Refine
Year of publication
Document Type
- Conference Proceeding (934)
- Article (reviewed) (559)
- Article (unreviewed) (124)
- Master's Thesis (66)
- Part of a Book (65)
- Contribution to a Periodical (58)
- Book (30)
- Bachelor Thesis (29)
- Patent (29)
- Letter to Editor (28)
Conference Type
- Konferenzartikel (734)
- Konferenz-Abstract (134)
- Sonstiges (34)
- Konferenz-Poster (22)
- Konferenzband (12)
Language
- English (1981) (remove)
Keywords
- RoboCup (32)
- Dünnschichtchromatographie (27)
- COVID-19 (23)
- Export (23)
- Machine Learning (19)
- Gamification (17)
- Kommunikation (15)
- Finite-Elemente-Methode (13)
- Government Measures (13)
- TRIZ (13)
Institute
- Fakultät Maschinenbau und Verfahrenstechnik (M+V) (590)
- Fakultät Elektrotechnik und Informationstechnik (E+I) (bis 03/2019) (501)
- Fakultät Elektrotechnik, Medizintechnik und Informatik (EMI) (ab 04/2019) (373)
- Fakultät Wirtschaft (W) (281)
- INES - Institut für nachhaltige Energiesysteme (167)
- Fakultät Medien und Informationswesen (M+I) (bis 21.04.2021) (157)
- ivESK - Institut für verlässliche Embedded Systems und Kommunikationselektronik (146)
- Fakultät Medien (M) (ab 22.04.2021) (82)
- IMLA - Institute for Machine Learning and Analytics (72)
- ACI - Affective and Cognitive Institute (58)
Open Access
- Open Access (832)
- Closed Access (666)
- Closed (293)
- Bronze (137)
- Gold (75)
- Diamond (67)
- Hybrid (45)
- Grün (12)
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/.
For the treatment of bone defects, biodegradable, compressive biomaterials are needed as replacements that degrade as the bone regenerates. The problem with existing materials has either been their insufficient mechanical strength or the excessive differences in their elastic modulus, leading to stress shielding and eventual failure. In this study, the compressive strength of CPC ceramics (with a layer thickness of more than 12 layers) was compared with sintered β-TCP ceramics. It was assumed that as the number of layers increased, the mechanical strength of 3D-printed scaffolds would increase toward the value of sintered ceramics. In addition, the influence of the needle inner diameter on the mechanical strength was investigated. Circular scaffolds with 20, 25, 30, and 45 layers were 3D printed using a 3D bioplotter, solidified in a water-saturated atmosphere for 3 days, and then tested for compressive strength together with a β-TCP sintered ceramic using a Zwick universal testing machine. The 3D-printed scaffolds had a compressive strength of 41.56 ± 7.12 MPa, which was significantly higher than that of the sintered ceramic (24.16 ± 4.44 MPa). The 3D-printed scaffolds with round geometry reached or exceeded the upper limit of the compressive strength of cancellous bone toward substantia compacta. In addition, CPC scaffolds exhibited more bone-like compressibility than the comparable β-TCP sintered ceramic, demonstrating that the mechanical properties of CPC scaffolds are more similar to bone than sintered β-TCP ceramics.
Differentiation between human and non-human objects can increase efficiency of human-robot collaborative applications. This paper proposes to use convolutional neural networks for classifying objects in robotic applications. The body temperature of human beings is used to classify humans and to estimate the distance to the sensor. Using image classification with convolutional neural networks it is possible to detect humans in the surroundings of a robot up to five meters distance with low-cost and low-weight thermal cameras. Using transfer learning technique we trained the GoogLeNet and MobilenetV2. Results show accuracies of 99.48 % and 99.06 % respectively.
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.
Following their success in visual recognition tasks, Vision Transformers(ViTs) are being increasingly employed for image restoration. As a few recent works claim that ViTs for image classification also have better robustness properties, we investigate whether the improved adversarial robustness of ViTs extends to image restoration. We consider the recently proposed Restormer model, as well as NAFNet and the "Baseline network" which are both simplified versions of a Restormer. We use Projected Gradient Descent (PGD) and CosPGD for our robustness evaluation. Our experiments are performed on real-world images from the GoPro dataset for image deblurring. Our analysis indicates that contrary to as advocated by ViTs in image classification works, these models are highly susceptible to adversarial attacks. We attempt to find an easy fix and improve their robustness through adversarial training. While this yields a significant increase in robustness for Restormer, results on other networks are less promising. Interestingly, we find that the design choices in NAFNet and Baselines, which were based on iid performance, and not on robust generalization, seem to be at odds with the model robustness.
The identification of vulnerabilities is an important element in the software development life cycle to ensure the security of software. While vulnerability identification based on the source code is a well studied field, the identification of vulnerabilities on basis of a binary executable without the corresponding source code is more challenging. Recent research [1] has shown how such detection can generally be enabled by deep learning methods, but appears to be very limited regarding the overall amount of detected vulnerabilities. We analyse to what extent we could cover the identification of a larger variety of vulnerabilities. Therefore, a supervised deep learning approach using recurrent neural networks for the application of vulnerability detection based on binary executables is used. The underlying basis is a dataset with 50,651 samples of vulnerable code in the form of a standardised LLVM Intermediate Representation. Te vectorised features of a Word2Vec model are used to train different variations of three basic architectures of recurrent neural networks (GRU, LSTM, SRNN). A binary classification was established for detecting the presence of an arbitrary vulnerability, and a multi-class model was trained for the identification of the exact vulnerability, which achieved an out-of-sample accuracy of 88% and 77%, respectively. Differences in the detection of different vulnerabilities were also observed, with non-vulnerable samples being detected with a particularly high precision of over 98%. Thus, our proposed technical approach and methodology enables an accurate detection of 23 (compared to 4 [1]) vulnerabilities.
