNs are the first models to achieve results on par with the state-of-the-art on large image classification benchmarks while executing convolutions solely in the frequency domain and can be employed within any CNN architecture. They allow us to provide an extensive analysis of the learned receptive fields. Interestingly, our analysis shows that, although the proposed networks could learn very large convolution kernels, the learned filters practically translate into well-localized and relatively small convolution kernels in the spatial domain.
Assessing the robustness of deep neural networks against out-of-distribution inputs is crucial, especially in safety-critical domains like autonomous driving, but also in safety systems where malicious actors can digitally alter inputs to circumvent safety guards. However, designing effective out-of-distribution tests that encompass all possible scenarios while preserving accurate label information is a challenging task. Existing methodologies often entail a compromise between variety and constraint levels for attacks and sometimes even both. In a first step towards a more holistic robustness evaluation of image classification models, we introduce an attack method based on image solarization that is conceptually straightforward yet avoids jeopardizing the global structure of natural images independent of the intensity. Through comprehensive evaluations of multiple ImageNet models, we demonstrate the attack's capacity to degrade accuracy significantly, provided it is not integrated into the training augmentations. Interestingly, even then, no full immunity to accuracy deterioration is achieved. In other settings, the attack can often be simplified into a black-box attack with model-independent parameters. Defenses against other corruptions do not consistently extend to be effective against our specific attack.
Project website: https://github.com/paulgavrikov/adversarial_solarization
Entity Matching (EM) defines the task of learning to group objects by transferring semantic concepts from example groups (=entities) to unseen data. Despite the general availability of image data in the context of many EM-problems, most currently available EM-algorithms solely rely on (textual) meta data. In this paper, we introduce the first publicly available large-scale dataset for "visual entity matching", based on a production level use case in the retail domain. Using scanned advertisement leaflets, collected over several years from different European retailers, we provide a total of ~786k manually annotated, high resolution product images containing ~18k different individual retail products which are grouped into ~3k entities. The annotation of these product entities is based on a price comparison task, where each entity forms an equivalence class of comparable products. Following on a first baseline evaluation, we show that the proposed "visual entity matching" constitutes a novel learning problem which can not sufficiently be solved using standard image based classification and retrieval algorithms. Instead, novel approaches which allow to transfer example based visual equivalent classes to new data are needed to address the proposed problem. The aim of this paper is to provide a benchmark for such algorithms.
Information about the dataset, evaluation code and download instructions are provided under https://www.retail-786k.org/.
Die Erfindung betrifft in einem ersten Aspekt eine Vorrichtung zur transkutanen Aufbringung eines elektrischen Stimulationsreizes auf ein Ohr. Die Vorrichtung umfasst einen Schaltungsträger, mindestens zwei Elektroden sowie eine Steuerungseinheit, wobei die Steuerungseinheit dazu konfiguriert ist, anhand von Stimulationsparametern ein elektrisches Stimulationssignal an den Elektroden zu erzeugen. Dabei ist die Vorrichtung, insbesondere eine Oberfläche des Schaltungsträgers der Vorrichtung, auf eine anatomische Form eines Ohres angepasst, sodass Elektroden auf der Oberfläche des Schaltungsträgers aufgebracht sind und ausgewählte Bereiche des Ohres kontaktieren Die Vorrichtung ist dadurch kennzeichnet, dass diese weiterhin einen Sensor zur Erkennung mindestens eines physiologischen Parameter umfasst und eine Steuerungseinheit dazu konfiguriert ist, anhand des mindestens einen physiologischen Parameters die Stimulationsparameter für den Stimulationsreiz anzupassen.In einem weiteren Aspekt betrifft die Erfindung ein Verfahren zur Herstellung der erfindungsgemäßen Vorrichtung.
Die Erfindung betrifft ein Verfahren zum Maximieren der von einer analogen Entropiequelle abgeleiteten Entropie, wobei das Verfahren folgende Schritte aufweist:- Bereitstellen von Eingabedaten für die analoge Entropiequelle (2);- Erzeugen von Rückgabewerten durch die analoge Entropiequelle basierend auf den Eingabedaten (3); und- Gruppieren der Rückgabewerte, wobei das Gruppieren der Rückgabewerte ein Anwenden von Versätzen auf Rückgabewerte aufweist (4).
Blockchain interoperability: the state of heterogenous blockchain-to-blockchain communication
(2023)
Blockchain technology has been increasingly adopted over the past few years since the introduction of Bitcoin, with several blockchain architectures and solutions being proposed. Most proposed solutions have been developed in isolation, without a standard protocol or cryptographic structure to work with. This has led to the problem of interoperability, where solutions running on different blockchain platforms are unable to communicate, limiting the scope of use. With blockchains being adopted in a variety of fields such as the Internet of Things, it is expected that the problem of interoperability if not addressed quickly, will stifle technology advancement. This paper presents the current state of interoperability solutions proposed for heterogenous blockchain systems. A look is taken at interoperability solutions, not only for cryptocurrencies, but also for general data-based use cases. Current open issues in heterogenous blockchain interoperability are presented. Additionally, some possible research directions are presented to enhance and to extend the existing blockchain interoperability solutions. It was discovered that though there are a number of proposed solutions in literature, few have seen real-world implementation. The lack of blockchain-specific standards has slowed the progress of interoperability. It was also realized that most of the proposed solutions are developed targeting cryptocurrency-based applications.
This paper presents an overview of EREMI, a two-year project funded under ERASMUS+ KA203, and its results. The project team’s main objective was to develop and validate an advanced interdisciplinary higher education curriculum, which includes lifelong learning components. The curriculum focuses on enhancing resource efficiency in the manufacturing industry and optimising poorly or non-digitised industrial physical infrastructure systems. The paper also discusses the results of the project, highlighting the successful achievement of its goals. EREMI effectively supports the transition to Industry 5.0 by preparing a common European pool of future experts. Through comprehensive research and collaboration, the project team has designed a curriculum that equips students with the necessary skills and knowledge to thrive in the evolving manufacturing landscape. Furthermore, the paper explores the significance of EREMI’s contributions to the field, emphasising the importance of resource efficiency and system optimisation in industrial settings. By addressing the challenges posed by under-digitised infrastructure, the project aims to drive sustainable and innovative practices in manufacturing. All five project partner organisations have been actively engaged in offering relevant educational content and framework for decentralised sustainable economic development in regional and national contexts through capacity building at a local level. A crucial element of the added value is the new channel for obtaining feedback from students. The survey results, which are outlined in the paper, offer valuable insights gathered from students, contributing to the continuous improvement of the project.
Die vorliegende Erfindung betrifft ein Verfahren zum Herstellen dreidimensionaler Bauteile, bei dem aus einem pulverförmigen Ausgangswerkstoff (1), der mit mindestens zwei Komponenten gebildet ist, wobei die Komponenten einen unterschiedlichen Dampfdruck bei gleicher Temperatur aufweisen, durch ein additives Strahlfertigungsverfahren ein Bauteil hergestellt wird. Mindestens ein Prozessparameter zum Betrieb mindestens eines zweidimensional auslenkbaren Energiestrahls wird derart eingestellt, dass sich der Dampfdruck mindestens einer der Komponenten ändert, so dass der Anteil dieses chemischen Elements oder dieser Legierung im Bauteilvolumen lokal definiert im Bauteil variiert wird.
Bei der Vorrichtung zum Verdampfen einer Flüssigkeit ist eine offenporöse Struktur (1) in einem Gehäuse (8) angeordnet, die zumindest bereichsweise als eine Heizvorrichtung ausgebildet oder mittels einer externen Heizvorrichtung oder Bereiche der offenporösen Struktur (1) auf eine Temperatur, die mindestens der Siedetemperatur der jeweiligen Flüssigkeit entspricht, erwärmbar ist. Die Flüssigkeit ist in einem außerhalb des Gehäuses (8) angeordneten Reservoir (4), mit einer Menge aufgenommen, die während des Betriebs eine kontinuierliche Verdampfung von Flüssigkeit ermöglicht. Das Reservoir ist über mindestens eine Leitung (3) für Flüssigkeit mit dem Gehäuse (8) verbunden und in der mindestens einen Leitung (3) ist/sind ein Ventil und/oder eine Pumpe oder ein Verdichter (5) angeordnet. Die Leitung (3) mündet in mindestens eine Öffnung mindestens einer Düse (2) oder mindestens eine Austrittsöffnung und die Düse (2), deren Öffnung(en) und/oder die mindestens eine Austrittsöffnung der Leitung (3) ist/sind so angeordnet, dass Flüssigkeit auf Oberflächenbereiche der offenporösen Struktur (1) auftrifft und/oder in Poren der offenporösen Struktur (1) eintritt, wenn Flüssigkeit durch die eine Leitung (3) strömt.
Method and system for extractin metal and oxygen from powdered metal oxides (EP000004170066A2)
(2023)
A method for extracting metal and oxygen from powdered metal oxides in electrolytic cell is proposed, the electrolytic cell comprising a container, a cathode, an anode and an oxygen-ion-conducting membrane, the method comprising providing a solid oxygen ion conducting electrolyte powder into a container, providing a feedstock comprising at least one metal oxide in powdered form into the container, applying an electric potential across the cathode and the anode, the cathode being in communication with the electrolyte powder and the anode being in communication with the membrane in communication with the electrolyte powder, such that at least one respective metallic species of the at least one metal oxide is reduced at the cathode and oxygen is oxidized at the anode to form molecular oxygen, wherein the potential across the cathode and the anode is greater than the dissociation potential of the at least one metal oxide and less than the dissociation potential of the solid electrolyte powder and the membrane.
