Article
Refine
Document Type
- Article (67) (remove)
Has Fulltext
- yes (67)
Keywords
Institute
- Informatik (14)
- Media (13)
- Gesellschaftswissenschaften (9)
- Elektrotechnik und Informationstechnik (6)
- Mathematik und Naturwissenschaften (6)
- Chemie- und Biotechnologie (5)
- Maschinenbau und Kunststofftechnik (4)
- Soziale Arbeit (3)
- Human-Computer Interaction & Visual Analytics (vis) (2)
- da/sec - Biometrics and Internet Security Research Group (2)
In order to generate a machine learning algorithm (MLA) that can support ophthalmologists with the diagnosis of glaucoma, a carefully selected dataset that is based on clinically confirmed glaucoma patients as well as borderline cases (e.g., patients with suspected glaucoma) is required. The clinical annotation of datasets is usually performed at the expense of the data volume, which results in poorer algorithm performance. This study aimed to evaluate the application of an MLA for the automated classification of physiological optic discs (PODs), glaucomatous optic discs (GODs), and glaucoma-suspected optic discs (GSODs). Annotation of the data to the three groups was based on the diagnosis made in clinical practice by a glaucoma specialist. Color fundus photographs and 14 types of metadata (including visual field testing, retinal nerve fiber layer thickness, and cup–disc ratio) of 1168 eyes from 584 patients (POD = 321, GOD = 336, GSOD = 310) were used for the study. Machine learning (ML) was performed in the first step with the color fundus photographs only and in the second step with the images and metadata. Sensitivity, specificity, and accuracy of the classification of GSOD vs. GOD and POD vs. GOD were evaluated. Classification of GOD vs. GSOD and GOD vs. POD performed in the first step had AUCs of 0.84 and 0.88, respectively. By combining the images and metadata, the AUCs increased to 0.92 and 0.99, respectively. By combining images and metadata, excellent performance of the MLA can be achieved despite having only a small amount of data, thus supporting ophthalmologists with glaucoma diagnosis.
The benefits of ideation for both industry and academia alike have been outlined by countless studies, leading to research into various approaches attempting to add new ideation methods or examine how the quality of the ideas and solutions created can be measured. Although AI-based approaches are being researched, there is no attempt to provide the ideation participants with information that inspire new ideas and solutions in real time. Our proposal presents a novel and intuitive approach that supports users in real time by providing them with relevant information as they conduct ideation. By analyzing their ideas within the respective ideation sessions, our approach recommends items of interest with high contextual similarity to the proposed ideas, allowing users to skim through, for example, publications and inspire new ideas quickly. The recommendations also evolve in real time. As more ideas are written during the ideation session, the recommendations become more precise. This real-time approach is instantiated with various ideation methods as a proof of concept, and various models are evaluated and compared to identify the best model for working with ideas.
The kinetics and mechanism of drug binding to its target are critical to pharmacological efficacy. A high throughput (HTS) screen often results in hundreds of hits, of which usually only simple IC50 values are determined during reconfirmation. However, kinetic parameters such as residence time for reversible inhibitors and the kinact/KI ratio, which is the critical measure for evaluating covalent inactivators, are early predictive measures to assess the chances of success of the hits in the clinic. Using the promising cancer target human histone deacetylase 8 as an example, we present a robust method that calculates concentration-dependent apparent rate constants for the inhibition or inactivation of HDAC8 from dose–response curves recorded after different pre-incubation times. With these data, hit compounds can be classified according to their mechanism of action, and the relevant kinetic parameters can be calculated in a highly parallel fashion. HDAC8 inhibitors with known modes of action were correctly assigned to their mechanism, and the binding mechanisms of some hits from an internal HDAC8 screening campaign were newly determined. The oxonitriles SVE04 and SVE27 were classified as fast reversible HDAC8 inhibitors with moderate time-constant IC50 values of 4.2 and 2.6 µM, respectively. The hit compound TJ-19-24 and SAH03 behave like slow two-step inactivators or reversible inhibitors, with a very low reverse isomerization rate.