The importance of machine learning (ML) has been increasing dramatically for years. From assistance systems to production optimisation to healthcare support, almost every area of daily life and industry is coming into contact with machine learning. Besides all the benefits ML brings, the lack of transparency and difficulty in creating traceability pose major risks. While solutions exist to make the training of machine learning models more transparent, traceability is still a major challenge. Ensuring the identity of a model is another challenge, as unnoticed modification of a model is also a danger when using ML. This paper proposes to create an ML Birth Certificate and 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.
Automation devices or automation stations (AS) take on the task of controlling, regulating, monitoring and, if necessary, optimising building systems and their system components (e.g. pumps, compressors, fans) based on recorded process variables. For this purpose, a wide range of control and regulation methods are used, starting with simple on/off controllers, through classic PID controllers, to higher-order controllers such as adaptive, model-predictive, knowledge-based or adaptive controllers.
Starting with a brief introduction to automation technology (Sect. 7.1), the chapter goes into the structure and functionality of the usual compact controllers using the application examples of solar thermal systems and heat pump systems (Sect. 7.2). Finally, the integration of system automation into a higher-level building automation system and into the building management system is described using specific application examples (Sect. 7.3).
This central book chapter now details the implementation of automation of solar domestic hot water systems, solar assisted building heating, rooms, solar cooling systems, heat pump heating systems, geothermal systems and thermally activated building component systems. Hydraulic and automation diagrams are used to explain how the automation of these systems works. A detailed insight into the engineering and technical interrelationships involved in the use of these systems, as well as the use of simulation tools, enables effective control and regulation. System characteristic curves and systematic procedures support the automation engineer in his tasks.
Renewable energy sources such as solar radiation, geothermal heat and ambient heat are available for energy conversion. With the help of special converters, these resources can be put to use. These include solar collectors, geothermal probes and chillers. They collect the energy and convert it to a temperature level high enough to be suitable for heat purposes. In the case of refrigeration machines, a distinction is made between electrically and thermally driven machines.
The use of renewable energy sources for heating and cooling in buildings today offers the best opportunities to avoid the use of fossil fuels and the associated climate-damaging emissions. However, unlike fossil fuels, renewable energy sources such as solar radiation are not available at the push of a button, but occur uncontrollably depending on weather conditions, the location of the building and the time of year. Their use is free of charge. However, complex converters and systems usually have to be installed in order to use them. These must be carefully planned and operated in order to avoid unnecessary costs and to generate the maximum possible yield. The regenerative energy systems are usually integrated into existing conventional systems. When designing the control and regulation equipment, it is crucial to design the automation of the systems in such a way that primarily renewable energy sources are used and the share of fossil energy sources is minimized.
This textbook helps use regenerative systems for heating and cooling effectively. Integration and automation schemes provide a quick overview. Practical examples clearly show standard solutions for the integration of regenerative energy sources. For the 2nd edition, improvements have been made to the text and illustrations, and references to standards have been updated. Control questions at the end of the main chapters serve to consolidate the understanding of the content.
Public educational institutions are increasingly confronted with a decline in the number of applicants, which is why competition between colleges and universities is also intensifying. For this reason, it is important to position oneself as an institution in order to be perceived by the various target groups and to differentiate oneself from the competition. In this context, the brand and thus its perception and impact play a decisive role, especially in view of the desired communication of the institution's own values and its self-image, the brand identity. To this end, emotions serve as an approach to creating positive stimulation and brand loyalty.
In this study, circular economy (CE) relevance in Germany will be discussed based on LinkedIn readily available data. LinkedIn company profiles located in Germany with ‘circular economy’ in their description or any other field were selected and used as a data source to analyze their CE relation. Overall, 514 German companies were analyzed in reference to the 15 German regions they belong. Most companies are located in the federal state of Berlin (126), followed by North Rhine-Westphalia (96) and Bavaria (77). In terms of the industry sector, they are self-classified to environmental services (64), management consulting (50), renewables & environment (33), research (31), and computer software (18) etc. Regarding their employees with LinkedIn profiles, 22,621 people are affiliated with these companies, ranging from one to 7,877. All examined companies have a total of 819,632 followers on LinkedIn, ranging from none to 88,167. An increase in CE-related companies was recorded in 13 of the 16 federal states of Germany over a one-year period. This work provides essential insights into the increasing relevance and trends of the circular economy in German enterprises and will help conduct further national studies with readily available data from LinkedIn.
Human interaction frequently includes decision-making processes during which interactants call on verbal and non-verbal resources to manage the flow of interaction. In 2017, Stevanovic et al. carried out pioneering work, analyzing the unfolding of moment-by-moment dynamics by investigating the behavioral matching during search and decision-making phases. By studying the similarities in the participant's body sway during a conversation task in Finnish, the authors showed higher behavioral matching during decision phases than during search phases. The purpose of this research was to investigate the whole-body sway and its coordination during joint search and decision-making phases as a replication of the study by Stevanovic et al. (2017) but based on a German population. Overall, 12 dyads participated in this study and were asked to decide on 8 adjectives, starting with a pre-defined letter, to describe a fictional character. During this joint-decision task (duration: 206.46 ± 116.08 s), body sway of both interactants was measured using a 3D motion capture system and center of mass (COM) accelerations were computed. Matching of body sway was calculated using a windowed cross correlation (WCC) of the COM accelerations. A total of 101 search and 101 decision phases were identified for the 12 dyads. Significant higher COM accelerations (5.4*10−3 vs. 3.7*10−3 mm/s2, p < 0.001) and WCC coefficients (0.47 vs. 0.45, p = 0.043) were found during decision-making phases than during search phases. The results suggest that body sway is one of the resources humans use to communicate the arrival at a joint decision. These findings contribute to a better understanding of interpersonal coordination from a human movement science perspective.
