Refine
Departments, institutes and facilities
- Fachbereich Wirtschaftswissenschaften (1197)
- Fachbereich Informatik (1117)
- Fachbereich Angewandte Naturwissenschaften (743)
- Fachbereich Elektrotechnik, Maschinenbau und Technikjournalismus (587)
- Institut für funktionale Gen-Analytik (IFGA) (576)
- Institut für Technik, Ressourcenschonung und Energieeffizienz (TREE) (447)
- Fachbereich Sozialpolitik und Soziale Sicherung (373)
- Institute of Visual Computing (IVC) (308)
- Institut für Cyber Security & Privacy (ICSP) (299)
- Institut für Verbraucherinformatik (IVI) (244)
- Internationales Zentrum für Nachhaltige Entwicklung (IZNE) (186)
- Institut für Sicherheitsforschung (ISF) (87)
- Graduierteninstitut (59)
- Präsidium (39)
- Institut für Medienentwicklung und -analyse (IMEA) (37)
- Stabsstelle Kommunikation und Marketing (37)
- Centrum für Entrepreneurship, Innovation und Mittelstand (CENTIM) (33)
- Institut für Detektionstechnologien (IDT) (28)
- Zentrum für Innovation und Entwicklung in der Lehre (ZIEL) (25)
- Sprachenzentrum (24)
- Bibliothek (23)
- Zentrum für Ethik und Verantwortung (ZEV) (18)
- Institut für Soziale Innovationen (ISI) (13)
- Verwaltung (12)
- Zentrum für Wissenschafts- und Technologietransfer (ZWT) (10)
- Institut für IT-Service (ITS) (7)
- Institut für Existenzgründung und Mittelstandsförderung (IfEM) (3)
- International Office (3)
- Gleichstellungsstelle (1)
- Institut für KI und Autonome Systeme (A2S) (1)
- Zentrum für Campus-IT (1)
Document Type
- Article (2352)
- Conference Object (1781)
- Part of a Book (905)
- Book (monograph, edited volume) (454)
- Report (193)
- Contribution to a Periodical (117)
- Doctoral Thesis (90)
- Working Paper (90)
- Preprint (86)
- Master's Thesis (63)
- Lecture (62)
- Conference Proceedings (54)
- Part of Periodical (44)
- Bachelor Thesis (40)
- Patent (40)
- Research Data (24)
- Other (17)
- Book review (12)
- Diploma Thesis (9)
- Video (9)
- Periodical (9)
- Study Thesis (2)
- Postdoctoral thesis (1)
Year of publication
Keywords
- Lehrbuch (87)
- Deutschland (33)
- Nachhaltigkeit (29)
- Controlling (25)
- Unternehmen (25)
- Management (20)
- Corporate Social Responsibility (18)
- Betriebswirtschaftslehre (17)
- Digitalisierung (16)
- Prozessmanagement (16)
This thesis proposes a multi-label classification approach using the Multimodal Transformer (MulT) [80] to perform multi-modal emotion categorization on a dataset of oral histories archived at the Haus der Geschichte (HdG). Prior uni-modal emotion classification experiments conducted on the novel HdG dataset provided less than satisfactory results. They uncovered issues such as class imbalance, ambiguities in emotion perception between annotators, and lack of representative training data to perform transfer learning [28]. Hence, the objectives of this thesis were to achieve better results by performing a multi-modal fusion and resolving the problems arising from class imbalance and annotator-induced bias in emotion perception. A further objective was to assess the quality of the novel HdG dataset and benchmark the results using SOTA techniques. Through a literature survey on the challenges, models, and datasets related to multi-modal emotion recognition, we created a methodology utilizing the MulT along with a multi-label classification approach. This approach produced a considerable improvement in the overall emotion recognition by obtaining an average AUC of 0.74 and Balanced-accuracy of 0.70 on the HdG dataset, which is comparable to state-of-the-art (SOTA) results on other datasets. In this manner, we were also able to benchmark the novel HdG dataset as well as introduce a novel multi-annotator learning approach to understand each annotator’s relative strengths and weaknesses for emotion perception. Our evaluation results highlight the potential benefits of the novel multi-annotator learning approach in improving overall performance by resolving the problems arising from annotator-induced bias and variation in the perception of emotions. Complementing these results, we performed a further qualitative analysis of the HdG annotations with a psychologist to study the ambiguities found in the annotations. We conclude that the ambiguities in annotations may have resulted from a combination of several socio-psychological factors and systemic issues associated with the process of creating these annotations. As these problems are also present in most multi-modal emotion recognition datasets, we conclude that the domain could benefit from a set of annotation guidelines to create standardized datasets.
Object detection concerns the classification and localization of objects in an image. To cope with changes in the environment, such as when new classes are added or a new domain is encountered, the detector needs to update itself with the new information while retaining knowledge learned in the past. Previous works have shown that training the detector solely on new data would produce a severe "forgetting" effect, in which the performance on past tasks deteriorates through each new learning phase. However, in many cases, storing and accessing past data is not possible due to privacy concerns or storage constraints. This project aims to investigate promising continual learning strategies for object detection without storing and accessing past training images and labels. We show that by utilizing the pseudo-background trick to deal with missing labels, and knowledge distillation to deal with missing data, the forgetting effect can be significantly reduced in both class-incremental and domain-incremental scenarios. Furthermore, an integration of a small latent replay buffer can result in a positive backward transfer, indicating the enhancement of past knowledge when new knowledge is learned.
This paper presents a novel approach to address noise, vibration, and harshness (NVH) issues in electrically assisted bicycles (e-bikes) caused by the drive unit. By investigating and optimising the structural dynamics during early product development, NVH can decisively be improved and valuable resources can be saved, emphasising its significance for enhancing riding performance. The paper offers a comprehensive analysis of the e-bike drive unit’s mechanical interactions among relevant components, culminating—to the best of our knowledge—in the development of the first high-fidelity model of an entire e-bike drive unit. The proposed model uses the principles of elastic multi body dynamics (eMBD) to elucidate the structural dynamics in dynamic-transient calculations. Comparing power spectra between measured and simulated motion variables validates the chosen model assumptions. The measurements of physical samples utilise accelerometers, contactless laser Doppler vibrometry (LDV) and various test arrangements, which are replicated in simulations and provide accessibility to measure vibrations onto rotating shafts and stationary structures. In summary, this integrated system-level approach can serve as a viable starting point for comprehending and managing the NVH behaviour of e-bikes.
Pyrolysis–Gas Chromatography
(2022)
The methodology of analytical pyrolysis-GC/MS has been known for several years, but is seldom used in research laboratories and process control in the chemical industry. This is due to the relative difficulty of interpreting the identified pyrolysis products as well as the variety of them. This book contains full identification of several classes of polymers/copolymers and biopolymers that can be very helpful to the user. In addition, the practical applications can encourage analytical chemists and engineers to use the techniques explored in this volume.