The article investigates the development of a manufacturing route for highly porous titanium foams suitable for craniofacial surgery applications, particularly in cranioplasties. The study focuses on the polyurethane replication method for foam production and emphasizes reducing residual gas content, as it significantly affects the mechanical properties and suitability for approval of the foams. Various factors such as starting materials, solvent debinding, heating schedules, and hydrogen atmosphere are analyzed for their impact on residual gas content. It is shown that significant reductions in residual gas content can only be achieved by reworking each step of the process. A combination of initial solvent debinding of the PU template with dimethyl sulphoxide, reduction of suspension additives, use of coarser Gd. 1 powders, and an integrated debinding and sintering process under partial hydrogen atmosphere achieves a significant reduction in residual gas content. This way, the potential for producing titanium foams that comply with relevant standards for craniofacial implants is demonstrated.
Training deep neural networks using backpropagation is very memory and computationally intensive. This makes it difficult to run on-device learning or fine-tune neural networks on tiny, embedded devices such as low-power micro-controller units (MCUs). Sparse backpropagation algorithms try to reduce the computational load of on-device learning by training only a subset of the weights and biases. Existing approaches use a static number of weights to train. A poor choice of this so-called backpropagation ratio limits either the computational gain or can lead to severe accuracy losses. In this paper we present TinyProp, the first sparse backpropagation method that dynamically adapts the back-propagation ratio during on-device training for each training step. TinyProp induces a small calculation overhead to sort the elements of the gradient, which does not significantly impact the computational gains. TinyProp works particularly well on fine-tuning trained networks on MCUs, which is a typical use case for embedded applications. For typical datasets from three datasets MNIST, DCASE2020 and CIFAR10, we are 5 times faster compared to non-sparse training with an accuracy loss of on average 1%. On average, TinyProp is 2.9 times faster than existing, static sparse backpropagation algorithms and the accuracy loss is reduced on average by 6 % compared to a typical static setting of the back-propagation ratio.
Verfahren zum Betrieb eines batterieelektrischen Fahrzeugs mit einer elektrischen Maschine zum Antrieb des Fahrzeugs und einem Inverter (1) zum Ansteuern der elektrischen Maschine, wobei der Inverter (1) eine dreiphasige Brückenschaltung mit einer Anzahl von als Halbleiter ausgebildeten Schaltern (3) umfasst, wobei im Inverter (1) entstehende Verluste zum Heizen eines Innenraums des Fahrzeugs und/oder zum Temperieren einer Batterie und/oder zum Temperieren von Getriebeöl verwendet werden, wobei der Inverter (1) mittels Raumzeigermodulation gesteuert wird, wobei ein nicht-optimales Schaltverhalten des Inverters (1) herbeigeführt wird, indem nicht optimale Spannungs-Raumzeiger (e, eu, ev, ew, e1, e2, -e1, -e2) eingestellt werden, wobei eine Skalierung der Spannungs-Raumzeiger (e, e1, e2) über die Schaltung von Nullspannungsvektoren, die je nach zeitlichem Anteil die Spannung reduzieren, oder durch Zuhilfenahme eines jeweils gegenüberliegenden Spannungs-Raumzeigers (-e1, -e2) erfolgt, so dass eine Schaltfolge mit einer maximalen Anzahl von Schaltzyklen realisiert wird, dadurch gekennzeichnet, dass in der Mitte einer Schaltperiode (Tp) keine Symmetrie erzeugt wird.
Die Erfindung betrifft ein Verfahren zum Betrieb eines batterieelektrischen Fahrzeugs mit einer elektrischen Maschine zum Antrieb des Fahrzeugs und einem Inverter (1) zum Ansteuern der elektrischen Maschine, wobei der Inverter (1) eine dreiphasige Brückenschaltung mit einer Anzahl von als Halbleiter ausgebildeten Schaltern (3) umfasst, wobei im Inverter (1) entstehende Verluste zum Heizen eines Innenraums des Fahrzeugs und/oder zum Temperieren einer Batterie und/oder zum Temperieren von Getriebeöl verwendet werden, wobei der Inverter (1) mittels Raumzeigermodulation gesteuert wird, wobei ein nicht-optimales Schaltverhalten des Inverters (1) herbeigeführt wird, indem nicht optimale Spannungs-Raumzeiger (e, eu, ev, ew, e1, e2, -e1, -e2) eingestellt werden, wobei eine Skalierung der Spannungs-Raumzeiger (e, e1, e2) über die Schaltung von Nullspannungsvektoren, die je nach zeitlichem Anteil die Spannung reduzieren, oder durch Zuhilfenahme eines jeweils gegenüberliegenden Spannungs-Raumzeigers (-e1, - e2) erfolgt, so dass eine Schaltfolge mit einer maximalen Anzahl von Schaltzyklen realisiert wird, wobei in der Mitte einer Schaltperiode (Tp) keine Symmetrie erzeugt wird.
Die Erfindung betrifft ein Verfahren zum Betrieb eines batterieelektrischen Fahrzeugs mit einer elektrischen Maschine zum Antrieb des Fahrzeugs und einem Inverter (1) zum Ansteuern eine Stators (2) der elektrischen Maschine, wobei der Inverter (1) eine dreiphasige Brückenschaltung mit einer Anzahl von als Halbleiter ausgebildeten Schaltern (3) umfasst, wobei im Inverter (1) und/oder in der elektrischen Maschine entstehende Verluste zum Heizen eines Innenraums des Fahrzeugs und/oder zum Temperieren einer Batterie und/oder zum Temperieren von Getriebeöl verwendet werden, wobei während des Stillstands des Fahrzeugs ein von einem Permanentmagneten der elektrischen Maschine verursachter Permanentmagnetfluss durch Einstellen einer nichtdrehmomentbildenden Statorstromkomponente (Id) in Höhe des negativen Quotienten aus einem Statorfluss (&psgr;PM) und einer d-Komponente einer Statorinduktivität (Ld) so stark geschwächt wird, dass der magnetische Fluss kompensiert wird, wobei ein sehr hochfrequenter Wechselstrom als drehmomentbildende Statorstromkomponente (Iq) eingestellt wird.
Die Erfindung betrifft ein Verfahren zum Betrieb eines batterieelektrischen Fahrzeugs mit einer elektrischen Maschine zum Antrieb des Fahrzeugs und einem Inverter (1) zum Ansteuern eines Stators (2) der elektrischen Maschine, wobei der Inverter (1) eine dreiphasige Brückenschaltung mit einer Anzahl von als Halbleiter ausgebildeten Schaltern (3) umfasst, wobei im Inverter (1) und/oder in der elektrischen Maschine entstehende Verluste zum Heizen eines Innenraums des Fahrzeugs und/oder zum Temperieren einer Batterie und/oder zum Temperieren von Getriebeöl verwendet werden, wobei eine als Wechselstrom ausgebildete nichtdrehmomentbildende Statorstromkomponente (Id) in die elektrische Maschine eingeprägt wird, wobei im Stillstand eine drehmomentbildende Statorstromkomponente (Iq) zu Null geregelt wird, wobei im Fahrbetrieb ein Kompensationsstrom als drehmomentbildende Statorstromkomponente (Iq) eingeprägt wird, der ein durch die Variation der nichtdrehmomentbildenden Statorstromkomponente (Id) entstehendes Drehmoment kompensiert.
Design and Implementation of a Camera-Based Tracking System for MAV Using Deep Learning Algorithms
(2023)
In recent years, the advancement of micro-aerial vehicles has been rapid, leading to their widespread utilization across various domains due to their adaptability and efficiency. This research paper focuses on the development of a camera-based tracking system specifically designed for low-cost drones. The primary objective of this study is to build up a system capable of detecting objects and locating them on a map in real time. Detection and positioning are achieved solely through the utilization of the drone’s camera and sensors. To accomplish this goal, several deep learning algorithms are assessed and adopted because of their suitability with the system. Object detection is based upon a single-shot detector architecture chosen for maximum computation speed, and the tracking is based upon the combination of deep neural-network-based features combined with an efficient sorting strategy. Subsequently, the developed system is evaluated using diverse metrics to determine its performance for detection and tracking. To further validate the approach, the system is employed in the real world to show its possible deployment. For this, two distinct scenarios were chosen to adjust the algorithms and system setup: a search and rescue scenario with user interaction and precise geolocalization of missing objects, and a livestock control scenario, showing the capability of surveying individual members and keeping track of number and area. The results demonstrate that the system is capable of operating in real time, and the evaluation verifies that the implemented system enables precise and reliable determination of detected object positions. The ablation studies prove that object identification through small variations in phenotypes is feasible with our approach.
Due to its performance, the field of deep learning has gained a lot of attention, with neural networks succeeding in areas like Computer Vision (CV), Neural Language Processing (NLP), and Reinforcement Learning (RL). However, high accuracy comes at a computational cost as larger networks require longer training time and no longer fit onto a single GPU. To reduce training costs, researchers are looking into the dynamics of different optimizers, in order to find ways to make training more efficient. Resource requirements can be limited by reducing model size during training or designing more efficient models that improve accuracy without increasing network size.