Femtosecond (fs) time-resolved magneto-optics is applied to investigate laser-excited ultrafast dynamics of one-dimensional nickel gratings on fused silica and silicon substrates for a wide range of periodicities Λ = 400–1500 nm. Multiple surface acoustic modes with frequencies up to a few tens of GHz are generated. Nanoscale acoustic wavelengths Λ/n have been identified as nth-spatial harmonics of Rayleigh surface acoustic wave (SAW) and surface skimming longitudinal wave (SSLW), with acoustic frequencies and lifetimes being in agreement with theoretical calculations. Resonant magnetoelastic excitation of the ferromagnetic resonance (FMR) by SAW’s third spatial harmonic, and, most interestingly fingerprints of the parametric resonance at 1/2 SAW frequency have been observed. Numerical solutions of Landau–Lifshitz–Gilbert (LLG) equation magnetoelastically driven by complex polychromatic acoustic fields quantitatively reproduce all resonances at once. Thus, our results provide a solid experimental and theoretical base for a quantitative understanding of ultrafast fs-laser-driven magnetoacoustics and tailoring the magnetic-grating-based metasurfaces at the nanoscale.
Sustainable Production
(2023)
Visual programming languages (VPL) let users develop software programs by combining visual program elements, like lists of objects, loops or conditional statements rather than by specifying them textually.
Humanoid robots programming is a very attractive and motivating application domain for students, especially for programming beginners. Humanoid robots are constructed in such a way that they mimic the human body by using actuators that perform like muscles. Typically, a humanoid robot consists of sensors and actuators, i.e. torso, a head, two arms, and two legs, though some humanoid robots may replicate only part of the body, for example, from the waist up. In some cases, humanoid robots are equipped with heads designed to replicate additional human facial features such as eyes. Additional sensors are needed by a robot to gather information about the conditions of the environment to allow the robot to make necessary decisions about its position or certain actions that the situation requires, e.g. an arm movement or an open/close hand action. Other examples for sensor are reflective infrared sensors used to detect objects in proximity.
In this work, we introduce a use-case centered approach based on sensors and actors of a robot and a workflow model to visually describe the sequence of actions including conditional actions or concurrent actions. We provide an in-depth discussion of a new VPL based teaching method for programming humanoid robots based on VPLs. Open research challenges, limits and perspectives for further development of our teaching approach are discussed as well.
Sensors and actuators enable creation of context-aware applications in which applications can discover and take advantage of contextual information, such as user location, nearby people and objects. In this work, we use a general context definition, which can be applied to various devices, e.g., robots and mobile devices. Developing context-based software applications is considered as one of the most challenging application domains due to the sensors and actuators as part of a device. We introduce a new development approach for context-based applications by using use-case descriptions and Visual Programming Languages (VPL). The introduction of web-based VPLs, such as Scratch and Snap, has reinvigorated the usefulness of VPLs. We provide an in-depth discussion of our new VPL based method, a step by step development process to enable development of context-based applications. Two case studies illustrate how to apply our approach to different problem domains: Context-based mobile apps and context-based humanoid robot applications.
The main advantage of mobile context-aware applications is to provide effective and tailored services by considering the environmental context, such as location, time, nearby objects and other data, and adapting their functionality according to the changing situations in the context information without explicit user interaction. The idea behind Location-Based Services (LBS) and Object-Based Services (OBS) is to offer fully-customizable services for user needs according to the location or the objects in a mobile user's vicinity. However, developing mobile context-aware software applications is considered as one of the most challenging application domains due to the built-in sensors as part of a mobile device. Visual Programming Languages (VPL) and hybrid visual programming languages are considered to be innovative approaches to address the inherent complexity of developing programs. The key contribution of our new development approach for location and object-based mobile applications is a use case driven development approach based on use case templates and visual code templates to enable even programming beginners to create context-aware mobile applications. An example of the use of the development approach is presented and open research challenges and perspectives for further development of our approach are formulated.
Background/Purpose
Several methods are used to evaluate the outcome of total hip arthroplasty (THA), however, their relationship at different time points after surgery is unclear. The purpose of this exploratory study was to investigate correlations between self-report function, performance-based tests (PBTs) and biomechanical parameters in patients 12 months after THA.
Methods
Eleven patients were included in this preliminary cross-sectional study. Hip disability and Osteoarthritis Outcome Score (HOOS) was completed for self-reported function. As PBTs, the Timed-up-and-Go test (TUG) and 30-Second-Chair-Stand test (30CST) were used. Biomechanical parameters were derived from analyses of hip strength, gait and balance. Potential correlations were calculated using Spearman correlation coefficient r.
Results
HOOS scores and parameters of PBTs showed moderate to strong correlations (0.3 < r < 0.7). Correlation analysis between HOOS scores and biomechanical parameters revealed moderate to strong correlations for hip strength whereas correlations with gait parameters and balance were rather weak (r < 0.3). Moderate to strong correlations were also found between parameters of hip strength and 30CST.
Conclusion
For THA outcome assessment 12 months after surgery, our first results indicate that self-report measures or PBTs could be used. Analysis of hip strength also appears to be reflected in HOOS and PBT parameters and may be considered as an adjunct. Given the weak correlations with gait and balance parameters, we suggest that gait analysis and balance testing should be performed in addition to PROMs and PBTs as they may provide supplementary information, especially for THA patients that are at risk for falls.
