Wiss. Zeitschriftenartikel reviewed: Sonstiger Nachweis des Review-Verfahrens
Refine
Document Type
- Article (reviewed) (34)
Is part of the Bibliography
- yes (34)
Keywords
- 3D printing (2)
- CPC (2)
- Machine Learning (2)
- 3D-Visualisierung (1)
- AANET (1)
- AI applications (1)
- AI prototype (1)
- Aircraft Ad-Hoc Network (1)
- Archiv für Kriminologie (1)
- Artificial Intelligence (1)
Institute
- Fakultät Maschinenbau und Verfahrenstechnik (M+V) (11)
- Fakultät Elektrotechnik, Medizintechnik und Informatik (EMI) (ab 04/2019) (9)
- Fakultät Medien (M) (ab 22.04.2021) (8)
- Fakultät Wirtschaft (W) (6)
- IMLA - Institute for Machine Learning and Analytics (4)
- INES - Institut für nachhaltige Energiesysteme (4)
- POIM - Peter Osypka Institute of Medical Engineering (4)
- CRT - Campus Research & Transfer (1)
- IBMS - Institute for Advanced Biomechanics and Motion Studies (ab 16.11.2022) (1)
Aircraft ad hoc networks simplify airplane-to-airplane or airplane-to-service station communication. It evolved from MANET and VANET ad-hoc networks. MANET connects mobile networks and VANET for cars. Adhoc networks are popular because they can be built without routers or access points when no network exists. Flights are self-organizing nodes in AANET. This dynamic network requires only two nodes and no specific infrastructure. This method is important for GPS navigation, aircraft–ship communications, and navy signaling. These Ad Hoc networks let aircraft interact with the grounds and service stations to decrease traffic between aircraft. It can also connect with a network radar aircraft to avoid collisions. Planes ad-hoc networks connect planes spontaneously. It is versatile and simple. The aircraft adapts to the situation to make connections; thus, routers or networks are unnecessary. Planes’ fast mobility accelerates network evolution. No infrastructure is needed for aircraft to transmit and relay data. AANET optimizes performance despite restricted bandwidth, power, and processing. This paper describes the AANET network and the recommended solutions to improve airplane performance. It also covers existing methodologies, benefits and cons, and various scholars’ work on the AANET.
VisualTorch is a library designed for visualizing neural network architectures in PyTorch. It offers support for multiple visualization styles, such as layered-style, graph-style, and the newly added LeNet-like visualization. When provided with a sequential or custom PyTorch model, alongside the input shape and visualization specifications, VisualTorch automatically translates the model structure into an architectural diagram. The resulting diagram can be refined using various configurations, including style, color, opacity, size, and a legend. VisualTorch is particularly valuable for projects involving PyTorch-based neural networks. By facilitating the generation of graphics with a single function call, it streamlines the process of visualizing neural network architectures. This ensures that the produced results are suitable for publication with minimal additional modifications. Moreover, owing to its diverse customization options, VisualTorch empowers users to generate polished figures suitable for publication.
Die Herstellung von Kochschinken bringt einige Herausforderungen mit sich. Für die Produktion werden Fleischteile mithilfe von Salzlake in einem mehrstufigen Pökel- und Garprozess verarbeitet. Dabei kann es zu Qualitätsschwankungen kommen, die auf Strukturfehler im Fleisch zurückzuführen sind. Das Resultat: Die Salzlake wird nicht optimal aufgenommen. Ein auf historischen Daten trainiertes KI-Modell soll das Problem lösen.
AbstractAccurate and automatic assessments of body segment kinematics via wearable sensors are essential to provide new insights into the complex interactions between active lifestyle and fall risk in various populations. To remotely assess near-falls due to balance disturbances in daily life, current approaches primarily rely on biased questionnaires, while contemporary data-driven research focuses on preliminary fall-related scenarios. Here, we worked on an automated framework based on accurate trunk kinematics, enabling the detection of near-fall scenarios during locomotion. Using a wearable inertial measurement cluster in conjunction with evaluation algorithms focusing on trunk angular acceleration, the proposed sensor-framework approach revealed accurate distinguishment of balance disturbances related to trips and slips, thereby minimising false detections during activities of daily living. An important factor contributing to the framework’s high sensitivity and specificity for automatic detection of near-falls was the consideration of the individual’s gait characteristics. Therefore, the sensor-framework presents an opportunity to substantially impact remote fall risk assessment in healthy and pathological conditions outside the laboratory.
OBJECTIVE: To compare knee abduction moment (KAM) magnitudes between a generic 180° pivot turn (modified 505 change-of-direction test; m505) and a handball-specific sidestep cut, and to assess ranking consistency. Additionally, to examine the resultant ground reaction force (GRF) and its frontal plane moment arm to the knee to comprehend their contributions to KAM.
STUDY DESIGN: Observational laboratory study.