This thesis combines eigenvalue computation and high-dimensional loss surface visualization to study different optimizers and deep neural network models. Eigenvectors of different eigenvalues are computed, and the loss landscape and optimizer trajectory are projected onto the plane spanned by those eigenvectors. A new parallelization method for the stochastic Lanczos method is introduced, resulting in faster computation and thus enabling high-resolution videos of the trajectory and secondorder information during neural network training. Additionally, the thesis presents the loss landscape between two minima along with the eigenvalue density spectrum at intermediate points for the first time.
Secondly, this thesis presents a regularization method for Generative Adversarial Networks (GANs) that uses second-order information. The gradient during training is modified by subtracting the eigenvector direction of the biggest eigenvalue, preventing the network from falling into the steepest minima and avoiding mode collapse. The thesis also shows the full eigenvalue density spectra of GANs during training.
Thirdly, this thesis introduces ProxSGD, a proximal algorithm for neural network training that guarantees convergence to a stationary point and unifies multiple popular optimizers. Proximal gradients are used to find a closed-form solution to the problem of training neural networks with smooth and non-smooth regularizations, resulting in better sparsity and more efficient optimization. Experiments show that ProxSGD can find sparser networks while reaching the same accuracy as popular optimizers.
Lastly, this thesis unifies sparsity and neural architecture search (NAS) through the framework of group sparsity. Group sparsity is achieved through ℓ2,1-regularization during training, allowing for filter and operation pruning to reduce model size with minimal sacrifice in accuracy. By grouping multiple operations together, group sparsity can be used for NAS as well. This approach is shown to be more robust while still achieving competitive accuracies compared to state-of-the-art methods
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 m argin and reach almost perfect results in terms of F1-score for several networks and datasets. Sources available at: https://github.com/adverML/multiLID
An in-depth study of U-net for seismic data conditioning: Multiple removal by moveout discrimination
(2024)
Seismic processing often involves suppressing multiples that are an inherent component of collected seismic data. Elaborate multiple prediction and subtraction schemes such as surface-related multiple removal have become standard in industry workflows. In cases of limited spatial sampling, low signal-to-noise ratio, or conservative subtraction of the predicted multiples, the processed data frequently suffer from residual multiples. To tackle these artifacts in the postmigration domain, practitioners often rely on Radon transform-based algorithms. However, such traditional approaches are both time-consuming and parameter dependent, making them relatively complex. In this work, we present a deep learning-based alternative that provides competitive results, while reducing the complexity of its usage, and, hence simplifying its applicability. Our proposed model demonstrates excellent performance when applied to complex field data, despite it being exclusively trained on synthetic data. Furthermore, extensive experiments show that our method can preserve the inherent characteristics of the data, avoiding undesired oversmoothed results, while removing the multiples from seismic offset or angle gathers. Finally, we conduct an in-depth analysis of the model, where we pinpoint the effects of the main hyperparameters on real data inference, and we probabilistically assess its performance from a Bayesian perspective. In this study, we put particular emphasis on helping the user reveal the inner workings of the neural network and attempt to unbox the model.
It is common practice to apply padding prior to convolution operations to preserve the resolution of feature-maps in Convolutional Neural Networks (CNN). While many alternatives exist, this is often achieved by adding a border of zeros around the inputs. In this work, we show that adversarial attacks often result in perturbation anomalies at the image boundaries, which are the areas where padding is used. Consequently, we aim to provide an analysis of the interplay between padding and adversarial attacks and seek an answer to the question of how different padding modes (or their absence) affect adversarial robustness in various scenarios.
In this paper, we describe a first publicly available fine-grained product recognition dataset based on leaflet images. Using advertisement leaflets, collected over several years from different European retailers, we provide a total of 41.6k manually annotated product images in 832 classes. Further, we investigate three different approaches for this fine-grained product classification task, Classification by Image, by Text, as well as by Image and Text. The approach "Classification by Text" uses the text extracted directly from the leaflet product images. We show, that the combination of image and text as input improves the classification of visual difficult to distinguish products. The final model leads to an accuracy of 96.4% with a Top-3 score of 99.2%. We release our code at https://github.com/ladwigd/Leaflet-Product-Classification.
Neural networks have a number of shortcomings. Amongst the severest ones is the sensitivity to distribution shifts which allows models to be easily fooled into wrong predictions by small perturbations to inputs that are often imperceivable to humans and do not have to carry semantic meaning. Adversarial training poses a partial solution to address this issue by training models on worst-case perturbations. Yet, recent work has also pointed out that the reasoning in neural networks is different from humans. Humans identify objects by shape, while neural nets mainly employ texture cues. Exemplarily, a model trained on photographs will likely fail to generalize to datasets containing sketches. Interestingly, it was also shown that adversarial training seems to favorably increase the shift toward shape bias. In this work, we revisit this observation and provide an extensive analysis of this effect on various architectures, the common L_2-and L_-training, and Transformer-based models. Further, we provide a possible explanation for this phenomenon from a frequency perspective.
Seismic data processing involves techniques to deal with undesired effects that occur during acquisition and pre-processing. These effects mainly comprise coherent artefacts such as multiples, non-coherent signals such as electrical noise, and loss of signal information at the receivers that leads to incomplete traces. In the past years, there has been a remarkable increase of machine-learning-based solutions that have addressed the aforementioned issues. In particular, deep-learning practitioners have usually relied on heavily fine-tuned, customized discriminative algorithms. Although, these methods can provide solid results, they seem to lack semantic understanding of the provided data. Motivated by this limitation, in this work, we employ a generative solution, as it can explicitly model complex data distributions and hence, yield to a better decision-making process. In particular, we introduce diffusion models for three seismic applications: demultiple, denoising and interpolation. To that end, we run experiments on synthetic and on real data, and we compare the diffusion performance with standardized algorithms. We believe that our pioneer study not only demonstrates the capability of diffusion models, but also opens the door to future research to integrate generative models in seismic workflows.
Neural networks tend to overfit the training distribution and perform poorly on out-ofdistribution data. A conceptually simple solution lies in adversarial training, which introduces worst-case perturbations into the training data and thus improves model generalization to some extent. However, it is only one ingredient towards generally more robust models and requires knowledge about the potential attacks or inference time data corruptions during model training. This paper focuses on the native robustness of models that can learn robust behavior directly from conventional training data without out-of-distribution examples. To this end, we study the frequencies in learned convolution filters. Clean-trained models often prioritize high-frequency information, whereas adversarial training enforces models to shift the focus to low-frequency details during training. By mimicking this behavior through frequency regularization in learned convolution weights, we achieve improved native robustness to adversarial attacks, common corruptions, and other out-of-distribution tests. Additionally, this method leads to more favorable shifts in decision-making towards low-frequency information, such as shapes, which inherently aligns more closely with human vision.
The mathematical representations of data in the Spherical Harmonic (SH) domain has recently regained increasing interest in the machine learning community. This technical report gives an in-depth introduction to the theoretical foundation and practical implementation of SH representations, summarizing works on rotation invariant and equivariant features, as well as convolutions and exact correlations of signals on spheres. In extension, these methods are then generalized from scalar SH representations to Vectorial Harmonics (VH), providing the same capabilities for 3d vector fields on spheres.
Predictive control has great potential in the home energy management domain. However, such controls need reliable predictions of the system dynamics as well as energy consumption and generation, and the actual implementation in the real system is associated with many challenges. This paper presents the implementation of predictive controls for a heat pump with thermal storage in a real single-family house with a photovoltaic rooftop system. The predictive controls make use of a novel cloud camera-based short-term solar energy prediction and an intraday prediction system that includes additional data sources. In addition, machine learning methods were used to model the dynamics of the heating system and predict loads using extensive measured data. The results of the real and simulated operation will be presented.
The increasingly stringent CO2 emissions standards require innovative solutions in the vehicle development process. One possibility to reduce CO2 emissions is the electrification of powertrains. The resulting increased complexity, as well as the increased competition and time pressure make the use of simulation software and test benches indispensable in the early development phases. This publication therefore presents a methodology for test bench coupling to enable early testing of electrified powertrains. For this purpose, an internal combustion engine test bench and an electric motor test bench are virtually interconnected. By applying and extending the Distributed Co-Simulation Protocol Standard for the presented hybrid electric powertrain use case, real-time-capable communication between the two test benches is achieved. Insights into the test bench setups, and the communication between the test benches and the protocol extension, especially with regard to temperature measurements, enable the extension to be applied to other powertrain or test bench configurations. The shown results from coupled test bench operations emphasize the applicability. The discussed experiences from the test bench coupling experiments complete the insights.
With the function RooTri(), we present a simple and robust calculation method for the approximation of the intersection points of a scalar field given as an unstructured point cloud with a plane oriented arbitrarily in space. The point cloud is approximated to a surface consisting of triangles whose edges are used for computing the intersection points. The function contourc() of Matlab is taken as a reference. Our experiments show that the function contourc() produces outliers that deviate significantly from the defined nominal value, while the quality of the results produced by the function RooTri() increases with finer resolution of the examined grid.