Due to globalization and the resulting increase in competition on the market, products must be produced more and more cheaply, especially in series production, because buyers expect new variants or even completely new products in ever shorter cycles. Injection molding is the most important production process for manufacturing plastic components in large quantities. However, the conventional production of a mold is extremely time-consuming and costly, which creates a contradiction to the fast pace of the market. Additive tooling is an area of application of additive manufacturing, which in the field of injection molding is preferably used for the prototype production of mold inserts. This allows injection molding tools to be produced faster and more cheaply than through the subtractive manufacturing of metal tools. Material Jetting processes using polymers (MJT-UV/P), also called Polyjet Modeling (PJM), have a great potential for use in additive tooling. Due to the poorer mechanical and thermal properties compared to conventional mold insert materials, e.g. steel or aluminum, the previously used design principles cannot be applied. Accordingly, new design guidelines are necessary, which are developed in this paper. The necessary information is obtained with the help of a systematic literature research. The design guidelines are mapped in a uniform design guide, which is structured according to the design process of injection molds. The guidelines do not only refer to the constructive design of the injection mold or the polymer mold insert, but to the entire design process and describe the four phases of planning, conception, development and realization. Particular attention is paid to the special geometric designs of a polymer mold insert and the thermomechanical properties of the mold insert materials. As a result, design guidelines are available that are adapted to the special requirements of additive tooling of molds inserts made of plastics for injection molding.
The increasing diffusion of rapidly developing AI technologies led to the idea of the experiment to combine TRIZ-based automated idea generation with the natural language processing tool ChatGPT, using the chatbot to interpret the automatically generated elementary solution principles. The article explores the opportunities and benefits of a novel AI-enhanced approach to teaching systematic innovation, analyses the learning experience, identifies the factors that affect students' innovation and problem-solving performance, and highlights the main difficulties students face, especially in interdisciplinary problems.
Inner Congo
(2023)
This research-creation project, part of the DE\GLOBALIZE artistic research cycle presented at the #IFM2022 Conference, investigates the complexities of Congo violence, care, and colonialism. Drawing on Michel Serres' metaphor of the great estuaries, the study explores the topology of interactive documentaries, blending theory, emotion, and personal experiences. Accessible through the interactive web documentation at http://deglobalize.com, the platform offers a media-archaeological archive for speculative ethnography, enabling the forensic processing of single documents in line with actor-network theory.
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.
Artificial Intelligence (AI) can potentially transform many aspects of modern society in various ways, including automation of tasks, personalization of products and services, diagnosis of diseases and their treatment, transportation, safety, and security in public spaces, etc. Recently, AI technology has been transforming the financial industry, offering new ways to analyse data and automate processes, reduce costs, increase efficiency, and provide more personalized services to customers. However, it also raised important ethical and regulatory questions that need to be addressed by the industry and society as a whole. The aim of the Erasmus+ project Transversal Skills in Applied Artificial Intelligence - TSAAI (KA220-HED - Cooperation Partnerships in higher education) has been to establish a training platform that will incorporate teaching guidelines based on a curriculum covering different areas of application of AI technology. In this work, we will focus on applying AI models in the financial and insurance sectors.
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.
A smart energy concept was designed and implemented for a cluster of 5 existing multi-family houses, which combines heat pumps, photovoltaic (PV) modules and combined heat and power units (CHP) to achieve energy- and cost-efficient operation. Measurement results of the first year of operation show that the local power generation by PV modules and CHP unit has a positive effect on the electrical self-sufficiency by reducing electricity import from the grid. In winter, when the CHP unit operates continuously for long periods, the entire electricity for the heat pump and 91 % of the total electricity demand of the neighborhood are supplied locally. In summer, only 53 % is generated within the neighborhood. The use of a specifically developed energy management system EMS is intended to further increase this share. CO2 emissions for heating and electricity of the neighborhood are evaluated and amount to 18.4 kg/(m2a). Compared to the previous energy system consisting of gas boilers (29.1 kg/(m2a)), savings of 37 % are achieved with electricity consumption from the grid being reduced by 65 %. In the second construction stage, an additional heat pump, CHP unit and PV modules will be added. The measurement results indicate that the final district energy system is likely to achieve the ambitious CO2 reduction goal of -50% and further increase the self-sufficiency of the district.
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.
Enhancing engineering creativity with automated formulation of elementary solution principles
(2023)
The paper describes a method for the automated formulation of elementary creative stimuli for product or process design at different levels of abstraction and in different engineering domains. The experimental study evaluates the impact of structured automated idea generation on inventive thinking in engineering design and compares it with previous experimental studies in educational and industrial settings. The outlook highlights the benefits of using automated ideation in the context of AI-assisted invention and innovation.
This book constitutes the proceedings of the 23rd International TRIZ Future Conference on Towards AI-Aided Invention and Innovation, TFC 2023, which was held in Offenburg, Germany, during September 12–14, 2023. The event was sponsored by IFIP WG 5.4.
The 43 full papers presented in this book were carefully reviewed and selected from 80 submissions. The papers are divided into the following topical sections: AI and TRIZ; sustainable development; general vision of TRIZ; TRIZ impact in society; and TRIZ case studies.
Eco-innovations in chemical processes should be designed to use raw materials, energy and water as efficiently and economically as possible to avoid the generation of hazardous waste and to conserve raw material reserves. Applying inventive principles identified in natural systems to chemical process design can help avoid secondary problems. However, the selection of nature-inspired principles to improve technological or environmental problems is very time-consuming. In addition, it is necessary to match the strongest principles with the problems to be solved. Therefore, the research paper proposes a classification and assignment of nature-inspired inventive principles to eco-parameters, eco-engineering contradictions and eco-innovation domains, taking into account environmental, technological and economic requirements. This classification will help to identify suitable principles quickly and also to realize rapid innovation. In addition, to validate the proposed classification approach, the study is illustrated with the application of nature-inspired invention principles for the development of a sustainable process design for the extraction of high-purity silicon dioxide from pyrophyllite ores. Finally, the paper defines a future research agenda in the field of nature-inspired eco-engineering in the context of AI-assisted invention and innovation.
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.
Optimization of energetic refurbishment roadmaps for multi-family buildings utilizing heat pumps
(2023)
A novel methodology for calculating optimized refurbishment roadmaps is developed in this paper. The aim of the roadmaps is to determine when and how should which component of the building envelope and heat generation system be refurbished to achieve the lowest net present value. The integrated optimization approach couples a particle swarm optimization algorithm with a dynamic building simulation of the building envelope and the heat supply system. Due to a free selection of implementation times and refurbishment depth, the optimization method achieves the lowest net present value and high CO2 reduction and is therefore an important contribution to achieve climate neutrality in the building stock.
