Refine
Document Type
- Conference Proceeding (194)
- Article (reviewed) (98)
- Article (unreviewed) (21)
- Letter to Editor (16)
- Master's Thesis (12)
- Book (7)
- Doctoral Thesis (7)
- Patent (7)
- Part of a Book (3)
- Bachelor Thesis (1)
Conference Type
- Konferenzartikel (169)
- Konferenz-Abstract (19)
- Sonstiges (5)
- Konferenz-Poster (1)
Language
- English (369) (remove)
Keywords
- RoboCup (12)
- Deep Leaning (11)
- Machine Learning (11)
- Götz von Berlichingen (8)
- neuroprosthetics (8)
- Blockchain (6)
- machine learning (6)
- Heart rhythm model (5)
- Modeling and simulation (5)
- neural networks (5)
Institute
- Fakultät Elektrotechnik, Medizintechnik und Informatik (EMI) (ab 04/2019) (369) (remove)
Open Access
- Open Access (180)
- Closed Access (115)
- Closed (69)
- Bronze (31)
- Gold (28)
- Diamond (22)
- Grün (3)
- Hybrid (2)
"Ad fontes!"
Francesco Petrarca (1301–1374)
In the beginning, there was an idea: the reconstruction of the first "Iron Hand" of the Franconian imperial knight Götz von Berlichingen (1480–1562). We found that with this historical prosthesis, simple actions for daily use, such as holding a wine glass, a mobile phone, a bicycle handlebar grip, a horse’s reins, or some grapes, are possible without effort. Controlling this passive artificial hand, however, is based on the help of a healthy second hand.
This thesis focuses on the development and implementation of a Datagram Transport Layer Security (DTLS) communication framework within the ns-3 network simulator, specifically targeting the LoRaWAN model network. The primary aim is to analyse the behaviour and performance of DTLS protocols across different network conditions within a LoRaWAN context. The key aspects of this work include the following.
Utilization of ns-3: This thesis leverages ns-3’s capabilities as a powerful discrete event network simulator. This platform enables the emulation of diverse network environments, characterized by varying levels of latency, packet loss, and bandwidth constraints.
Emulation of Network Challenges: The framework specifically addresses unique challenges posed by certain network configurations, such as duty cycle limitations. These constraints, which limit the time allocated for data transmission by each device, are crucial in understanding the real-world performance of DTLS protocols.
Testing in Multi-client-server Scenarios: A significant feature of this framework is its ability to test DTLS performance in complex scenarios involving multiple clients and servers. This is vital for assessing the behaviour of a protocol under realistic network conditions.
Realistic Environment Simulation: By simulating challenging network conditions, such as congestion, limited bandwidth, and resource constraints, the framework provides a realistic environment for thorough evaluation. This allows for a comprehensive analysis of DTLS in terms of security, performance, and scalability.
Overall, this thesis contributes to a deeper understanding of DTLS protocols by providing a robust tool for their evaluation under various and challenging network conditions.
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.
Decarbonisation Strategies in Energy Systems Modelling: APV and e-tractors as Flexibility Assets
(2023)
This work presents an analysis of the impact of introducing Agrophotovoltaic technologies and electric tractors into Germany’s energy system. Agrophotovoltaics involves installing photovoltaic systems in agricultural areas, allowing for dual usage of the land for both energy generation and food production. Electric tractors, which are agricultural machinery powered by electric motors, can also function as energy storage units, providing flexibility to the grid. The analysis includes a sensitivity study to understand how the availability of agricultural land influences Agrophotovoltaic investments, followed by the examination of various scenarios that involve converting diesel tractors to electric tractors. These scenarios are based on the current CO2 emission reduction targets set by the German Government, aiming for a 65% reduction below 1990 levels by 2030 and achieving zero emissions by 2045. The results indicate that approximately 3% of available agricultural land is necessary to establish a viable energy mix in Germany. Furthermore, the expansion of electric tractors tends to reduce the overall system costs and enhances the energy-cost-efficiency of Agrophotovoltaic investments.
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.
In the past ten years, applications of artificial neural networks have changed dramatically. outperforming earlier predictions in domains like robotics, computer vision, natural language processing, healthcare, and finance. Future research and advancements in CNN architectures, Algorithms and applications are expected to revolutionize various industries and daily life further. Our task is to find current products that resemble the given product image and description. Deep learning-based automatic product identification is a multi-step process that starts with data collection and continues with model training, deployment, and continuous improvement. The caliber and variety of the dataset, the design selected, and ongoing testing and improvement all affect the model's effectiveness. We achieved 81.47% training accuracy and 72.43% validation accuracy for our combined text and image classification model. Additionally, we have discussed the outcomes from the other dataset and numerous methods for creating an appropriate model.