Featherweight Generic Go (FGG) is a minimal core calculus modeling the essential features of the programming language Go. It includes support for overloaded methods, interface types, structural subtyping, and generics. The most straightforward semantic description of the dynamic behavior of FGG programs is to resolve method calls based on runtime type information of the receiver. This article shows a different approach by defining a type-directed translation from FGG− to an untyped lambda-calculus. FGG− includes all features of FGG but type assertions. The translation of an FGG− program provides evidence for the availability of methods as additional dictionary parameters, similar to the dictionary-passing approach known from Haskell type classes. Then, method calls can be resolved by a simple lookup of the method definition in the dictionary. Every program in the image of the translation has the same dynamic semantics as its source FGG− program. The proof of this result is based on a syntactic, step-indexed logical relation. The step index ensures a well-founded definition of the relation in the presence of recursive interface types and recursive methods. Although being non-deterministic, the translation is coherent.
Team description papers of magmaOffenburg are incremental in the sense that each year we address a different topic of our team and the tools around our team. In this year’s team description paper we focus on the architecture of the software. It is a main factor for being able to keep the code maintainable even after 15 years of development. We also describe how we make sure that the code follows this architecture.
In this paper, the performance of different continuous-time and discrete-time models of the electrical subsystem of induction machines and permanent-magnet synchronous machines as well as methods based on them for decoupling the direct and
quadrature axis components of the stator current are investigated and compared. The focus here is on inverter-fed, pulse width modulated drives when operated with a relatively large product of stator frequency and sampling time, where significant
differences between the models and decoupling methods used come to light. Recommendations for a discrete-time model to be used uniformly in the future are made, as well as statements on whether feedforward or feedback decoupling structures are better suited and whether state controllers improve decoupling measures for very steep speed ramps. Simulation studies and measurement results support the statements made above.
MINT-College TIEFE
(2021)
Das Projekt MINT-College TIEFE konnte in der zweiten Förderperiode die verschiedenen Maßnahmen der vorangegangenen Förderperiode weiter ausbauen und verstetigen. Die Angebote im Rahmen des Projekts MINT-College TIEFE begleiteten die Studierenden über den Student-Life-Cycle hinweg über das komplette Studium der technischen Studiengänge, beginnend in der Schule und endend beim Übergang in den Beruf. Um die Qualität der Lehre an der Hochschule Offenburg zu verbessern, wurden darüber hinaus verschiedene digital unterstützte Lehrformate weiterentwickelt und ausgebaut. Zentrale Angebote des MINT-College, das 2019 zentrale Einrichtung der Hochschule Offenburg wurde, sind die für die Studieneingangsphase entwickelten Angebote der Einführungstage, des Mentorenprogramms, der Brückenkurse, des Lernzentrums und Angebote für den Übergang in den Beruf, wie das Gründerbüro. Die mediendidaktischen Unterstützungsangebote für Lehrende unterstützten den Lernkulturwandel an der Hochschule. Es wurden systematisch nachhaltige Strukturen aufgebaut, um Innovationen für das Lehren und das Lernen auch künftig entwickeln, erproben und etablieren zu können.
eLetter zum Artikel "Condiciones neuropsi-quiátricas y probable causa de muerte de Maurice Ravel" von Gómez-Carvajal AM, Botero-Meneses JS, Palacios-Espinosa X und Palacios-Sánchez L., veröffentlicht in Iatreia 35(3), Seite 341-8 (DOI: https://doi.org/10.17533/udea.iatreia.154).
Evaluierung von Kalman Filter Konfigurationen zur Roboterlokaliserung mittels Sensordatenfusion
(2023)
In dieser Arbeit werden drei verschiedene Konfigurationen der von Tom Moore, für das Robot Operating System, entwickelte Kalman-Filter vorgestellt. Diese bilden die Grundlage für eine Lokalisierung mittels Sensorfusion in dem verwendeten ROS-Framework. Ziel dieser Arbeit ist der Aufbau und die Verifikation einer Lokalisierung für ein mobiles Robotersystem Husky A200 der Firma Clearpath Robotics. Hierzu wurden die Möglichkeiten des bestehenden Systems untersucht und mehrere Versionen von Lokalisierungsfiltern konfiguriert. Am an Ende, wird eine Verifikation der Ergebnisse in verschiedenen Szenarien gegeneinandergestellt. Hierzu werden die Ergebnisse einer Variante des Extended Kalman-Filters in 2D (EKF2D), eine Variante des Unscented Kalman-Filter in 2D (UKF2D) und eine Variante des Extended Kalman-Filters in 3D (EKF3D) verifiziert und verglichen. Die Untersuchungen ergaben das der EKF2D die besten und robustesten Ergebnisse für eine Lokalisierung erbringt, trotz, im Vergleich zu der UKF2D Variante, 17,3 % höhere Endpositionsabweichung aufweist. Die in diesem Projekt gewählte EKF3D Konfigurationsvariante eignet sich, wegen seinen starken Ungenauigkeiten in der Höhenbestimmung nicht für eine aussagekräftige Positionsbestimmung.
Die Positionierung mobiler Systeme mit hoher Genauigkeit ist eine Voraussetzung für intelligentes autonomes Verhalten, sowohl in der Feldrobotik als auch in industriellen Umgebungen. Dieser Beitrag beschreibt den Aufbau einer Roboterplattform und ihre Verwendung für den Test und die Bewertung von Kalman-Filter-Konfigurationen. Der Aufbau wurde mit einem mobilen Roboter Husky A200 und einem LiDAR-Sensor (Light Detection and Ranging) realisiert. Zur Verifizierung des vorgeschlagenen Aufbaus wurden fünf verschiedene Szenarien ausgearbeitet. Mit denen wurden die Filter auf ihre Leistungsfähigkeit hinsichtlich der Genauigkeit der Positionsbestimmung getestet.
Device and method for monitoring and optimising a temporal trigger stability (WO2023094554A1)
(2023)
The present invention relates to devices for monitoring and optimising a temporal trigger stability of an extracorporeal circulatory support means, and to open-loop and closed-loop control units for the extracorporeal circulatory support means comprising such a device, and to corresponding methods. A device (10) for monitoring a temporal trigger stability of an extracorporeal circulatory support means is accordingly proposed, which device is designed to receive a first dataset (14) of a measurement of an ECG signal of a supported patient over a predefined period of time. The device (10) comprises an evaluation unit (16), which is designed to determine or identify a plurality of R triggers (26) from the first dataset (14), wherein the evaluation unit (16) is also designed to receive or provide a second dataset (20) having evaluated ECG signals and a plurality of R triggers (28) and to selectively map the second dataset (20) on the first dataset (14). The device is also designed to emit a signal (22) that characterises a temporal gap between successive R triggers (26) from the first dataset (14) and successive R triggers (28) from the second dataset (20) which are mapped on the first dataset.
Die vorliegende Erfindung betrifft Vorrichtungen zum Überwachen und Optimieren einer zeitlichen Triggerstabilität einer extrakorporalen Kreislaufunterstützung sowie Steuer- und Regeleinheiten zur extrakorporalen Kreislaufunterstützung, umfassend eine solche Vorrichtung und entsprechende Verfahren. Entsprechend wird eine Vorrichtung (10) zum Überwachen einer zeitlichen Triggerstabilität einer extrakorporalen Kreislaufunterstützung vorgeschlagen, welche dazu eingerichtet ist, einen ersten Datensatz (14) einer Messung eines EKG-Signals eines unterstützten Patienten über einen vorgegebenen Zeitraum zu empfangen. Die Vorrichtung (10) umfasst eine Auswerteeinheit (16), welche dazu eingerichtet ist, mehrere R-Trigger (26) aus dem ersten Datensatz (14) zu bestimmen oder zu identifizieren, wobei die Auswerteeinheit (16) weiterhin dazu eingerichtet ist, einen zweiten Datensatz (20) mit ausgewerteten EKG-Signalen und mehreren R-Triggern (28) zu empfangen oder bereitzustellen und den zweiten Datensatz (20) selektiv auf dem ersten Datensatz (14) abzubilden. Die Vorrichtung ist weiterhin dazu eingerichtet, ein Signal (22) auszugeben, welches kennzeichnend für einen zeitlichen Abstand sukzessiver R-Trigger (26) aus dem ersten Datensatz (14) und darauf abgebildeten sukzessiven R-Trigger (28) aus dem zweiten Datensatz (20) ist.
A balcony photovoltaic (PV) system, also known as a micro-PV system, is a small PV system consisting of one or two solar modules with an output of 100–600 Wp and a corresponding inverter that uses standard plugs to feed the renewable energy into the house grid. In the present study we demonstrate the integration of a commercial lithium-ion battery into a commercial micro-PV system. We firstly show simulations over one year with one second time resolution which we use to assess the influence of battery and PV size on self-consumption, self-sufficiency and the annual cost savings. We then develop and operate experimental setups using two different architectures for integrating the battery into the micro-PV system. In the passive hybrid architecture, the battery is in parallel electrical connection to the PV module. In the active hybrid architecture, an additional DC-DC converter is used. Both architectures include measures to avoid maximum power point tracking of the battery by the module inverter. Resulting PV/battery/inverter systems with 300 Wp PV and 555 Wh battery were tested in continuous operation over three days under real solar irradiance conditions. Both architectures were able to maintain stable operation and demonstrate the shift of PV energy from the day into the night. System efficiencies were observed comparable to a reference system without battery. This study therefore demonstrates the feasibility of both active and passive coupling architectures.
Das Ziel des Projekts PRYSTINE war es, eine fehlertolerante 360°-Rundumwahrnehmung für das hochautomatisierte Fahren in städtischen und ländlichen Umgebungen, auf Basis einer robusten Radar- und Lidar-Sensorfusion sowie Kontrollfunktionen, zu realisieren.