The method is exemplarily applied to a multi-family house built in 1970. In comparison to a standard refurbishment roadmap, cost savings of 6–16 % and CO2 savings of 6–59 % are possible. The sensitivity of the refurbishment roadmap measures is analyzed on the basis of a parametric analysis. Robust optimization results are obtained with a mean refurbishment level of approx. 50 kWh/m2/a of the building envelope. The preferred heat generation system is a bivalent brine-heat pump system with a share of 70 % of the heat load being covered by the electric heat pump.
Heat pumps play a central role in decarbonizing the heat supply of buildings. However, in this article, implementing heat pumps in existing buildings, a significant challenge is still presented due to high temperature requirements. In this article, a systematic analysis of the effects of heat source temperatures, maximum heat pump condenser temperatures, and system temperatures on the seasonal performance of heat pump (HP) systems is presented. The quantitative performance analysis encompasses over 50 heat pumps installed in residential buildings, revealing correlations between the building characteristics, observed temperatures, and heat pump type. The performance of an HP system retrofitted to a 30-dwelling multifamily building is presented in more detail. The bivalent HP system combines air and ground as heat sources and achieves a seasonal performance factor of 3.25 with a share of the gas boiler of 27% in its first year of operation. In these findings, the technical feasibility of retrofitting heat pumps is demonstrated in existing buildings and insights are provided into overcoming the challenges associated with high temperature requirements.
Lithium-ion batteries exhibit slow voltage dynamics on the minute time scale that are usually associated with transport processes. We present a novel modelling approach toward these dynamics by combining physical and data-driven models into a Grey-box model. We use neural networks, in particular neural ordinary differential equations. The physical structure of the Grey-box model is borrowed from the Fickian diffusion law, where the transport domain is discretized using finite volumes. Within this physical structure, unknown parameters (diffusion coefficient, diffusion length, discretization) and dependencies (state of charge, lithium concentration) are replaced by neural networks and learnable parameters. We perform model-to-model comparisons, using as training data (a) a Fickian diffusion process, (b) a Warburg element, and (c) a resistor-capacitor circuit. Voltage dynamics during constant-current operation and pulse tests as well as electrochemical impedance spectra are simulated. The slow dynamics of all three physical models in the order of ten to 30 min are well captured by the Grey-box model, demonstrating the flexibility of the present approach.
A novel peptidyl-lys metalloendopeptidase (Tc-LysN) from Tramates coccinea was recombinantly expressed in Komagataella phaffii using the native pro-protein sequence. The peptidase was secreted into the culture broth as zymogen (~38 kDa) and mature enzyme (~19.8 kDa) simultaneously. The mature Tc-LysN was purified to homogeneity with a single step anion-exchange chromatography at pH 7.2. N-terminal sequencing using TMTpro Zero and mass spectrometry of the mature Tc-LysN indicated that the pro-peptide was cleaved between the amino acid positions 184 and 185 at the Kex2 cleavage site present in the native pro-protein sequence. The pH optimum of Tc-LysN was determined to be 5.0 while it maintained ≥60% activity between pH values 4.5—7.5 and ≥30% activity between pH values 8.5—10.0, indicating its broad applicability. The temperature maximum of Tc-LysN was determined to be 60 °C. After 18 h of incubation at 80 °C, Tc-LysN still retained ~20% activity. Organic solvents such as methanol and acetonitrile, at concentrations as high as 40% (v/v), were found to enhance Tc-LysN’s activity up to ~100% and ~50%, respectively. Tc-LysN’s thermostability, ability to withstand up to 8 M urea, tolerance to high concentrations of organic solvents, and an acidic pH optimum make it a viable candidate to be employed in proteomics workflows in which alkaline conditions might pose a challenge. The nano-LC-MS/MS analysis revealed bovine serum albumin (BSA)’s sequence coverage of 84% using Tc-LysN which was comparable to the sequence coverage of 90% by trypsin peptides.
Currently, immersive technologies are enjoying great popularity. This trend is reflected in technological advances and the emergence of new products for the mass market, such as augmented reality glasses. The range of applications for immersive technologies is growing with more efficient and affordable technologies and student adoption. Especially in education, the use will improve existing learning methods. Immersive application use visual, audio and haptic sensors to fully engage the user in a virtual environment. This impression is reinforced with the help of realistic visualizations and the opportunity for interaction. In particular, Augmented reality is characterized by a high degree of integration between reality and the inserted virtual objects. An augmented interactive simulation for the determination of the specific charge of an electron will be used as an example to demonstrate how such immersion can be created for users. A virtual Helmholtz coil is used to measure and calculate the e/m constant. The voltage at the cathode for generating the electron beam, but also the voltage of the homogeneous magnetic field for deflecting the electron beam, can be variably controlled by haptic user input. Based on these voltages, an immersive virtual electron beam is calculated and visualized. In this paper, the authors present the conceptual steps of this immersive application and address the challenges associated with designing and developing an augmented and interactive simulation.
Redesigning a curriculum for teaching media technology is a major challenge. Up-to-date teaching and learning concepts are necessary that meet the constant technological progress and prepare students specifically for their professional life. Teaching and studying should be characterized by a student-oriented teaching and learning culture. In order to achieve this goal, consistent evaluation is essential. The aim of the evaluation concept presented here is to generate structured information regarding the quality of content-related, didactic and organizational aspects of teaching. The exchange of opinions between students and lecturers should be encouraged in order to continuously improve the teaching and learning processes.