Biometric fingerprint identification hinges on the reliability of its sensors; however, calibrating and standardizing these sensors poses significant challenges, particularly in regards to repeatability and data diversity. To tackle these issues, we propose methodologies for fabricating synthetic 3D fingerprint targets, or phantoms, that closely emulate real human fingerprints. These phantoms enable the precise evaluation and validation of fingerprint sensors under controlled and repeatable conditions. Our research employs laser engraving, 3D printing, and CNC machining techniques, utilizing different materials. We assess the phantoms’ fidelity to synthetic fingerprint patterns, intra-class variability, and interoperability across different manufacturing methods. The findings demonstrate that a combination of laser engraving or CNC machining with silicone casting produces finger-like phantoms with high accuracy and consistency for rolled fingerprint recordings. For slap recordings, direct laser engraving of flat silicone targets excels, and in the contactless fingerprint sensor setting, 3D printing and silicone filling provide the most favorable attributes. Our work enables a comprehensive, method-independent comparison of various fabrication methodologies, offering a unique perspective on the strengths and weaknesses of each approach. This facilitates a broader understanding of fingerprint recognition system validation and performance assessment.
We address the need for a large-scale database of children’s faces by using generative adversarial networks (GANs) and face-age progression (FAP) models to synthesize a realistic dataset referred to as “HDA-SynChildFaces”. Hence, we proposed a processing pipeline that initially utilizes StyleGAN3 to sample adult subjects, which is subsequently progressed to children of varying ages using InterFaceGAN. Intra-subject variations, such as facial expression and pose, are created by further manipulating the subjects in their latent space. Additionally, this pipeline allows the even distribution of the races of subjects, allowing the generation of a balanced and fair dataset with respect to race distribution. The resulting HDA-SynChildFaces consists of 1,652 subjects and 188,328 images, each subject being present at various ages and with many different intra-subject variations. We then evaluated the performance of various facial recognition systems on the generated database and compared the results of adults and children at different ages. The study reveals that children consistently perform worse than adults on all tested systems and that the degradation in performance is proportional to age. Additionally, our study uncovers some biases in the recognition systems, with Asian and black subjects and females performing worse than white and Latino-Hispanic subjects and males.
District heating plays a key role in the German heat transition (“Wärmewende”) to achieve climate protection targets. In order to realise the heating transition, the legislator has established cost efficiency as a central criterion in the relevant legislation. Ecology, as the third pillar of sustainability, is thus taking a back seat, despite the transformation’s influence on other sustainability dimensions beyond climate protection.
The article takes an ecological perspective on the district heating
transformation and shows that, from this perspective, greater emphasis
should be placed on local environmental heat and large heat pumps.
In the second step, the decentralised information available on the
actual transformation plans of district heating suppliers is aggregated and evaluated at a national level for the first time. The evaluation indicates a possible gap between the developed sustainable target state and the plans of district heating suppliers, which are primarily focussed on the cost efficiency criterion. This comparison identifies a potential conflict of objectives between the legislative cost efficiency criterion and the ecological sustainability perspective.
In this paper, we present a new processing method, called MOSES—Impacts, for the detection of micrometer-sized damage on glass plate surfaces. It extends existing methods by a separation of damaged areas, called impacts, to support state-of-the-art recycling systems in optimizing their parameters. These recycling systems are used to repair process-related damages on glass plate surfaces, caused by accelerated material fragments, which arise during a laser–matter interaction in a vacuum. Due to a high number of impacts, the presented MOSES—Impacts algorithm focuses on the separation of connected impacts in two-dimensional images. This separation is crucial for the extraction of relevant features such as centers of gravity and radii of impacts, which are used as recycling parameters. The results show that the MOSES—Impacts algorithm effectively separates impacts, achieves a mean agreement with human users of (82.0 ± 2.0)%, and improves the recycling of glass plate surfaces by identifying around 7% of glass plate surface area as being not in need of repair compared to existing methods.