Im Teilvorhaben "Entwurf der Systemarchitektur von Radarsensoren auf Grundlage identifizierter Szenarien" stand die Entwicklung eines zukunftsfähigen RF-CMOS basierten Radarsystems im Fokus, das sich durch eine hohe Robustheit und Fehlertoleranz bei gleichzeitiger Reduktion der Kosten, Chipfläche und Leistungsaufnahme auszeichnet.
Darin war die Hochschule Offenburg sowohl an der Spezifizierung und am Entwurf einer Systemarchitektur für einen neuartigen RF-CMOS basierten Radarchip als auch an der anschließenden Untersuchung und Validierung des im Projekt realisierten hochauflösenden Radarsensors beteiligt.
Subjects utilizing a cochlear implant (CI) in one ear and a hearing aid (HA) on the contralateral ear suffer from mismatches in stimulation timing due to different processing latencies of both devices. This device delay mismatch leads to a temporal mismatch in auditory nerve stimulation. Compensating for this auditory nerve stimulation mismatch by compensating for the device delay mismatch can significantly improve sound source localization accuracy. One CI manufacturer has already implemented the possibility of mismatch compensation in its current fitting software. This study investigated if this fitting parameter can be readily used in clinical settings and determined the effects of familiarization to a compensated device delay mismatch over a period of 3–4 weeks. Sound localization accuracy and speech understanding in noise were measured in eleven bimodal CI/HA users, with and without a compensation of the device delay mismatch. The results showed that sound localization bias improved to 0°, implying that the localization bias towards the CI was eliminated when the device delay mismatch was compensated. The RMS error was improved by 18% with this improvement not reaching statistical significance. The effects were acute and did not further improve after 3 weeks of familiarization. For the speech tests, spatial release from masking did not improve with a compensated mismatch. The results show that this fitting parameter can be readily used by clinicians to improve sound localization ability in bimodal users. Further, our findings suggest that subjects with poor sound localization ability benefit the most from the device delay mismatch compensation.
Der verstärkte Einsatz von Wärmepumpen bei der Realisierung einer klimaneutralen Wärmeversorgung führt zu einer signifikanten Zunahme und Änderung der elektrischen Lasten in den Verteilnetzen. Daher gilt es, Wärmepumpen so zu steuern, dass sie Verteilnetze wenig belasten oder sogar unterstützen.
Inhalt des Projekts „PV²WP - PV Vorhersage für die netzdienliche Steuerung von Wärmepumpen“ (Projektlaufzeit 1.07.2018 – 30.06.2021) war die Demonstration eines neuen Ansatzes zur Steuerung von Heizungssystemen, die auf Wärmepumpen und thermischen Speichern basieren und in Kombination mit einer Photovoltaikanlage betrieben werden. Das übergeordnete Ziel war dabei die Verbesserung der Netzintegration und Smart-Grid-Tauglichkeit entsprechender Heizungssysteme durch eine kostengünstige Technologie bei gleichzeitiger Erhöhung der Wirtschaftlichkeit.
Dabei wurden drei zukunftsweisende Technologien in Kombination genutzt und demonstriert: wolkenkamerabasierte Kurzfristprognosen, prädiktive Steuerung und Regelung sowie machinelearning-basierte Systemmodellierung als Basis für die Optimierung. Als Demonstrationsumgebung diente mit dem Projekthaus Ulm ein real bewohntes Einfamilienhaus.Umweltforschung
Mit dem Klimaschutzgesetz 2021 wurden von der Bundesregierung die Klimaschutzvorgaben verschärft und die Treibhausgasneutralität bis 2045 als Ziel verankert. Zur Erreichung dieses ambitionierten Ziels ist es notwendig, im Bereich der Mobilität weitgehend von Verbrennungsmotoren mit fossilen Kraftstoffen auf Elektromobilität mit regenerativ erzeugtem Strom umzusteigen. Dabei ist die zügige Bereitstellung einer ausreichenden Ladeinfrastruktur für die Elektrofahrzeuge eine große Herausforderung. Neben der Installation einer ausreichend großen Zahl von Ladepunkten selbst besteht die Herausforderung darin, diese in das bestehende Verteilungsnetz zu integrieren bzw. das Verteilungsnetz so auszubauen, dass weiter ein sicherer Netzbetrieb gewährleistet werden kann. Dabei sind insbesondere Lösungen gefragt, bei denen der Ausbau der Ladeinfrastruktur und der Netzbetriebsmittel durch intelligentes Management des Ladens so gering wie möglich gehalten wird, indem vorhandene oder neu zu installierender Hardware möglichst effizient genutzt wird.
Hier setzte das Projekt „Intelligente Ladeinfrastruktur für Elektrofahrzeuge auf dem Parkplatz der Hochschule Offenburg (INTLOG)“ (Projektlaufzeit 15.11.2020 – 30.09.2022) an. Inhalt des Projekts war es, einen Ladepark für den Parkplatz der Hochschule Offenburg mit 20 Ladepunkten à 11 kW und somit einer Gesamtladeleistung von 220 kW an einen vorhandenen Ortsnetztransformator mit 200 kW Nennleistung anzuschließen, der aber bereits von anderen Verbrauchern genutzt wurde. Das übergeordnete Ziel war es also, eine Ladeinfrastruktur von maßgeblichem Umfang in die bestehende Netzinfrastruktur ohne zusätzlichen Ausbau zu integrieren.
Dabei wurden zukunftsweisende Technologien genutzt und weiterentwickelt sowie teilweise in Praxis, im Labor und in der Computersimulation demonstriert.
Electrolyte-gated transistors (EGTs) represent an interesting alternative to conventional dielectric-gating to reduce the required high supply voltage for printed electronic applications. Here, a type of ink-jet printable ion-gel is introduced and optimized to fabricate a chemically crosslinked ion-gel by self-assembled gelation, without additional crosslinking processes, e.g., UV-curing. For the self-assembled gelation, poly(vinyl alcohol) and poly(ethylene-alt-maleic anhydride) are used as the polymer backbone and chemical crosslinker, respectively, and 1-ethyl-3-methylimidazolium trifluoromethanesulfonate ([EMIM][OTf]) is utilized as an ionic species to ensure ionic conductivity. The as-synthesized ion-gel exhibits an ionic conductivity of ≈5 mS cm−1 and an effective capacitance of 5.4 µF cm−2 at 1 Hz. The ion-gel is successfully employed in EGTs with an indium oxide (In2O3) channel, which shows on/off-ratios of up to 1.3 × 106 and a subthreshold swing of 80.62 mV dec−1.
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.
Deep learning approaches are becoming increasingly important for the estimation of the Remaining Useful Life (RUL) of mechanical elements such as bearings. This paper proposes and evaluates a novel transfer learning-based approach for RUL estimations of different bearing types with small datasets and low sampling rates. The approach is based on an intermediate domain that abstracts features of the bearings based on their fault frequencies. The features are processed by convolutional layers. Finally, the RUL estimation is performed using a Long Short-Term Memory (LSTM) network. The transfer learning relies on a fixed-feature extraction. This novel deep learning approach successfully uses data of a low-frequency range, which is a precondition to use low-cost sensors. It is validated against the IEEE PHM 2012 Data Challenge, where it outperforms the winning approach. The results show its suitability for low-frequency sensor data and for efficient and effective transfer learning between different bearing types.
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
Die Erfindung betrifft eine Schaltungsanordnung (10) für ein Kraftfahrzeug, mit einer Hochvolt-Batterie (12) zum Speichern von elektrischer Energie, mit wenigstens einer elektrischen Maschine (14) zum Antreiben des Kraftfahrzeugs, mit einem Stromrichter (16), mittels welchem von der Hochvolt-Batterie (12) bereitstellbare Hochvolt-Gleichspannung in Hochvolt-Wechselspannung zum Betreiben der elektrischen Maschine (14) umwandelbar ist, und mit einem Ladeanschluss (20) zum Bereitstellen von elektrischer Energie zum Laden der Hochvolt-Batterie (12), wobei der Stromrichter (16) als ein Drei-Stufen-Stromrichter ausgebildet ist und wenigstens eine einer Phase (u) der elektrischen Maschine (14) zugeordnete Schaltereinheit (46) aufweist, welche zwei in Reihe geschaltete Schaltergruppen (52, 54) umfasst, die jeweils zwei in Reihe geschaltete IGBTs (T11, T12, T13, T14) aufweisen, wobei zwischen den IGBTs (T11, T12) einer der Schaltergruppen (52, 54) ein Anschluss (64) angeordnet ist, welcher direkt mit einer Leitung (34) des Ladeanschlusses (20) elektrisch verbunden ist.
A circuit arrangement of a motor vehicle includes a high-voltage battery for storing electrical energy, an electric machine for driving the motor vehicle, a converter via which high-voltage direct current voltage provided by the high-voltage battery is convertible into high-voltage alternating current voltage for operating the electric machine, and a charging connection for providing electrical energy for charging the high-voltage battery. The converter is a three-stage converter having a first switch unit which is assigned to a first phase of the electric machine. The first switch unit has two switch groups connected in series which each have two insulated-gate bipolar transistors (IGBTs) connected in series, where a connection is disposed between the IGBTs of one of the two switch groups, which connection is electrically connected directly to a line of the charging connection.