The paper will focus on the activities of the International Year of Light and Optical Technologies 2015 (IYL) with their impact in life, science, art, culture, education and outreach as well as the importance in promoting the objectives for sustainable development. It describes our activities carried out in the run-up to or during the IYL, as well as reports on the generic projects that led to the success of the IYL. The success of the IYL is illustrated by examples and statistics. Relating to the potential and success of the IYL, the impact and the genesis of the International Day of Light (IDL) is presented. Impressions from the opening ceremony of the IYL in Paris at UNESCO headquarters and the Inaugural Ceremony of the IDL will then be covered. A second focus is placed on the interdisciplinary media projects realized by the students of our university dedicated to these events. Finally, an analysis of the impact and legacy of IYL and IDL will be presented.
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 paper presents a system that uses a multi-stage AI analysis method for determining the condition and status of bicycle paths using machine learning methods. The approach for analyzing bicycle paths includes three stages of analysis: detection of the road surface, investigation of the condition of the bicycle paths, and identification of substrate characteristics. In this study, we focus on the first stage of the analysis. This approach employs a low-threshold data collection method using smartphone-generated video data for image recognition, in order to automatically capture and classify surface condition and status.
For the analysis convolutional neural networks (CNN) are employed. CNNs have proven to be effective in image recognition tasks and are particularly well-suited for analyzing the surface condition of bicycle paths, as they can identify patterns and features in images. By training the CNN on a large dataset of images with known surface conditions, the network can learn to identify common features and patterns and reliably classify them.
The results of the analysis are then displayed on digital maps and can be utilized in areas such as bicycle logistics, route planning, and maintenance. This can improve safety and comfort for cyclists while promoting cycling as a mode of transportation. It can also assist authorities in maintaining and optimizing bicycle paths, leading to more sustainable and efficient transportation system.
In this paper we present the concept of the "KI-Labor Südbaden" to support regional companies in the use of AI technologies. The approach is based on the "Periodic Table of AI" and is extended with both new dimensions for sustainability, and the impact of AI on the working environment. It is illustrated on the basis of three real-world use cases: 1. The detection of humans with lowresolution infrared (IR) images for collaborative robotics; 2. The use of machine data from specifically designed vehicles; 3. State-of-the-art Large Language Models (LLMs) applied to internal company documents. We explain the use cases, thereby demonstrating how to apply the Periodic Table of AI to structure AI applications.
This article presents the development, parameterization, and experimental validation of a pseudo-three-dimensional (P3D) multiphysics aging model of a 500 mAh high-energy lithium-ion pouch cell with graphite negative electrode and lithium nickel manganese cobalt oxide (NMC) positive electrode. This model includes electrochemical reactions for solid electrolyte interphase (SEI) formation at the graphite negative electrode, lithium plating, and SEI formation on plated lithium. The thermodynamics of the aging reactions are modeled depending on temperature and ion concentration and the reactions kinetics are described with an Arrhenius-type rate law. Good agreement of model predictions with galvanostatic charge/discharge measurements and electrochemical impedance spectroscopy is observed over a wide range of operating conditions. The model allows to quantify capacity loss due to cycling near beginning-of-life as function of operating conditions and the visualization of aging colormaps as function of both temperature and C-rate (0.05 to 2 C charge and discharge, −20 °C to 60 °C). The model predictions are also qualitatively verified through voltage relaxation, cell expansion and cell cycling measurements. Based on this full model, six different aging indicators for determination of the limits of fast charging are derived from post-processing simulations of a reduced, pseudo-two-dimensional isothermal model without aging mechanisms. The most successful aging indicator, compared to results from the full model, is based on combined lithium plating and SEI kinetics calculated from battery states available in the reduced model. This methodology is applicable to standard pseudo-two-dimensional models available today both commercially and as open source.
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.
Landing heel first has been associated with elevated external knee abduction moments (KAM), thereby potentially increasing the risk of sustaining a non-contact ACL injury. Apart from the foot strike angle, knee valgus angle (VAL) and vertical center of mass velocity at initial ground contact (IC) have been associated with increased KAM in females across different sidestep cuts. While real-time biofeedback training has been proven effective for gait retraining [4], the highly dynamic, non-cyclical nature of cutting maneuvers makes real-time feedback unsuitable and alternative approaches necessary. This study aimed at assessing the efficacy of immediate software-aided feedback on cutting technique in reducing KAM during handball-specific cutting maneuvers.
Die Erfindung betrifft eine Vorrichtung zur biologischen Methanisierung von CO und/oder CO2 mittels methanogener Mikroorganismen durch Umsetzung von H2 und CO und/oder CO2, die eine Begasungskolonne und eine Entgasungskolonne, jeweils mit einer Bodenseite und einer der Bodenseite gegenüberliegenden oberen Seite, ein in der Begasungskolonne und der Entgasungskolonne bereitgestelltes Medium mit methanogenen Mikroorganismen, eine Zuführeinrichtung zum Zuführen eines H2 enthaltenden Gases in das Medium der Begasungskolonne, eine Abführeinrichtung zum Abführen eines CH4 enthaltenden Gases aus der Entgasungskolonne, eine Verbindungsleitung zwischen Begasungskolonne und Entgasungskolonne im Bereich der Bodenseiten, eine Pumpe zum Überführen von Medium über die Verbindungsleitung von der Begasungskolonne in die Entgasungskolonne, und eine Rückführleitung zwischen der Begasungskolonne und der Entgasungskolonne im Bereich der oberen Seiten zum Rückführen von Medium aus der Entgasungskolonne in die Begasungskolonne aufweist. Die Erfindung betrifft auch ein Verfahren zur biologischen Methanisierung von CO und/oder CO2 in einer Vorrichtung mittels methanogener Mikroorganismen als Teil eines in der Vorrichtung bereitgestellten Mediums, wobei das Medium in einem Kreislauf über eine Begasungskolonne und eine Entgasungskolonne geführt wird, wobei die Kolonnen jeweils über eine Verbindungsleitung im Bereich ihrer Bodenseiten und über eine Rückführleitung im Bereich der den Bodenseiten gegenüberliegenden oberen Seiten miteinander verbunden sind, worin das Medium sich in der Begasungskolonne absteigend und in der Entgasungskolonne aufsteigend bewegt, worin dem Medium in der Begasungskolonne ein H2 enthaltendes Gas zugeführt wird.
