Digitalisierung
Refine
Year of publication
Document Type
- conference proceeding (article) (426)
- Article (201)
- Part of a Book (49)
- conference proceeding (presentation, abstract) (49)
- Preprint (25)
- Book (14)
- Research Data (13)
- Working Paper (9)
- conference proceeding (volume) (5)
- Report (5)
Language
- English (628)
- German (185)
- Multiple languages (1)
Is part of the Bibliography
- no (814)
Keywords
- Offshoring (15)
- Betriebliches Informationssystem (12)
- Informationstechnik (12)
- Digitalisierung (11)
- Datenschutz (10)
- Internet of Things (9)
- Datensicherung (8)
- Elektronische Gesundheitskarte (8)
- Information systems (8)
- Künstliche Intelligenz (8)
Institute
- Fakultät Informatik und Mathematik (474)
- Fakultät Elektro- und Informationstechnik (257)
- Laboratory for Safe and Secure Systems (LAS3) (233)
- Labor für Digitalisierung (LFD) (100)
- Labor Regensburg Strategic IT Management (ReSITM) (72)
- Labor eHealth (eH) (38)
- Fakultät Maschinenbau (35)
- Labor für Technikfolgenabschätzung und Angewandte Ethik (LaTe) (28)
- Fakultät Sozial- und Gesundheitswissenschaften (26)
- Labor Parallele und Verteilte Systeme (24)
Begutachtungsstatus
- peer-reviewed (310)
- begutachtet (10)
Object detection and recognition is a core task in machine vision. Both the position and the rotation of the objects are of interest. Common algorithms for object recognition based on neural networks use a regression formulation and are aimed at changing environments. In industrial applications, the setting is different: One would like to determine with high accuracy, the pose of known objects. We are investigating a prototype application in this field, where we identify the rotation of an object in a plane. We use common network architectures and provide an overview of how well they are suited for this purpose. In addition, we compare our results with standard image processing algorithms, paying particular attention to the accuracy with metrics relevant in the industry. Moreover, an U-shape phenomenon with disturbed data occurred during the experiments, which is partially explained analytically.
The ARGO ship classification dataset holds 1750 labelled images from PlanetScope-4-Band satelites. The dataset creation process and results on the dataset are published in the demo paper:
{CITE}
The imagery is provided as numpy binary files. All image data is licensed by Planet Labs PBC. The channel ordering is BGRN. The dataset is provided in two folders named "ship" and "non_ship". Those folders correspond to the original labels created during automated dataset creation. The files are numbered.
Two additional .csv files are provided. The shipsAIS_2017_Zone17.csv file holds the AIS information on the imagery contained in the ship folder. The data was retrieved from marinecadastre.gov.
During the experiments errors in the automatically created dataset emerged which are further described in the paper. The manual relabelling is supplied in the corrected_labels.csv file.
In recent years, universities have been faced with increasing numbers of students dropping out. This is partly due to the fact that students are limited in their ability to explore individual learning paths through different course materials. However, a promising remedy to this issue is the implementation of adaptive learning management systems. These systems recommend customised learning paths to students - based on their individual learning styles. Learning styles are commonly classified using questionnaires and learning analytics, but both methods are prone to error. Questionnaires may yield superficial responses due to time constraints or lack of motivation, while learning analytics ignore offline learning behaviour. To address these limitations, this study aims to integrating Eye Tracking for a more accurate classification of students' learning styles. Ultimately, this comprehensive approach could not only open up a deeper understanding of subconscious processes, but also provide valuable insights into students' unique learning preferences.
This dataset contains the result of the survey to learning styles, learning strategies, and personality traits.
The survey was executed in winter term 2023/24 and summer term 2023 in a German university (OTH Regensburg) during the course "Software Engineering".
Examined questionnaires are ILS (learning styles), LIST-K (learning strategies), and BFI-10 (personality traits).
The same three questionnaires were asked at two different survey periods three to four months apart while each survey period lasts one to two weeks. Pretest data were examined at the start of the term, while posttest data at the end.
This dataset contains information queried from 22 students inside a Moodle based learning management system during the winter term 2023/24 at a German university.
Abstract
With the use of learning management systems students benefit from being recommended suitable learning elements based on their individual needs. In doing so, recommendation algorithms are applied which first query the student’s learning style. To improve the recommendation of learning elements a continuous analysis of the individual’s learning style is required. A frequent questionnaire assessment would however be too time consuming. Instead, in a prior study an algorithm has been designed to identify changes in learning styles from the student’s selection of learning elements. In this paper, we investigate the functionality of that algorithm by applying it on real student data. In particular, we test if the algorithm correctly indicates changes in learning styles. The utilised data is collected in our learning management system. To be precise, the data is obtained from 22 students enrolled in a software engineering course during the winter term of 2023/24. The data comprises two types of information for each student: 1) learning style collected at the start and end of the term, and 2) the user’s actual selection of learning elements inside the learning management system.
The uniqueness of this study lies in the data and the evaluation strategy based on it. Having the learning style at the end of the semester period as ground truth allows us to test if the algorithm operates correctly with actual user data from our learning management system. The results validate the behaviour of our algorithm, yet they strongly suggest the need for an adaptation. Further research is required on how to parameterise the underlying models.
Many of the envisioned use-cases for quantum computers involve optimisation processes. While there are many algorithmic primitives to perform the required calculations, all eventually lead to quantum gates operating on quantum bits, with an order as determined by the structure of the objective function and the properties of target hardware. When the structure of the problem representation is not aligned with structure and boundary conditions of the executing hardware, various overheads to degrade the computation may arise, possibly negating any possible quantum advantage.
Therefore, automatic transformations of problem representations play an important role in quantum computing when descriptions (semi-)targeted at humans must be cast into forms that can be executed on quantum computers. Mathematically equivalent formulations are known to result in substantially different non-functional properties depending on hardware, algorithm and detail properties of the problem. Given the current state of noisy-intermediate scale quantum hardware (NISQ), these effects are considerably more pronounced than in classical computing. Likewise, efficiency of the transformation itself is relevant because possible quantum advantage may easily be eradicated by the overhead of transforming between representations. In this paper we consider a specific class of higher-level representations (polynomial unconstrained binary optimisation problems), and devise novel automatic transformation mechanisms into widely used quadratic unconstrained binary optimisation problems that substantially improve efficiency and versatility over the state of the art. We also identify what influence factors of lower-level details can be abstracted away in the transformation process, and which details must be made available to higher-level abstractions.