Human histone deacetylase 4 (HDAC4) is a key epigenetic regulator involved in a number of important cellular processes. This makes HDAC4 a promising target for the treatment of several cancers and neurodegenerative diseases, in particular Huntington's disease. HDAC4 is highly regulated by phosphorylation and oxidation, which determine its nuclear or cytosolic localization, and exerts its function through multiple interactions with other proteins, forming multiprotein complexes of varying composition. The catalytic domain of HDAC4 is known to interact with the SMRT/NCOR corepressor complex when the structural zinc-binding domain (sZBD) is intact and forms a closed conformation. Crystal structures of the HDAC4 catalytic domain have been reported showing an open conformation of HDAC4 when bound to certain ligands. Here, we investigated the relevance of this HDAC4 conformation under physiological conditions in solution. We show that proper zinc chelation in the sZBD is essential for enzyme function. Loss of the structural zinc ion not only leads to a massive decrease in enzyme activity, but it also has serious consequences for the overall structural integrity and stability of the protein. However, the Zn2+ free HDAC4 structure in solution is incompatible with the open conformation. In solution, the open conformation of HDAC4 was also not observed in the presence of a variety of structurally divergent ligands. This suggests that the open conformation of HDAC4 cannot be induced in solution, and therefore cannot be exploited for the development of HDAC4-specific inhibitors.
The development of compact neutron sources for applications is extensive and features many approaches. For ion-based approaches, several projects with different parameters exist. This article focuses on ion-based neutron production below the spallation barrier for proton and deuteron beams with arbitrary energy distributions with kinetic energies from 3 MeV to 97 MeV. This model makes it possible to compare different ion-based neutron source concepts against each other quickly. This contribution derives a predictive model using Monte Carlo simulations (an order of 50,000 simulations) and deep neural networks. It is the first time a model of this kind has been developed. With this model, lengthy Monte Carlo simulations, which individually take a long time to complete, can be circumvented. A prediction of neutron spectra then takes some milliseconds, which enables fast optimization and comparison. The models’ shortcomings for low-energy neutrons (<0.1 MeV
) and the cut-off prediction uncertainty (±3 MeV
) are addressed, and mitigation strategies are proposed.
A growing body of literature mainly in the context of consumer research indicates that the formal-aesthetic and conceptual design of objects can influence users' thoughts, emotions and even behavioural patterns. While there is strong evidence regarding these effects on actual purchasing decisions, evidence on the effect of aesthetic design features (e.g., haptics, colour) on health-related mental concepts and intentions for health behaviour change is scarce. Based on insights from material and conceptual priming, this article illustrates the research-driven and evidence-based design process of two design primes and comprises pre-tests and an experiment in two settings on the effect of design on health behaviour focusing i.a. on intention for health behaviour change. In an evidence-based and research-driven process, two lecterns were designed to work as primes, i.e., to have a positive vs. negative influence on several mental constructs (sense of control, sense of coherence, resiliency, self-efficacy) and health-related intention. The lecterns differed mainly in terms of aesthetic appearance (e.g., material, colour, proportion, steadiness). They were tested in (a.) a university setting with students (n = 83) and (b.) a clinical setting with orthopaedic rehabilitation patients (n = 38). Participants were asked to perform an unrelated task (evaluation of an unrelated product) while standing at and using the lecterns. Overall, t-tests and Mann-Whitney-U tests show no significant differences but differing tendencies in a mentioning task. When asked to name health-promoting activities, in the clinical setting, participants using the "positive" prime (i.e., the steady lectern, n = 13) mentioned more sport-related aspects on average and a higher portion of sport-related aspects of their answers than participants using the "negative" prime (n = 11). In the university setting (positive: n = 36; negative n = 38), no such differences emerged. This finding gives reason to believe that the prime might be specifically effective in the clinical setting as it relates to physical activity being the most relevant topic of the patients' pathology.