METHODS: High-level female handball players (n = 45) performed the m505 and handball-specific sidestep cut. Resultant GRF, its frontal plane moment arm to the knee, and KAM were obtained and subsequently compared between the tasks. Rank correlation coefficients were employed to assess if variables of both tasks are related.
RESULTS: Peak KAM was similar for the m505 and the sidestep cut (1.79 (0.95 – 3.53) Nm/kg vs. 1.64 (0.34 – 3.60) Nm/kg; rB = .25; p = .14). The ranking of the players' peak KAM differed substantially (rS = 0.26, p = .084), suggesting that different tasks could classify the same player with different injury risk. The m505 generated lower resultant GRF (24 ± 4 N/kg, 95% CI [23, 24] vs. 33 ± 9 N/kg, 95% CI [31, 35]; d = 1.30; p < .001) but longer frontal plane moment arms (7.8 ± 1.8 cm, 95% CI [7.3, 8.4] vs. 5.4 ± 1.5 cm, 95% CI: [5.0, 5.8]; d = 1.36; p < .001) than the sidestep cut.
CONCLUSION: A difference in individual ACL injury risk assessment depending on movement type was revealed. While KAM magnitudes were similar across direction-change tasks, player rankings differed. The contributions of resultant GRF and frontal plane moment arms to peak KAM varied between tasks, underscoring the importance of task-specific and individualized injury prevention.
Social media is associated with many positive aspects, such as sharing information and media with friends and relatives worldwide. However, in recent years studies have identified a large number of negative effects in connection with social media. This article presents a systematization of this dark side of social media and provides an overview of the identified dark aspects. Furthermore, the authors outline measures that can be taken to counteract these dark aspects.
Die automatische Extraktion von Produkt- und Fertigungsinformationen (Product Manufacturing Information - PMI) aus technischen CAD-Zeichnungen ist eine Voraussetzung für die Fertigung und Qualitätskontrolle in der Produktion. Aufgrund des speziellen Stils von CAD-Zeichnungen und der begrenzten Verfügbarkeit von Trainings- und Testdaten bleibt die Digitalisierung von CAD-Zeichnungen in Rasterbildern eine Herausforderung für Texterkennungssoftware (Optical Character Recognition - OCR). Dieser Beitrag stellt ein neuartiges, auf Deep Learning basierendes Framework vor, das dieses Problem adressiert, indem es Form- und Lagetoleranzen (Geometrical Dimensioning and Tolerancing - GD&T) sowie Bemaßungen in CAD-Zeichnungen lokalisiert und erkennt. Das Framework besteht aus einem zentralen Lokalisierungsmodul und mehreren nachgelagerten Pipelines für einzelne Klassen von PMI. Die Leistungsfähigkeit des Lokalisierungsmoduls, des Netzwerks zur Zeilenerkennung und der einzelnen Pipelines wird anhand realer Datensätze evaluiert. Ihre Leistung wird mit der des OCR-Programms Tesseract verglichen.
Generative Adversarial Networks (GANs) have earned significant attention in various domains due to their generative model’s compelling ability to generate realistic examples probably drawn from sample distribution. Image security indicates the process of protecting digital images from unauthorized access, modification, or distribution. This requires a guarantee of image privacy, integrity, and authenticity to prohibit them from being exploited by malicious attacks. GANs can also be utilized for improving image security by exploiting its generation ability in encryption, steganography, and privacy-preserving tech-niques. This paper reviews GANs-based image security techniques providing a systematic overview of current literature and comparing the role of GANs in image encryption, image steganography, and priva-cy preserving from multiple dimensions. Additionally, it outlines future research directions to further explore the potential of GANs in addressing privacy and image security concerns.
Sinkende Mitgliederzahlen und knapper werdende finanzielle Ressourcen zwingen die Kirchen in Deutschland, ihre Organisationsstruktur und inhaltliche Ausrichtung zu überprüfen und zu verändern. Dieser Beitrag analysiert am Beispiel der Gemeindeberatung des Strategieprozesses „ekiba 2032“ der Evangelischen Landeskirche in Baden, wie ein organisatorischer und inhaltlicher Transformationsprozess unter Berücksichtigung der Besonderheiten einer Organisation mit internen Beratenden gestaltet werden kann.
Das Gewinnen und Binden von Fachkräften beschäftigt alle Arbeitgeber. Im vorliegenden Beitrag wird ein Benchmarkverfahren vorgestellt das produzierenden Unternehmen die Gelegenheit gibt, bezüglich dieses Themas methodisch strukturiert gemeinsam voneinander zu lernen. Dazu werden die Bewertungsgrundlage für den Benchmark und die Anforderungen an seine Organisation vorgestellt und erläutert. Zum Schluss wird die Anwendung des Benchmarkverfahrens exemplarisch aufgezeigt.