Suche
Anzeige der Dokumente 21-27 von 27
Dissertation
Context Awareness for Smartphone-Based Cooperative VRU Collision Avoidance
(2024)
Nach Angaben der Weltgesundheitsorganisation sterben weltweit noch immer jährlich rund 1,35 Millionen Menschen bei Verkehrsunfällen. Ungefähr 54% dieser Todesfälle ereignen sich unter ungeschützten Verkehrsteilnehmern wie Fußgängern, Radfahrern und Motorradfahrern. Fußgänger und Radfahrer machen dabei zusammen rund 26% aller Verkehrstoten aus. Im Gegensatz zu fahrzeugbasierten Kollisionsvermeidungssystemen setzen kooperative Systeme die Verwendung von mobilen Geräten wie Smartphones zur kontinuierlichen Erfassung von ...
Aufsatz
Continuous Feature Networks: A Novel Method to Process Irregularly and Inconsistently Sampled Data With Position-Dependent Features
(2023-12-30)
Continuous Kernels have been a recent development in convolutional neural networks. Such kernels are used to process data sampled at different resolutions as well as irregularly and inconsistently sampled data. Convolutional neural networks have the property of translational invariance (e.g., features are detected regardless of their position in the measurement domain), which is unsuitable if the position of detected features is relevant for the prediction task. However, the capabilities of continuous kernels to ...
Konferenzveröffentlichung
Utilizing Continuous Kernels for Processing Irregularly and Inconsistently Sampled Data With Position-Dependent Features
(2023-03-13)
Continuous Kernels have been a recent development in convolutional neural networks. Such kernels are used to process data sampled at different resolutions as well as irregularly and inconsistently sampled data. Convolutional neural networks have the property of translational invariance (e.g., features are detected regardless of their position in the measurement domain), which is unsuitable for certain types of data, where the position of detected features is relevant. However, the capabilities of continuous kernels ...
Dissertation
Effektive Integration von heterogenen Produktkatalogen im schnelllebigen Umfeld des E-Commerce
(2023)
Online-Marktplätze generieren von Jahr zu Jahr einen größeren Anteil des Einzelhandelsumsatzes. Ein wichtiger Faktor für den Erfolg von Online-Marktplätzen ist die korrekte Darstellung der Produktdaten für ihre Kunden. Diese Daten werden häufig von Zulieferern in Form von Produktkatalogen zur Verfügung gestellt, die in den Online-Marktplatz integriert werden müssen. Um dies zu erreichen, sind insbesondere kleine und mittelständische Unternehmen häufig auf aufwändige manuelle Arbeitsschritte bei der Datenintegration ...
Dissertation
Patterns of Practice - Interdisciplinary Negotiation of Cultural Complexity through Practice-Based Methods in Informatics
(2022)
Following the principle of knowing through making, this thesis discusses development and application of a practice-based methodology for construction of digital artefacts within
cultural contexts. It addresses the epistemological diversity and complexity inhering within interdisciplinary projects, suggesting methodological devices able to navigate the variegated disciplinary landscape present within respective development projects. The conceptual pair complexity/complication acts as theoretical point of reference ...
Dissertation
Algorithms for Emotion Recognition
(2023)
Technological advancements have increasingly facilitated emotion recognition through physiological sensors integrated into intelligent devices, such as earables and wristbands. People commonly wear these devices in their everyday lives (i.e., in the wild). Patterns can be extracted from various physiological signals, enabling the recognition of emotions. This capability can be integrated into diverse applications, such as attention management systems, human-robot interaction, and stress detection, enhancing them to ...
Dissertation
Object Detection for Automotive Radar Perception
(2024)
Automated vehicles are among the biggest trends in the automotive industry. The desired level of automation slowly progresses from advanced driver assistance system functions to fully autonomous driving. Excellent environmental perception is a critical requirement in this development. This thesis focuses on solutions to the challenges that come with the utilization of automotive radar systems for road user recognition. Therefore, several machine learning techniques are applied and compared to detect and classify ...