Featherweight Generic Go (FGG) is a minimal core calculus modeling the essential features of the programming language Go. It includes support for overloaded methods, interface types, structural subtyping and generics. The most straightforward semantic description of the dynamic behavior of FGG programs is to resolve method calls based on runtime type information of the receiver.
This article shows a different approach by defining a type-directed translation from FGG to an untyped lambda-calculus. The translation of an FGG program provides evidence for the availability of methods as additional dictionary parameters, similar to the dictionary-passing approach known from Haskell type classes. Then, method calls can be resolved by a simple lookup of the method definition in the dictionary.
Every program in the image of the translation has the same dynamic semantics as its source FGG program. The proof of this result is based on a syntactic, step-indexed logical relation. The step-index ensures a well-founded definition of the relation in the presence of recursive interface types and recursive methods.
Modelbasierte Zustandsschätzung elektrischer Betriebsmittel der Mittel- und Niederspannungsebenen
(2022)
Im Projekt MOBCOM wird ein neues Verfahren zur Zustandsüberwachung von elektrischen Betriebsmitteln in Niederspannungsnetzen und Anlagen entwickelt. Mittels PLC (power line communication) Technologie werden hochfrequente transiente Vorgänge auf dem Stromkanal und dessen Übertragungseigenschaften erfasst und bewertet.
In dem Abschlussbericht wird ein Prototyp für Powerline-Kommunikation zur Netzüberwachung beschrieben. Der Prototyp basiert auf einem PLC-Empfänger, welcher den Kanal misst, um so Informationen über den PLC-Kanal und den aktuellen Zustand des Stromnetzes zu erhaltet. Der PLC-Empfänger verwendet das Kommunikationssignal, um eine genaue Schätzung des Stromkanals zu erhalten und liefert Informationen zur Erkennung von Teilentladungen und anderen Anomalien im Netz. Diese Überwachung des Stromnetzes macht sich die bestehende PLC-Infrastruktur zunutze und verwendet die ohnehin übertragenen Datensignale, um eine Echtzeitmessung der Kanalübertragungsfunktion und des empfangenen Rauschsignals zu erhalten. Da dieses Signal im Vergleich zu einfacheren Messsensoren mit einer hohen Abtastrate abgetastet wird, enthält es wertvolle Informationen über mögliche Beeinträchtigungen im Netz, die behoben werden müssen. Während die Kanalmessungen auf einem empfangenen PLC-Signal beruhen, können Informationen über Teilentladungen oder andere Störquellen allein durch einen PLC-Empfänger gesammelt werden, d. h. ohne eine PLC-Übertragung. Es wurde ein Prototyp auf Basis von Software Defined Radio entwickelt, der die gleichzeitige Kommunikation und Erfassung für ein Stromnetz implementiert.
The importance of machine learning has been increasing dramatically for years. From assistance systems to production optimisation to support the health sector, almost every area of daily life and industry comes into contact with machine learning. Besides all the benefits that ML brings, the lack of transparency and the difficulty in creating traceability pose major risks. While there are solutions that make the training of machine learning models more transparent, traceability is still a major challenge. Ensuring the identity of a model is another challenge. Unnoticed modification of a model is also a danger when using ML. One solution is to create an ML birth certificate and an ML family tree secured by blockchain technology. Important information about training and changes to the model through retraining can be stored in a blockchain and accessed by any user to create more security and traceability about an ML model.
Es wird ein System zur Vorlesungsnachverfolgung (engl. Lecture Tracking) vorgestellt, das eine Kamera automatisch in Richtung des Vortragenden ausrichtet. Die kontinuierliche Positionsbestimmung der Kamera als auch die des Vortragenden erfolgt dabei durch Smartphones. Die Kamera und ein Smartphone sind an einen Roboter montiert, der als Schwenkeinheit dient. Das andere Smartphone trägt der Vortragende. Beide Smartphones können ihre Position im Raum bestimmen, sodass der erforderliche Drehwinkel berechnet und an den Roboter gesendet werden kann. Dieser führt dann die entsprechende Rotation durch, sodass der Vortragende immer in der Bildmitte zu sehen ist.
Titanium and stainless steel are commonly known as osteosynthesis materials with high strength and good biocompatibility. However, they have the big disadvantage that a second operation for hardware removal is necessary. Although resorbable systems made of polymers or magnesium are increasingly used, they show some severe adverse foreign body reactions or unsatisfying degradation behavior. Therefore, we started to investigate molybdenum as a potential new biodegradable material for osteosynthesis in craniomaxillofacial surgery. To characterize molybdenum as a biocompatible material, we performed in vitro assays in accordance with ISO Norm 10993-5. In four different experimental setups, we showed that pure molybdenum and molybdenum rhenium alloys do not lead to cytotoxicity in human and mouse fibroblasts. We also examined the degradation behavior of molybdenum by carrying out long-term immersion tests (up to 6 months) with molybdenum sheet metal. We showed that molybdenum has sufficient mechanical stability over at least 6 months for implants on the one hand and is subject to very uniform degradation on the other. The results of our experiments are very promising for the development of new resorbable osteosynthesis materials for craniomaxillofacial surgery based on molybdenum.
Blockchain-IIoT integration into industrial processes promises greater security, transparency, and traceability. However, this advancement faces significant storage and scalability issues with existing blockchain technologies. Each peer in the blockchain network maintains a full copy of the ledger which is updated through consensus. This full replication approach places a burden on the storage space of the peers and would quickly outstrip the storage capacity of resource-constrained IIoT devices. Various solutions utilizing compression, summarization or different storage schemes have been proposed in literature. The use of cloud resources for blockchain storage has been extensively studied in recent years. Nonetheless, block selection remains a substantial challenge associated with cloud resources and blockchain integration. This paper proposes a deep reinforcement learning (DRL) approach as an alternative to solving the block selection problem, which involves identifying the blocks to be transferred to the cloud. We propose a DRL approach to solve our problem by converting the multi-objective optimization of block selection into a Markov decision process (MDP). We design a simulated blockchain environment for training and testing our proposed DRL approach. We utilize two DRL algorithms, Advantage Actor-Critic (A2C), and Proximal Policy Optimization (PPO) to solve the block selection problem and analyze their performance gains. PPO and A2C achieve 47.8% and 42.9% storage reduction on the blockchain peer compared to the full replication approach of conventional blockchain systems. The slowest DRL algorithm, A2C, achieves a run-time 7.2 times shorter than the benchmark evolutionary algorithms used in earlier works, which validates the gains introduced by the DRL algorithms. The simulation results further show that our DRL algorithms provide an adaptive and dynamic solution to the time-sensitive blockchain-IIoT environment.
Spatially Distributed Wireless Networks (SDWN) are one of the basic technologies for the Internet of Things (IoT) and (Industrial) Internet of Things (IIoT) applications. These SDWN for many of these applications has strict requirements such as low cost, simple installation and operations, and high potential flexibility and mobility. Among the different Narrowband Wireless Wide Area Networking (NBWWAN) technologies, which are introduced to address these categories of wireless networking requirements, Narrowband Internet of Things (NB-IoT) is getting more traction due to attractive system parameters, energy-saving mode of operation with low data rates and bandwidth, and its applicability in 5G use cases. Since several technologies are available and because the underlying use cases come with various requirements, it is essential to perform a systematic comparative analysis of competing technologies to choose the right technology. It is also important to perform testing during different phases of the system development life cycle. This paper describes the systematic test environment for automated testing of radio communication and systematic measurements of the performance of NB-IoT.
In this paper, we study the runtime performance of symmetric cryptographic algorithms on an embedded ARM Cortex-M4 platform. Symmetric cryptographic algorithms can serve to protect the integrity and optionally, if supported by the algorithm, the confidentiality of data. A broad range of well-established algorithms exists, where the different algorithms typically have different properties and come with different computational complexity. On deeply embedded systems, the overhead imposed by cryptographic operations may be significant. We execute the algorithms AES-GCM, ChaCha20-Poly1305, HMAC-SHA256, KMAC, and SipHash on an STM32 embedded microcontroller and benchmark the execution times of the algorithms as a function of the input lengths.
In recent years, the topic of embedded machine learning has become very popular in AI research. With the help of various compression techniques such as pruning, quantization and others compression techniques, it became possible to run neural networks on embedded devices. These techniques have opened up a whole new application area for machine learning. They range from smart products such as voice assistants to smart sensors that are needed in robotics. Despite the achievements in embedded machine learning, efficient algorithms for training neural networks in constrained domains are still lacking. Training on embedded devices will open up further fields of applications. Efficient training algorithms would enable federated learning on embedded devices, in which the data remains where it was collected, or retraining of neural networks in different domains. In this paper, we summarize techniques that make training on embedded devices possible. We first describe the need and requirements for such algorithms. Then we examine existing techniques that address training in resource-constrained environments as well as techniques that are also suitable for training on embedded devices, such as incremental learning. At the end, we also discuss which problems and open questions still need to be solved in these areas.
The integration of Internet of Things devices onto the Blockchain implies an increase in the transactions that occur on the Blockchain, thus increasing the storage requirements.