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.
Phytases are widely used food and feed enzymes to improve phosphate availability and reduce anti-nutritional factors. Despite the benefits, enzyme usage is restricted by the harsh conditions in a gastrointestinal tract (pH 2–6) and feed pelleting conditions at high temperatures (60–90 °C). The commercially available phytase Quantum® Blue has been immobilized as CLEAs using glutardialdehyde and soy protein resulting in a residual activity of 33%. The influence of the precipitating agent, precipitant concentration, cross-linker concentration and cross-linking time, sodium borohydride as well as the proteic feeders gluten, soy protein and bovine serum albumin (BSA) has been optimized. The best conditions were 90% (v/v) ethyl lactate as precipitating reagent, 100 mM glutardialdehyde and a soy protein concentration of 227 mg/L with a cross-linking time of 1 h. The intrinsically stable phytase remained its high thermal stability and temperature optimum. The phytase-CLEA achieved a 425% increase of residual activity under harsh acidic conditions between pH 2.2 and 3.5 compared to the free enzyme. The free and immobilized phytase were deployed in an in vitro assay simulating the acidic conditions in the gizzard of poultry at pH 2. The hydrolysis of phytate was monitored using a novel high-performance thin-layer chromatography (HPTLC) analysis and DAD scanner to study the InsPx fingerprint. All lower inositol phosphate pools (InsP1–InsP6) and free phosphate were separated and analyzed. The phytase-CLEA efficiently released 80% of the total phosphate within 180 min, whereas the free enzyme only released 6% in the same time under the same conditions.
In this work the nonlinear behavior of layered surface acoustic wave (SAW) resonators is studied with the help of finite element (FE) computations. The full calculations depend strongly on the availability of accurate tensor data. While there are accurate material data for linear computations, the complete sets of higher-order material constants, needed for nonlinear simulations, are still not available for relevant materials. To overcome this problem, scaling factors were used for each available nonlinear tensor. The approach here considers piezoelectricity, dielectricity, electrostriction, and elasticity constants up to the fourth order. These factors act as a phenomenological estimate for incomplete tensor data. Since no set of fourth-order material constants for LiTaO3 is available, an isotropic approximation for the fourth-order elastic constants was applied. As a result, it was found that the fourth-order elastic tensor is dominated by one-fourth order Lamé constant. With the help of the FE model, derived in two different, but equivalent ways, we investigate the nonlinear behavior of a SAW resonator with a layered material stack. The focus was set to third-order nonlinearity. Accordingly, the modeling approach is validated using measurements of third-order effects in test resonators. In addition, the acoustic field distribution is analyzed.
Established robot manufacturers have developed methods to determine and optimize the accuracy of their robots. These methods vary from robot manufacturers to their competitors. Due to the lack of published data, a comparison of robot performance is difficult. The aim of this article is to find methods to evaluate important characteristics of a robot with an accurate and cost-effective setup. A laser triangulation sensor and geometric referenced spheres were used as a base to compare the robot performance.
In this contribution, we present a novel 3D printed multi-material, electromagnetic vibration harvester. The harvester is based on a cantilever design and utilizes an embedded constantan wire within a matrix of polyethylene terephthalate glycol (PETG). A prototype has been manufactured with a combination of a fused filament fabrication (FFF) printer and a robot with a custom-made tool.
In the framework of electro-elasticity theory and the finite element method (FEM), a model is set up for the computation of quantities in surface acoustic wave (SAW) devices accounting for nonlinear effects. These include second-order and third-order intermodulations, second and third harmonic generation and the influence of electro-acoustic nonlinearity on the frequency characteristics of SAW resonators. The model is based on perturbation theory, and requires input material constants, e.g., the elastic moduli up to fourth order for all materials involved. The model is two-dimensional, corresponding to an infinite aperture, but all three Cartesian components of the displacement and electrical fields are accounted for. The first version of the model pertains to an infinite periodic arrangement of electrodes. It is subsequently generalized to systems with a finite number of electrodes. For the latter version, a recursive algorithm is presented which is related to the cascading scheme of Plessky and Koskela and strongly reduces computation time and memory requirements. The model is applied to TC-SAW systems with copper electrodes buried in an oxide film on a LiNbO3 substrate. Results of computations are presented for the electrical current due to third-order intermodulations and the displacement field associated with the second harmonic and second-order intermodulations, generated by monochromatic input tones. The scope of this review is limited to methodological aspects with the goal to enable calculations of nonlinear quantities in SAW devices on inexpensive and easily accessible computing platforms.
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.
This thesis deals with the redesign of manufacturing systems by simulation and optimization. Material flow simulation is a common tool for solving problems in system design. Limitations are the high requirements in time and knowledge to execute simulation studies, evaluate results and solve design problems. New chances arrives with the technologies of industry 4.0 and the digital shadow, providing data for simulation. However, the methods to use production data for the redesign of production systems are not available yet. Purpose of this work is providing the methods to automate simulation from digital shadow, use simulation to optimize and solve problems in system design. Two case studies are used to support the action research approach of this work. The result of this work is a framework for the application of the digital shadow in optimization and problem-solving.
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.
Seismic data processing relies on multiples attenuation to improve inversion and interpretation. Radon-based algorithms are often used for multiples and primaries discrimination. Deep learning, based on convolutional neural networks (CNNs), has shown encouraging applications for demultiple that could mitigate Radon-based challenges. In this work, we investigate new strategies to train a CNN for multiples removal based on different loss functions. We propose combined primaries and multiples labels in the loss for training a CNN to predict primaries, multiples, or both simultaneously. Moreover, we investigate two distinctive training methods for all the strategies: UNet based on minimum absolute error (L1) training, and adversarial training (GAN-UNet). We test the trained models with the different strategies and methods on 400 synthetic data. We found that training to predict multiples, including the primaries …
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 this work, we employ a generative solution, since it can explicitly model complex data distributions and hence, yield to a better decision-making process. In particular, we introduce diffusion models for multiple removal. To that end, we run experiments on synthetic and on real data, and we compare the deep diffusion performance with standard 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.