Analysing and predicting the advance rate of a tunnel boring machine (TBM) in hard rock is integral to tunnelling project planning and execution. It has been applied in the industry for several decades with varying success. Most prediction models are based on or designed for large-diameter TBMs, and much research has been conducted on related tunnelling projects. However, only a few models incorporate information from projects with an outer diameter smaller than 5 m and no penetration prediction model for pipe jacking machines exists to date. In contrast to large TBMs, small-diameter TBMs and their projects have been considered little in research. In general, they are characterised by distinctive features, including insufficient geotechnical information, sometimes rather short drive lengths, special machine designs and partially concurring lining methods like pipe jacking and segment lining. A database which covers most of the parameters mentioned above has been compiled to investigate the performance of small-diameter TBMs in hard rock. In order to provide sufficient geological and technical variance, this database contains 37 projects with 70 geotechnically homogeneous areas. Besides the technical parameters, important geotechnical data like lithological information, unconfined compressive strength, tensile strength and point load index is included and evaluated. The analysis shows that segment lining TBMs have considerably higher penetration rates in similar geological and technical settings mostly due to their design parameters. Different methodologies for predicting TBM penetration, including state-of-the-art models from the literature as well as newly derived regression and machine learning models, are discussed and deployed for backward modelling of the projects contained in the database. New ranges of application for small-diameter tunnelling in several industry-standard penetration models are presented, and new approaches for the penetration prediction of pipe jacking machines in hard rock are proposed.
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/.
Detecting Images Generated by Deep Diffusion Models using their Local Intrinsic Dimensionality
(2023)
Diffusion models recently have been successfully applied for the visual synthesis of strikingly realistic appearing images. This raises strong concerns about their potential for malicious purposes. In this paper, we propose using the lightweight multi Local Intrinsic Dimensionality (multiLID), which has been originally developed in context of the detection of adversarial examples, for the automatic detection of synthetic images and the identification of the according generator networks. In contrast to many existing detection approaches, which often only work for GAN-generated images, the proposed method provides close to perfect detection results in many realistic use cases. Extensive experiments on known and newly created datasets demonstrate that the proposed multiLID approach exhibits superiority in diffusion detection and model identification.Since the empirical evaluations of recent publications on the detection of generated images are often mainly focused on the "LSUN-Bedroom" dataset, we further establish a comprehensive benchmark for the detection of diffusion-generated images, including samples from several diffusion models with different image sizes.The code for our experiments is provided at https://github.com/deepfake-study/deepfake-multiLID.
One of the most important questions about smart metering systems for the end users is their data privacy and security. Indeed, smart metering systems provide a lot of advantages for distribution system operators (DSO), but functionalities offered to users of existing smart meters are still limited and society is becoming increasingly critical. Smart metering systems are accused of interfering with personal rights and privacy, providing unclear tariff regulations which not sufficiently encourage households to manage their electricity consumption in advance. In the specific field of smart grids, data security appears to be a necessary condition for consumer confidence without which they will not be able to give their consent to the collection and use of personal data concerning them.
Precisely synchronized communication is a major precondition for many industrial applications. At the same time, hardware cost and power consumption need to be kept as low as possible in the Internet of Things (IoT) paradigm. While many wired solutions on the market achieve these requirements, wireless alternatives are an interesting field for research and development. This article presents a novel IEEE802.11n/ac wireless solution, exhibiting several advantages over state-of-the-art competitors. It is based on a market-available wireless System on a Chip with modified low-level communication firmware combined with a low-cost field-programmable gate array. By achieving submicrosecond synchronization accuracy, our solution outperforms the precision of low-cost products by almost four orders of magnitude. Based on inexpensive hardware, the presented wireless module is up to 20 times cheaper than software-defined-radio solutions with comparable timing accuracy. Moreover, it consumes three to five times less power. To back up our claims, we report data that we collected with a high sampling rate (2000 samples per second) during an extended measurement campaign of more than 120 h, which makes our experimental results far more representative than others reported in the literature. Additional support is provided by the size of the testbed we used during the experiments, composed of a hybrid network with nine nodes divided into two independent wireless segments connected by a wired backbone. In conclusion, we believe that our novel Industrial IoT module architecture will have a significant impact on the future technological development of high-precision time-synchronized communication for the cost-sensitive industrial IoT market.
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.