A solution approach is to leverage cloud resources for storing blocks within the chain. The paper, therefore, proposes two solutions to this problem. The first being an improved hybrid architecture design which uses containerization to create a side chain on a fog node for the devices connected to it and an Advanced Time‑variant Multi‑objective Particle Swarm Optimization Algorithm (AT‑MOPSO) for determining the optimal number of blocks that should be transferred to the cloud for storage. This algorithm uses time‑variant weights for the velocity of the particle swarm optimization and the non‑dominated sorting and mutation schemes from NSGA‑III. The proposed algorithm was compared with results from the original MOPSO algorithm, the Strength Pareto Evolutionary Algorithm (SPEA‑II), and the Pareto Envelope‑based Selection Algorithm with region‑based selection (PESA‑II), and NSGA‑III. The proposed AT‑MOPSO showed better results than the aforementioned MOPSO algorithms in cloud storage cost and query probability optimization. Importantly, AT‑MOPSO achieved 52% energy efficiency compared to NSGA‑III.
To show how this algorithm can be applied to a real‑world Blockchain system, the BISS industrial Blockchain architecture was adapted and modified to show how the AT‑MOPSO can be used with existing Blockchain systems and the benefits it provides.
Recent work has investigated the distributions of learned convolution filters through a large-scale study containing hundreds of heterogeneous image models. Surprisingly, on average, the distributions only show minor drifts in comparisons of various studied dimensions including the learned task, image domain, or dataset. However, among the studied image domains, medical imaging models appeared to show significant outliers through "spikey" distributions, and, therefore, learn clusters of highly specific filters different from other domains. Following this observation, we study the collected medical imaging models in more detail. We show that instead of fundamental differences, the outliers are due to specific processing in some architectures. Quite the contrary, for standardized architectures, we find that models trained on medical data do not significantly differ in their filter distributions from similar architectures trained on data from other domains. Our conclusions reinforce previous hypotheses stating that pre-training of imaging models can be done with any kind of diverse image data.
In this paper, we propose a unified approach for network pruning and one-shot neural architecture search (NAS) via group sparsity. We first show that group sparsity via the recent Proximal Stochastic Gradient Descent (ProxSGD) algorithm achieves new state-of-the-art results for filter pruning. Then, we extend this approach to operation pruning, directly yielding a gradient-based NAS method based on group sparsity. Compared to existing gradient-based algorithms such as DARTS, the advantages of this new group sparsity approach are threefold. Firstly, instead of a costly bilevel optimization problem, we formulate the NAS problem as a single-level optimization problem, which can be optimally and efficiently solved using ProxSGD with convergence guarantees. Secondly, due to the operation-level sparsity, discretizing the network architecture by pruning less important operations can be safely done without any performance degradation. Thirdly, the proposed approach finds architectures that are both stable and well-performing on a variety of search spaces and datasets.
Despite the success of convolutional neural networks (CNNs) in many academic benchmarks for computer vision tasks, their application in the real-world is still facing fundamental challenges. One of these open problems is the inherent lack of robustness, unveiled by the striking effectiveness of adversarial attacks. Adversarial training (AT) is often considered as a remedy to train more robust networks. In this paper, we empirically analyze a variety of adversarially trained models that achieve high robust accuracies when facing state-of-the-art attacks and we show that AT has an interesting side-effect: it leads to models that are significantly less overconfident with their decisions even on clean data than non-robust models. Further, our analysis of robust models shows that not only AT but also the model's building blocks (like activation functions and pooling) have a strong influence on the models' prediction confidences.
Harnessing the overall benefits of the latest advancements in artificial intelligence (AI) requires the extensive collaboration of academia and industry. These collaborations promote innovation and growth while enforcing the practical usefulness of newer technologies in real life. The purpose of this article is to outline the challenges faced during cross-collaboration between academia and industry. These challenges are also inspected with the help of an ongoing project titled “Quality Assurance of Machine Learning Applications” (Q-AMeLiA), in which three universities cooperate with five industry partners to make the product risk of AI-based products visible. Further, we discuss the hurdles and the key challenges in machine learning (ML) technology transformation from academia to industry based on robustness, simplicity, and safety. These challenges are an outcome of the lack of common standards, metrics, and missing regulatory considerations when state-of-the-art (SOTA) technology is developed in academia. The use of biased datasets involves ethical concerns that might lead to unfair outcomes when the ML model is deployed in production. The advancement of AI in small and medium sized enterprises (SMEs) requires more in terms of common tandardization of concepts rather than algorithm breakthroughs. In this paper, in addition to the general challenges, we also discuss domain specific barriers for five different domains i.e., object detection, hardware benchmarking, continual learning, action recognition, and industrial process automation, and highlight the steps necessary for successfully managing the cross-sectoral collaborations between academia and industry.
Recently, RobustBench (Croce et al. 2020) has become a widely recognized benchmark for the adversarial robustness of image
classification networks. In it’s most commonly reported sub-task, RobustBench evaluates and ranks the adversarial robustness of trained neural networks on CIFAR10 under AutoAttack (Croce and Hein 2020b) with l∞ perturbations limited to ϵ = 8/255. With leading scores of the currently best performing models of around 60% of the baseline, it is fair to characterize this benchmark to be quite challenging. Despite it’s general acceptance in recent literature, we aim to foster discussion about the suitability of RobustBench as a key indicator for robustness which could be generalized to practical applications. Our line of argumentation against this is two-fold and supported by excessive experiments presented in this paper: We argue that I) the alternation of data by AutoAttack with l∞, ϵ = 8/255 is unrealistically strong, resulting in close to perfect detection rates of adversarial samples even by simple detection algorithms and human observers.
We also show that other attack methods are much harder to detect while achieving similar success rates. II) That results on low resolution data sets like CIFAR10 do not generalize well to higher resolution images as gradient based attacks appear to become even more detectable with increasing resolutions.
Many commonly well-performing convolutional neural network models have shown to be susceptible to input data perturbations, indicating a low model robustness. Adversarial attacks are thereby specifically optimized to reveal model weaknesses, by generating small, barely perceivable image perturbations that flip the model prediction. Robustness against attacks can be gained for example by using adversarial examples during training, which effectively reduces the measurable model attackability. In contrast, research on analyzing the source of a model’s vulnerability is scarce. In this paper, we analyze adversarially trained, robust models in the context of a specifically suspicious network operation, the downsampling layer, and provide evidence that robust models have learned to downsample more accurately and suffer significantly less from aliasing than baseline models.
Estimating the Robustness of Classification Models by the Structure of the Learned Feature-Space
(2022)
Over the last decade, the development of deep image classification networks has mostly been driven by the search for the best performance in terms of classification accuracy on standardized benchmarks like ImageNet. More recently, this focus has been expanded by the notion of model robustness, \ie the generalization abilities of models towards previously unseen changes in the data distribution. While new benchmarks, like ImageNet-C, have been introduced to measure robustness properties, we argue that fixed testsets are only able to capture a small portion of possible data variations and are thus limited and prone to generate new overfitted solutions. To overcome these drawbacks, we suggest to estimate the robustness of a model directly from the structure of its learned feature-space. We introduce robustness indicators which are obtained via unsupervised clustering of latent representations from a trained classifier and show very high correlations to the model performance on corrupted test data.
Aerosol particles play an important role in the climate system by absorbing and scattering radiation and influencing cloud properties. They are also one of the biggest sources of uncertainty for climate modeling. Many climate models do not include aerosols in sufficient detail due to computational constraints. To represent key processes, aerosol microphysical properties and processes have to be accounted for. This is done in the ECHAM-HAM (European Center for Medium-Range Weather Forecast-Hamburg-Hamburg) global climate aerosol model using the M7 microphysics, but high computational costs make it very expensive to run with finer resolution or for a longer time. We aim to use machine learning to emulate the microphysics model at sufficient accuracy and reduce the computational cost by being fast at inference time. The original M7 model is used to generate data of input–output pairs to train a neural network (NN) on it. We are able to learn the variables’ tendencies achieving an average R² score of 77.1%. We further explore methods to inform and constrain the NN with physical knowledge to reduce mass violation and enforce mass positivity. On a Graphics processing unit (GPU), we achieve a speed-up of up to over 64 times faster when compared to the original model.
Many commonly well-performing convolutional neural network models have shown to be susceptible to input data perturbations, indicating a low model robustness. To reveal model weaknesses, adversarial attacks are specifically optimized to generate small, barely perceivable image perturbations that flip the model prediction. Robustness against attacks can be gained by using adversarial examples during training, which in most cases reduces the measurable model attackability. Unfortunately, this technique can lead to robust overfitting, which results in non-robust models. In this paper, we analyze adversarially trained, robust models in the context of a specific network operation, the downsampling layer, and provide evidence that robust models have learned to downsample more accurately and suffer significantly less from downsampling artifacts, aka. aliasing, than baseline models. In the case of robust overfitting, we observe a strong increase in aliasing and propose a novel early stopping approach based on the measurement of aliasing.
