Nein
Refine
Year of publication
- 2023 (95) (remove)
Document Type
- Article (30)
- Conference Proceeding (30)
- Report (16)
- Part of a Book (8)
- Book (5)
- Master's Thesis (3)
- Doctoral Thesis (2)
- Other Publications (1)
Language
- German (49)
- English (45)
- Multiple languages (1)
Keywords
- Accelerometer calibration (1)
- Accelerometer sensor (1)
- Accelerometers (1)
- Allegation (1)
- Anticipation (1)
- Apnea detection (1)
- Architektur (1)
- Artificial intelligence models (1)
- Automobiles (1)
- Bayesian parameter estimation (1)
Institute
- Fakultät Architektur und Gestaltung (5)
- Fakultät Bauingenieurwesen (9)
- Fakultät Elektrotechnik und Informationstechnik (2)
- Fakultät Informatik (6)
- Fakultät Maschinenbau (4)
- Fakultät Wirtschafts-, Kultur- und Rechtswissenschaften (10)
- Institut für Angewandte Forschung - IAF (11)
- Institut für Naturwissenschaften und Mathematik - INM (1)
- Institut für Optische Systeme - IOS (3)
- Institut für Strategische Innovation und Technologiemanagement - IST (11)
Particularly for manufactured products subject to aesthetic evaluation, the industrial manufacturing process must be monitored, and visual defects detected. For this purpose, more and more computer vision-integrated inspection systems are being used. In optical inspection based on cameras or range scanners, only a few examples are typically known before novel examples are inspected. Consequently, no large data set of non-defective and defective examples could be used to train a classifier, and methods that work with limited or weak supervision must be applied. For such scenarios, I propose new data-efficient machine learning approaches based on one-class learning that reduce the need for supervision in industrial computer vision tasks. The developed novelty detection model automatically extracts features from the input images and is trained only on available non-defective reference data. On top of the feature extractor, a one-class classifier based on recent developments in deep learning is placed. I evaluate the novelty detector in an industrial inspection scenario and state-of-the-art benchmarks from the machine learning community. In the second part of this work, the model gets improved by using a small number of novel defective examples, and hence, another source of supervision gets incorporated. The targeted real-world inspection unit is based on a camera array and a flashing light illumination, allowing inline capturing of multichannel images at a high rate. Optionally, the integration of range data, such as laser or Lidar signals, is possible by using the developed targetless data fusion method.
Misbehave like Nobody’s Watching? Investor Attention to Corporate Misconduct and its Implications
(2023)
IT-Compliance in KMU
(2023)
Infrastructure-making in interwar India was a dynamic, multilayered process involving roads and vehicles in urban and rural sites. One of their strongest playgrounds was Bombay Presidency and the Central Provinces in central and western India. Focusing on this region in the interwar period, this paper analyzes the varied relationship between peasant households and town-centred modernizing agents in the making of road transport infrastructures. The central argument of this paper is about the persistence of bullock carts over motor cars in the region. This persistence was grounded in the specific regional environment, the effects of the 1930s economic depression, and the priorities of social classes. Pinpointing these connections, the paper highlights that “modernization” of infrastructure was not a simple, linear process of progressivist change, nor did it mean the survival of apparently “old” technologies in the modern era. Instead, the paper pays attention to conflicting social complexities, implications, and meanings of the connection between infrastructure and modernity that modernization assumptions often overlook. Here, the paper shows how technological change occurred as a result of real, material class interests pulling infrastructural technology in different directions. This was where and why arguments of road-motor lobbyists and cart advocates eventually clashed, and Gandhian social workers resisted motor transport in defense of peasant interests.
Prior quantitative research identified in the text of technology-based ventures' business plans distinctive performance patterns of evolving business models. Accordingly, interactions with customers, financiers, and people and the patenting strategy's status evolved and served as indicators of early-stage tech ventures' performance. With longitudinal data from five venture cases, this research sheds light on the evolving business model by validating the performance patterns, and elucidating how and why the ventures' business models evolved. Based on a generic systems theory framework for the indicators, the explanatory case studies re-contextualize the performance patterns taken from the snapshot perspective of business plans to the longitudinal perspective of technology-based ventures' life-cycle. This research confirms the relation of business model patterns of digital and non-digital ventures to the performance groups of failure, survival, or success and suggests a broader systems perspective for further research.
The random matrix approach is a robust algorithm to filter the mean and covariance matrix of noisy observations of a dynamic object. Afterward, virtual measurement models can be used to find iteratively the extent parameters of an object that would cause the same statistical moments within their measurements. In previous work, this was limited to elliptical targets and only contour measurements.In this paper, we introduce the parallel use of an elliptical, triangular and rectangular-shaped virtual measurement model and a shape classification that selects the model that fits best to the measurements. The measurement likelihood is modeled either via ray tracing, a uniformly or normally spatial distribution over the object’s extent or as a combination of those.The results show that the extent estimation works precisely and that the classification accuracy highly depends on the measurement noise.