Printed electronics can add value to existing products by providing new smart functionalities, such as sensing elements over large-areas on flexible or non-conformal surfaces. Here we present a hardware concept and prototype for a thinned ASIC integrated with an inkjet-printed temperature sensor alongside in-built additional security and unique identification features. The hybrid system exploits the advantages of inkjet-printable platinum-based sensors, physically unclonable function circuits and a fluorescent particle-based coating as a tamper protection layer.
PROFINET Security: A Look on Selected Concepts for Secure Communication in the Automation Domain
(2023)
We provide a brief overview of the cryptographic security extensions for PROFINET, as defined and specified by PROFIBUS & PROFINET International (PI). These come in three hierarchically defined Security Classes, called Security Class 1,2 and 3. Security Class 1 provides basic security improvements with moderate implementation impact on PROFINET components. Security Classes 2 and 3, in contrast, introduce an integrated cryptographic protection of PROFINET communication. We first highlight and discuss the security features that the PROFINET specification offers for future PROFINET products. Then, as our main focus, we take a closer look at some of the technical challenges that were faced during the conceptualization and design of Security Class 2 and 3 features. In particular, we elaborate on how secure application relations between PROFINET components are established and how a disruption-free availability of a secure communication channel is guaranteed despite the need to refresh cryptographic keys regularly. The authors are members of the PI Working Group CB/PG10 Security.
Wireless communication networks are crucial for enabling megatrends like the Internet of Things (IoT) and Industry 4.0. However, testing these networks can be challenging due to the complex network topology and RF characteristics, requiring a multitude of scenarios to be tested. To address this challenge, the authors developed and extended an automated testbed called Automated Physical TestBed (APTB). This testbed provides the means to conduct controlled tests, analyze coexistence, emulate multiple propagation paths, and model dependable channel conditions. Additionally, the platform supports test automation to facilitate efficient and systematic experimentation. This paper describes the extended architecture, implementation, and performance evaluation of the APTB testbed. The APTB testbed provides a reliable and efficient solution for testing wireless communication networks under various scenarios. The implementation and performance verification of the testbed demonstrate its effectiveness and usefulness for researchers and industry practitioners.
TSN, or Time Sensitive Networking, is becoming an essential technology for integrated networks, enabling deterministic and best effort traffic to coexist on the same infrastructure. In order to properly configure, run and secure such TSN, monitoring functionality is a must. The TSN standard already has some preparations to provide such functionality and there are different methods to choose from. We implemented different methods to measure the time synchronisation accuracy between devices as a C library and compared the measurement results. Furthermore, the library has been integrated into the ControlTSN engineering framework.
As industrial networks continue to expand and connect more devices and users, they face growing security challenges such as unauthorized access and data breaches. This paper delves into the crucial role of security and trust in industrial networks and how trust management systems (TMS) can mitigate malicious access to these networks.The TMS presented in this paper leverages distributed ledger technology (blockchain) to evaluate the trustworthiness of blockchain nodes, including devices and users, and make access decisions accordingly. While this approach is applicable to blockchain, it can also be extended to other areas. This approach can help prevent malicious actors from penetrating industrial networks and causing harm. The paper also presents the results of a simulation to demonstrate the behavior of the TMS and provide insights into its effectiveness.
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.
Fused Filament Fabrication (FFF) is a widespread additive manufacturing technology, mostly in the field of printable polymers. The use of filaments filled with metal particles for the manufacture of metallic parts by FFF presents specific challenges regarding debinding and sintering. For aluminium and its alloys, the sintering temperature range overlaps with the temperature range of thermal decomposition of many commonly used “backbone” polymers, which provide stability to the green parts. Moreover, the high oxygen affinity of aluminium necessitates the use of special sintering regimes and alloying strategies. Therefore, it is challenging to achieve both low porosity and low levels of oxygen and carbon impurities at the same time. Feedstocks compatible with the special requirements of aluminium alloys were developed. We present results on the investigation of debinding/sintering regimes by Fourier Transform Infrared spectroscopy (FTIR) based In-Situ Process Gas Analysis and discuss optimized thermal treatment strategies for Al-based FFF.
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.
In recent years, predictive maintenance tasks, especially for bearings, have become increasingly important. Solutions for these use cases concentrate on the classification of faults and the estimation of the Remaining Useful Life (RUL). As of today, these solutions suffer from a lack of training samples. In addition, these solutions often require high-frequency accelerometers, incurring significant costs. To overcome these challenges, this research proposes a combined classification and RUL estimation solution based on a Convolutional Neural Network (CNN) and a Long Short-Term Memory (LSTM) network. This solution relies on a hybrid feature extraction approach, making it especially appropriate for low-cost accelerometers with low sampling frequencies. In addition, it uses transfer learning to be suitable for applications with only a few training samples.
