Repository der Technischen Hochschule Ingolstadt
Not a member yet
4170 research outputs found
Sort by
Automation Bias in AI-assisted Medical Decision-making under Time Pressure in Computational Pathology
No full textEnergetic Potential of Parallel Operation of Two Heat Sources in a Dual-Source Heat Pump
Full text linkDual-source heat pumps can mitigate disadvantages of single source heat pumps: They have fewer geological requirements compared to ground-source heat pumps while having higher efficiencies compared to air-source heat pumps. Parallel operation of two heat sources can also make electric heaters for peak loads obsolete, leading to economic benefits in the operational costs. Parallel operation has not been analysed thoroughly at different evaporation temperature gradients. To address this gap in research, four possible interconnections of two heat sources were analysed using a refrigerant cycle simulation, two with similar and two with separate evaporation pressures. The energetic potential of each interconnection is evaluated and compared to single source operation with an air-source and a ground-source heat pump. The results showed that only the interconnections with separate evaporation pressure allowed significant reduction in evaporation power from the ground source. As expected, the efficiency – compared to single air-source operation – increased for all parallel interconnections but decreased compared to ground-source operation. Efficient peak load coverage with small ground-source collectors therefore requires a more complex interconnection of completely split evaporator branches at different evaporation pressures. While the efficiency and heating power compared to single ground-source operation decreased slightly (by 4% and 6%, respectively), the power load on the GSHX and ASHX reduced to about 54% and 66% compared to the corresponding single-source operation, respectively. This allows high efficiency at reduced GSHX size and ASHX noise emission. Additionally, this interconnection also allows increased flexibility for improved heat source management
Domain generalization across tumor types, laboratories, and species — Insights from the 2022 edition of the Mitosis Domain Generalization Challenge
Full text linkRecognition of mitotic figures in histologic tumor specimens is highly relevant to patient outcome assessment. This task is challenging for algorithms and human experts alike, with deterioration of algorithmic performance under shifts in image representations. Considerable covariate shifts occur when assessment is performed on different tumor types, images are acquired using different digitization devices, or specimens are produced in different laboratories. This observation motivated the inception of the 2022 challenge on MItosis Domain Generalization (MIDOG 2022). The challenge provided annotated histologic tumor images from six different domains and evaluated the algorithmic approaches for mitotic figure detection provided by nine challenge participants on ten independent domains. Ground truth for mitotic figure detection was established in two ways: a three-expert majority vote and an independent, immunohistochemistry-assisted set of labels. This work represents an overview of the challenge tasks, the algorithmic strategies employed by the participants, and potential factors contributing to their success. With an score of 0.764 for the top-performing team, we summarize that domain generalization across various tumor domains is possible with today’s deep learning-based recognition pipelines. However, we also found that domain characteristics not present in the training set (feline as new species, spindle cell shape as new morphology and a new scanner) led to small but significant decreases in performance. When assessed against the immunohistochemistry-assisted reference standard, all methods resulted in reduced recall scores, with only minor changes in the order of participants in the ranking
Nudging when the descriptive norm is low: Evidence from a carbon offsetting field experiment
No full textInnovationsmanagement zwischen Exploration und Exploitation
No full textUnternehmen sollen im Innovationsmanagement sowohl neue Möglichkeiten durch die Entwicklung bisher noch nicht bekannten Wissens aufdecken (Exploration), aber auch vorhandene Möglichkeiten durch die Nutzung bestehenden Wissens ausschöpfen (Exploitation).
In diesem Working Paper wird eine kritische Analyse von Exploration und Exploitation im Zusammenhang mit Innovationen vorgenommen. Nach der Einführung in die theoretischen Grundlagen folgt ein kritischer Vergleich der Formen, der das wechselseitige Verhältnis von Exploration und Exploitation beschreibt. Wie diese zentralen Begriffe des strategischen Wissensmanagements durch Ambidextrie ausbalanciert werden können, wird intensiv diskutiert. Sowohl die Einflussfaktoren von Exploration und Exploitation als auch die langfristigen und kurzfristigen Effekte beider Prozesse werden dabei miteinbezogen. In der anschließenden Diskussion der Ergebnisse werden wesentliche Aspekte dargestellt, welche einen optimalen Balanceakt von Exploration und Exploitation im Innovations- und Technologiemanagement induzieren. Mit Hilfe des hier vorstellten Innovation-Alignment-Portfolios können normative Strategien der Ausbalancierung abgeleitet werden
Driving Together: An Analysis of Passengers' Needs and Desire for Cooperative Control in Automated Vehicles
No full textDriving automation aims to enhance comfort, safety, and traffic flow by removing the human driver from the control loop. However, the human experience of commuting involves more than just reaching a destination or assuming the role of a driver. Factors like personal driving style and courtesy towards fellow road users are integral to the driving experience but often overlooked in the development of driving algorithms for automated vehicles. In this study, we explored the needs of passengers in highly automated vehicles. A qualitative use case analysis was conducted (N=16). In a second study, N=15 participants experienced the resulting use cases in an automated vehicle. In these scenarios, they were able to interact with the automation through a cooperation HMI. Results indicate that most participants expressed a desire for cooperative driving, albeit varying with the driving situation. Moreover, allowing cooperation improves passengers’ overall experience by satisfying psychological needs for autonomy, security, competence, and relatedness