Despite the success of convolutional neural networks (CNNs) in many academic benchmarks for computer vision tasks, their application in the real-world is still facing fundamental challenges. One of these open problems is the inherent lack of robustness, unveiled by the striking effectiveness of adversarial attacks. Current attack methods are able to manipulate the network's prediction by adding specific but small amounts of noise to the input. In turn, adversarial training (AT) aims to achieve robustness against such attacks and ideally a better model generalization ability by including adversarial samples in the trainingset. However, an in-depth analysis of the resulting robust models beyond adversarial robustness is still pending. In this paper, we empirically analyze a variety of adversarially trained models that achieve high robust accuracies when facing state-of-the-art attacks and we show that AT has an interesting side-effect: it leads to models that are significantly less overconfident with their decisions, even on clean data than non-robust models. Further, our analysis of robust models shows that not only AT but also the model's building blocks (like activation functions and pooling) have a strong influence on the models' prediction confidences. Data & Project website: https://github.com/GeJulia/robustness_confidences_evaluation
Over the last years, Convolutional Neural Networks (CNNs) have been the dominating neural architecture in a wide range of computer vision tasks. From an image and signal processing point of view, this success might be a bit surprising as the inherent spatial pyramid design of most CNNs is apparently violating basic signal processing laws, i.e. Sampling Theorem in their down-sampling operations. However, since poor sampling appeared not to affect model accuracy, this issue has been broadly neglected until model robustness started to receive more attention. Recent work in the context of adversarial attacks and distribution shifts, showed after all, that there is a strong correlation between the vulnerability of CNNs and aliasing artifacts induced by poor down-sampling operations. This paper builds on these findings and introduces an aliasing free down-sampling operation which can easily be plugged into any CNN architecture: FrequencyLowCut pooling. Our experiments show, that in combination with simple and Fast Gradient Sign Method (FGSM) adversarial training, our hyper-parameter free operator substantially improves model robustness and avoids catastrophic overfitting. Our code is available at https://github.com/GeJulia/flc_pooling
Metallische Gehäuse stellen eine große Herausforderung für die Schnittstelle von aktiven medizinischen Implantaten dar. Ihre elektrische Leitfähigkeit und die sich dadurch ergebenden Wirbelströme verhindern das Eindringen von hochfrequenten elektromagnetischen Wellen und Feldern. Aus diesem Grund werden die Antennen außerhalb des Gehäuses platziert. Niederfrequentere magnetische Felder dringen jedoch durch das metallische Gehäuse, wenn auch abgeschwächt. Damit kann eine induktive Kommunikation realisiert und so elektrische Durchführungen durch das ansonsten hermetisch dichte Gehäuse vermieden werden.
In dieser Arbeit wird die induktive Datenübertragung durch ein metallisches Gehäuse untersucht. Ein Modell wird entwickelt, das die Effekte des metallischen Gehäuses auf die Übertragung berücksichtigt. Hierzu werden in einem neuen Ansatz anhand von FEM Simulationen Korrekturfaktoren ermittelt. Diese Korrekturfaktoren können visualisiert und direkt auf die Auslegung der Antennenspulen angewendet werden. Im Gegensatz zu anderen Modellierungen werden nur frei zugängliche Software-Lösungen verwendet. Zudem werden die Feldverteilungen durch die im metallischen Gehäuse entstehenden Wirbelströme untersucht. Die unterschiedlichen Gehäuse- und Spulenparameter werden im Hinblick auf deren Einfluss auf das Übertragungsverhalten diskutiert, was in dieser Form bisher noch nicht veröffentlicht wurde. Das resultierende Modell kann auf unterschiedliche Ausführungen der metallischen Kapselung angepasst werden um damit die Grenzen und Einschränkungen unterschiedlicher metallischer Gehäuse-Materialien zu untersuchen.
Mit der Weiterentwicklung eines Transceivers, der mit 10 kBit/s bei 125 kHz Trägerfrequenz arbeitet, wird ein Übertragungsbaustein entwickelt, der mit herkömmlichen Mikrocontrollern verwendet werden kann. Der Transceiver wird in einem ASIC mit 32 Pin QFN-Gehäuse implementiert. Anschließend werden die Funktionalität überprüft und die elektrischen Eigenschaften im Hinblick auf Temperatur-, Spannungs- und Frequenz-Verhalten charakterisiert. Durch die geringe Stromaufnahme und die hohe Datenrate bei niedriger Trägerfrequenz eignet sich dieser Transceiver für Langzeitanwendungen in medizinischen Implantaten. Das Neue an dem Transceiver ist seine Einsatzfähigkeit für metallische Gehäuse, die wegen der schmalen Bandbreite mit \approx\unit[4]{kHz} eine effiziente Datenübertragung trotz hoher Dämpfung ermöglicht und darüber hinaus die frequenzabhängige Verzerrung der Impedanz- und Übertragungsparameter minimiert.
Anhand einer konkreten Anwendung für eine implantierbare steuerbare Infusionspumpe werden die gesamte Elektronik des Implantats sowie eines kleinen und ein großen Bediengerätes konzipiert, entwickelt, programmiert und erfolgreich in Betrieb genommen. Darin werden sowohl das induktive Übertragungsmodell als auch der Transceiver verwendet und somit deren Funktionalität und Einsatzfähigkeit demonstriert. Mithilfe dieser Entwicklung ist es möglich, über einen Abstand von 65 mm, die Dosierung eines Medikaments einzustellen und an den Tagesrhythmus der Patient*innen anzupassen sowie die Funktionalität des Implantats zu überprüfen. Aktuell gibt es auf dem Markt ein weiteres ähnliches Produkt, zu dem jedoch keine wissenschaftlichen Veröffentlichungen vorliegen. Diese Arbeit liefert damit einen wissenschaftlichen Beitrag für die Entwicklung langlebiger metallisch gekapselter Implantate mit induktiver Schnittstelle.
When people with hearing loss are provided with different devices in each ear, these devices usually have different processing latencies. This leads to static temporal offsets between both ears in the order of several milliseconds. This thesis measured effects of such offsets in stimulation timing on mechanisms of binaural hearing, such as sound localization and speech understanding in noise in hearing-impaired and normal-hearing listeners.
In this paper, a concept for an anthropomorphic replacement hand cast with silicone with an integrated sensory feedback system is presented. In order to construct the personalized replacement hand, a 3D scan of a healthy hand was used to create a 3D-printed mold using computer-aided design (CAD). To allow for movement of the index and middle fingers, a motorized orthosis was used. Information about the applied force for grasping and the degree of flexion of the fingers is registered using two pressure sensors and one bending sensor in each movable finger. To integrate the sensors and additional cavities for increased flexibility, the fingers were cast in three parts, separately from the rest of the hand. A silicone adhesive (Silpuran 4200) was examined to combine the individual parts afterwards. For this, tests with different geometries were carried out. Furthermore, different test series for the secure integration of the sensors were performed, including measurements of the registered information of the sensors. Based on these findings, skin-toned individual fingers and a replacement hand with integrated sensors were created. Using Silpuran 4200, it was possible to integrate the needed cavities and to place the sensors securely into the hand while retaining full flexion using a motorized orthosis. The measurements during different loadings and while grasping various objects proved that it is possible to realize such a sensory feedback system in a replacement hand. As a result, it can be stated that the cost-effective realization of a personalized, anthropomorphic replacement hand with an integrated sensory feedback system is possible using 3D scanning and 3D printing. By integrating smaller sensors, the risk of damaging the sensors through movement could be decreased.
Die Corona-Semester erforderten die Übertragung der Brückenkurse Mathematik in ein digitales Lehr-format. Gerade beim Studieneinstieg spielen persönliche Unterstützung und soziale Eingebundenheit für Studierende eine besonders wichtige Rolle. Deshalb lag die besondere Herausforderung bei der Übertragung in ein digitales Format darin, die wegfallenden üblichen Kennenlern- und Kommunika-tionsmöglichkeiten, die sich in Präsenzformaten beispielsweise in den Pausen oder im Gespräch mit den Sitznachbarn ergeben, zu kompensieren. Vorliegender Beitrag stellt vor, inwieweit der Transfer in ein digitales Format gelungen ist. Das digitale Brückenkurskonzept wurde in ein didaktisches Entwurfsmuster übertragen, um durch die strukturierte und nachvollziehbare Darstellung den Transfer und die Vergleichbarkeit der Ergebnisse zu erleichtern.
Positioning mobile systems with high accuracy is a prerequisite for intelligent autonomous behavior, both in industrial environments and in field robotics. This paper describes the setup of a robotic platform and its use for the evaluation of simultaneous localization and mapping (SLAM) algorithms. A configuration using a mobile robot Husky A200, and a LiDAR (light detection and ranging) sensor was used to implement the setup. For verification of the proposed setup, different scan matching methods for odometry determination in indoor and outdoor environments are tested. An assessment of the accuracy of the baseline 3D-SLAM system and the selected evaluation system is presented by comparing different scenarios and test situations. It was shown that the hdl_graph_slam in combination with the LiDAR OS1 and the scan matching algorithms FAST_GICP and FAST_VGICP achieves good mapping results with accuracies up to 2 cm.
Um die im Pariser Klimaschutzabkommen vereinbarte Begrenzung der Erderwärmung auf 1,5 Grad Celsius zu begrenzen, muss die Energiewende deutlich stärker vorangetrieben werden als bisher. Das Schaufenster C/sells in der größten der SINTEG-Modellregionen hat sich dieser Herausforderung gestellt. Über vier Jahre haben 56 Partner aus Energiewirtschaft, Wissenschaft und Politik in Baden-Württemberg, Bayern und Hessen daran gearbeitet, ein zelluläres Energiesystem zu etablieren. Sie haben Musterlösungen für eine erfolgreiche Energiewende entwickelt. In mehr als 30 Demonstrationszellen sowie in neun Partizipationszellen, den sogenannten C/sells-Citys, wurde demonstriert, wie ein Informationssystem die intelligente Organisation von Stromversorgungsnetzen und den regionalisierten Handel mit Energie und Flexibilitäten ermöglicht.