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.
An important step in seismic data processing to improve inversion and interpretation is multiples attenuation. Radon-based algorithms are often used for discriminating primaries and multiples. Recently, deep learning (DL), based on convolutional neural networks (CNNs) has shown promising results in demultiple that could mitigate the challenges of Radon-based methods. In this work, we investigate new different strategies to train a CNN for multiples removal based on different loss functions. We propose combined primaries and multiples labels in the loss for training a CNN to predict primaries, multiples, or both simultaneously. We evaluate the performance of the CNNs trained with the different strategies on 400 clean and noisy synthetic data, considering 3 metrics. We found that training a CNN to predict the multiples and then subtracting them from the input image is the most effective strategy for demultiple. Furthermore, including the primaries labels as a constraint during the training of multiples prediction improves the results. Finally, we test the strategies on a field dataset. The CNNs trained with different strategies report competitive results on real data compared with Radon demultiple. As a result, effectively trained CNN models can potentially replace Radon-based demultiple in existing workflows.
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.
Purpose
This study aims to investigate a systematic approach to the production and use of additively manufactured injection mould inserts in product development (PD) processes. For this purpose, an evaluation of the additive tooling design method (ATDM) is performed.
Design/methodology/approach
The evaluation of the ATDM is conducted within student workshops, where students develop products and validate them using AT-prototypes. The evaluation process includes the analysis of work results as well as the use of questionnaires and participant observation.
Findings
This study shows that the ATDM can be successfully used to assist in producing and using AT mould inserts to produce valid AT prototypes. As a reference for the implementation of AT in industrial PD, extracts from the work of the student project groups and suitable process parameters for prototype production are presented.
Originality/value
This paper presents the application and evaluation of a method to support AT in PD that has not yet been scientifically evaluated.
The paper compares different anti-windup strategies for the current control of inverter-fed permanent magnet synchronous machines (PMSM) controlled by pulse-width modulation. In this respect, the focus is on the drive behavior with a relatively large product of stator frequency and sampling time. A requirement for dynamically high-quality anti-windup measures is, among other things, a sufficiently accurate decoupling of the stator current direct axis and quadrature axis components even at high stator frequencies. Discrete-time models of the electrical subsystem of the PMSM are well suited for this purpose, of which the method found to be the most accurate in a preliminary investigation is used as the basis for all anti-windup methods examined. Simulation studies and measurement results document the performance of the compared methods.
Soiling is an important issue in the renewable energy sector since it can result in significant yield losses, especially in regions with higher pollution or dust levels. To mitigate the impact of soiling on photovoltaic (PV) plants, it is essential to regularly monitor and clean the panels, as well as develop accurate soiling predictions that can affect cleaning strategies and enhance the overall performance of PV power plants. This research focuses on the problem of soiling loss in photovoltaic power plants and the potential to improve the accuracy of soiling predictions. The study examines how soiling can affect the efficiency and productivity of the modules and how to measure and predict soiling using machine learning (ML) algorithms. The research includes analyzing real data from large-scale ground-mounted PV sites and comparing different soiling measurement methods. It was observed that there were some deviations in the real soiling loss values compared to the expected values for some projects in southern Spain, thus, the main goal of this work is to develop machine learning models that could predict the soiling more accurately. The developed models have a low mean square error (MSE), indicating the accuracy and suitability of the models to predict the soiling rates. The study also investigates the impact of different cleaning strategies on the performance of PV power plants and provides a powerful application to predict both the soiling and the number of cleaning cycles.
A report from the World Economic Forum (2019) stated loneliness as the third societal stressor in the world, mainly in western countries. Moreover, research shows that loneliness tends to be experienced more severely by young adults than other age groups (Rokach, 2000), which is the case of university students who face profound periods of loneliness when attending university in a new place (Diehl et al., 2018). Digital technology, especially mental health apps (MHapps), have been viewed as promising solutions to address this distress in universities, however, little evidence on this topic reveals uncertainty around how these resources impact individual well-being. Therefore, this research proposed to investigate how the gamified social mobile app Noneliness reduced loneliness rates and other associated mental health issues of students from a German university. As little work has focused on digital apps targeting loneliness, this project also proposed to describe and discuss the app’s design and development processes. A multimethod approach was adopted: literature review on high-efficacy MHapps design, gamification for mental health and loneliness interventions; User Experience Design and Human-centered Computing. Evaluations occurred according to the app’s development iterations, which assessed four versions (from prototype to Beta) through quantitative and qualitative studies with university students. The main results obtained regarding the design aspects were: users' preference for minimalistic interfaces; importance in maintaining privacy and establishing trust among users; students' willingness to use an online support space for emotional and educational support. Most used features were those related to group discussions, private chats and university social events. Preferred gamification elements were those that provided positive reinforcement to motivate social interactions (e.g. Points, Levels and Achievements). Results of a pilot randomized controlled trial with university students (N = 12), showed no statistically significant interactions in reducing loneliness among experimental group members (n = 7, x² = 3.500, p-value = 0.477, Cramer’s V = 0.27) who made continued use of the app for six weeks. On the other hand, the app showed effects of moderate magnitude on loneliness reduction in this group. The app also demonstrated relatively strong magnitude effects on other associated variables, such as depression and stress in the experimental group. In addition to motivating the conduct of further studies with larger samples, the findings point to a potential app effectiveness not only to reduce loneliness, but also other variables that may be associated with the distress.
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.