In recent times, 5G has found applications in several public as well as private networks. There is a growing need to make it compatible with diverse services without compromising security. Current security options for authenticating devices into a home network are 5G Authentication and Key Agreement (5G-AKA) and Extensible Authentication Protocol (EAP)-AKA'. However, for specific use cases such as private networks, more customizable and convenient authentication mechanisms are required. The current mobile networks use authentication based only on SIM cards, but as 5G is being applied in fields like IIoT and automation, even in Non-Public-Networks (NPNs), there is a need for a simpler method of authentication. Certificate-based authentication is one such mechanism that is passwordless and works solely on the information present in the digital certificate that the user holds. The paper suggests an authentication mechanism that performs certificate-based mutual authentication between the UE and the Home network. The proposed concept identifies both the user and network with digital certificates and intends to carry out primary authentication with the help of it. In this work we conduct a study on presently available authentication protocols for 5G networks, both theoretically and experimentally in hardware as well as virtual environments. On the basis of the analysis a series of proposed steps for certificate primary authentication are presented.
The Transport Layer Security protocol is a widespread cryptographic protocol designed to provide secure communication over insecure networks by providing authenticity, integrity, and confidentiality. As a first step, in the TLS Handshake Protocol a common master secret is negotiated. In many configurations, this step makes considerable use of asymmetric cryptographic algorithms. It seems to be a prevalent assumption that the use of such asymmetric cryptographic algorithms is unsuitable for resource-constrained devices. Therefore, the work at hand analyzes the runtime performance of the TLS vl.2 session establishments on an embedded ARM Cortex-M4 platform. We measure the execution time to generate and parse session establishment messages for the client and server sides. In particular, we study the impact of different elliptic curves used for the ephemeral Diffie-Hellman key exchange and the impact of different lengths and subject public key algorithms of certification paths. Our analysis shows that the use of asymmetric cryptographic algorithms is well possible on resource-constrained devices, if carefully chosen and well implemented. This allows the use of the well-proven TLS protocol also for applications from the (Industrial) Internet of Things, including Fieldbus communication.
Physical unclonable functions (PUFs) are increasingly generating attention in the field of hardware-based security for the Internet of Things (IoT). A PUF, as its name implies, is a physical element with a special and unique inherent characteristic and can act as the security anchor for authentication and cryptographic applications. Keeping in mind that the PUF outputs 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 this work, the PUF output positioning (POP) method is proposed, which is a novel method for grouping the PUF outputs in order to maximize the extracted entropy. To achieve this, an offset data is introduced as helper data, which is used to relax the constraints considered for the grouping of PUF outputs, and deriving more entropy, while reducing the secret key error bits. To implement the method, the key enrollment and key generation algorithms are presented. Based on a theoretical analysis of the achieved entropy, it is proven that POP can maximize the achieved entropy, while respecting the constraints induced to guarantee the reliability of the secret key. Moreover, a detailed security analysis is presented, which shows the resilience of the method against cyber-security attacks. The findings of this work are evaluated by applying the method on a hybrid printed PUF, where it can be practically shown that the proposed method outperforms other existing group-based PUF key generation methods.
The often-occurring short-term orders of manufactured products require a high machine availability. This requirement increases the importance of predictive maintenance solutions for bearings used in machines. There are, among others, hybrid solutions that rely on a physical model. For their usage, knowing the different degradation stages of bearings is essential. This research analyzes the underlying failure mechanisms of these stages theoretically and in a practical example of the well-known FEMTO dataset used for the IEEE PHM 2012 Data Challenge to provide this knowledge. In addition, it shows for which use cases the usage of low-frequency accelerometers is sufficient. The analysis provides that the degradation stages toward the end of the bearing life can also be detected with low-frequency accelerometers. Further, the importance of high-frequency accelerometers to detect bearing faults in early degradation stages is pointed out. These aspects have not been paid attention to by industry and research until now, despite providing a considerable cost-saving potential.
As cyber-attacks and functional safety requirements increase in Operational Technology (OT), implementing security measures becomes crucial. The IEC/IEEE 60802 draft standard addresses the security convergence in Time-Sensitive Networks (TSN) for industrial automation.We present the standard’s security architecture and its goals to establish end-to-end security with resource access authorization in OT systems. We compare the standard to our abstract technology-independent model for the management of cryptographic credentials during the lifecycles of OT systems. Additionally, we implemented the processes, mechanisms, and protocols needed for IEC/IEEE 60802 and extended the architecture with public key infrastructure (PKI) functionalities to support complete security management processes.
The automatic processing of handwritten forms remains a challenging task, wherein detection and subsequent classification of handwritten characters are essential steps. We describe a novel approach, in which both steps - detection and classification - are executed in one task through a deep neural network. Therefore, training data is not annotated by hand, but manufactured artificially from the underlying forms and yet existing datasets. It can be demonstrated that this single-task approach is superior in comparison to the state-of-the-art two task approach. The current study focuses on hand-written Latin letters and employs the EMNIST data set. However, limitations were identified with this data set, necessitating further customization. Finally, an overall recognition rate of 88.28% was attained on real data obtained from a written exam.
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.
This study focuses on the autonomous navigation and mapping of indoor environments using a drone equipped only with a monocular camera and height measurement sensors. A visual SLAM algorithm was employed to generate a preliminary map of the environment and to determine the drone's position within the map. A deep neural network was utilized to generate a depth image from the monocular camera's input, which was subsequently transformed into a point cloud to be projected into the map. By aligning the depth point cloud with the map, 3D occupancy grid maps were constructed by using ray tracing techniques to get a precise depiction of obstacles and the surroundings. Due to the absence of IMU data from the low-cost drone for the SLAM algorithm, the created maps are inherently unscaled. However, preliminary tests with relative navigation in unscaled maps have revealed potential accuracy issues, which can only be overcome by incorporating additional information from the given sensors for scale estimation.
Modern industrial production is heavily dependent on efficient workflow processes and automation. The steady flow of raw materials as well as the separation of vital parts and semi-finished products are at the core of these automated procedures. Commonly used systems for this work are bowl feeders, which separate the parts and material by a combination of mechanical vibration and friction. The production of these tools, especially the design of the ramping spiral, is delicate and time-consuming work, as the shape, slope, and material must be carefully adjusted for the corresponding parts. In this work, we propose an automated approach, making use of optimization procedures from artificial intelligence, to design the spiral ramps of the bowl feeders. Therefore, the whole system and considered parts are physically simulated and the optimized geometry is subsequently exported into a CAD system for the actual building, respectively printing. The employment of evolutionary optimization gives the need to develop a mathematical model for the whole setup and find an efficient representation of integral features.
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.
Encapsulant-free N.I.C.E. modules have strong ecological advantages compared to conventional laminated modules but suffer generally from lower electrical performance. Via long-term outdoor monitoring of fullsize industrial modules of both types with identical solar cells, we investigated if the performance difference remains constant over time and which parameters influence its value. After assessing about a full year’s data, two obvious levers for N.I.C.E. optimization are identified: The usage of textured glass and transparent adhesives on the module rear side. Also, the performance loss could be alleviated using tracking systems due to lower AOI values. Our measurements show additionally that N.I.C.E. module surfaces are in average about 2.5°C cooler compared to laminated modules. With these findings, we lay out a roadmap to reduce today’s LIV gap of about 5%rel by different optimizations.
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
Investigation on Bowtie Antennas Operating at Very Low Frequencies for Ground Penetrating Radar
(2023)
The efficiency of Ground Penetrating Radar (GPR) systems significantly depends on the antenna performance as the signal has to propagate through lossy and inhomogeneous media. GPR antennas should have a low operating frequency for greater penetration depth, high gain and efficiency to increase the receiving power and should be compact and lightweight for ease of GPR surveying. In this paper, two different designs of Bowtie antennas operating at very low frequencies are proposed and analyzed.
A method for evaluating skin cancer detection based on millimeter-wave technologies is presented. For this purpose, the relative permittivities are calculated using the effective medium theory for the benign and cancerous lesion, considering the change in water content between them. These calculated relative permittivities are further used for the simulation and evaluation of skin cancer detection using a substrate-integrated waveguide probe. A difference in the simulated scattering parameters S 11 of up to 13dB between healthy and cancerous skin can be determined in the best-case.
Skin cancer detection proves to be complicated and highly dependent on the examiner’s skills. Millimeter-wave technologies seem to be a promising aid for the detection of skin cancer. The different water content of the skin area affected by cancer compared to healthy skin changes its reflective property. Due to limited available resources on the dielectric properties of skin cancer, especially in comparison to surrounding healthy skin, accurate simulations and evaluations are quite challenging. Therefore, comparing different results for different approaches and starting points can be difficult. In this paper, the Effective Medium Theory is applied to model skin cancer, which provides permittivity values dependent on the water content.
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.