Refine
Year of publication
Document Type
- Article (1808)
- conference proceeding (article) (1675)
- Part of a Book (565)
- conference proceeding (presentation, abstract) (262)
- Book (159)
- conference talk (135)
- Report (122)
- Review (100)
- Working Paper (49)
- Preprint (46)
- conference proceeding (volume) (33)
- Doctoral Thesis (24)
- Edited collection (21)
- Part of Periodical (20)
- Master's Thesis (15)
- Lecture (12)
- Bachelor-/Diplom Thesis (10)
- Patent (10)
- Other (9)
- Moving Images (7)
- Study Thesis (4)
- Sound (3)
- Course Material (2)
- Habilitation (2)
Language
Is part of the Bibliography
- no (5093)
Keywords
- Simulation (37)
- Digitalisierung (29)
- Erneuerbare Energien (28)
- Energiewende (27)
- field emission (24)
- Bildgebendes Verfahren (22)
- Deutschland (22)
- Klimaneutralität (22)
- Deep Learning (21)
- Power-to-Gas (21)
Institute
- Fakultät Angewandte Sozial- und Gesundheitswissenschaften (1292)
- Fakultät Informatik und Mathematik (1121)
- Fakultät Maschinenbau (891)
- Fakultät Elektro- und Informationstechnik (796)
- Institut für Sozialforschung und Technikfolgenabschätzung (IST) (552)
- Labor Empirische Sozialforschung (458)
- Fakultät Angewandte Natur- und Kulturwissenschaften (398)
- Fakultät Bauingenieurwesen (350)
- Labor für Technikfolgenabschätzung und Angewandte Ethik (LaTe) (310)
- Laboratory for Safe and Secure Systems (LAS3) (277)
Begutachtungsstatus
- peer-reviewed (1546)
- begutachtet (92)
Als Alternative zur konventionellen Bettung von Leitungen und Rohren in Sand werden immer häufiger Zeitweise fließfähige, Selbstverdichtende Verfüllbaustoffe (ZFSV) verwendet. Die Bettung in ZFSV kann zu einer Zeit- und Kostenersparnis führen. In diesem Beitrag wird gezeigt, dass die Verwendung von ZFSV zur Rohrgrabenverfüllung gegenüber der konventionellen Sandbettung neben der Schonung der natürlichen Ressourcen zusätzlich ein Einsparpotenzial bezüglich der Treibhausgasemissionen aufweist.
Nach Einführung in die Thematik werden unter Berücksichtigungen der EBGEO und des aktuellen Entwurfs des neuen Eurocodes 7, Teil 3 numerische Berechnungen zur Beanspruchung unbewehrter pfahlartiger Tragglieder / Stabilisierungssäulen aufgrund von Spreizverformungen von Erddämmen durchgeführt. Dabei werden u.a. die Materialeigenschaften der Tragglieder und die Dehnsteifigkeiten eingelegter Geogitter variiert, sowie deren Einflüsse auf die Verdrehung und Verbiegung der Tragglieder aufgezeigt.
Real-time computational speed and a high degree of precision are requirements for computer-assisted interventions. Applying a segmentation network to a medical video processing task can introduce significant inter-frame prediction noise. Existing approaches can reduce inconsistencies by including temporal information but often impose requirements on the architecture or dataset. This paper proposes a method to include temporal information in any segmentation model and, thus, a technique to improve video segmentation performance without alterations during training or additional labeling. With Motion-Corrected Moving Average, we refine the exponential moving average between the current and previous predictions. Using optical flow to estimate the movement between consecutive frames, we can shift the prior term in the moving-average calculation to align with the geometry of the current frame. The optical flow calculation does not require the output of the model and can therefore be performed in parallel, leading to no significant runtime penalty for our approach. We evaluate our approach on two publicly available segmentation datasets and two proprietary endoscopic datasets and show improvements over a baseline approach.
Limitations in computer-assisted diagnosis include lack of labeled data and inability to model the relation between what experts see and what computers learn. Even though artificial intelligence and machine learning have demonstrated remarkable performances in medical image computing, their accountability and transparency level must be improved to transfer this success into clinical practice. The reliability of machine learning decisions must be explained and interpreted, especially for supporting the medical diagnosis. While deep learning techniques are broad so that unseen information might help learn patterns of interest, human insights to describe objects of interest help in decision-making. This paper proposes a novel approach, DeepCraftFuse, to address the challenge of combining information provided by deep networks with visual-based features to significantly enhance the correct identification of cancerous tissues in patients affected with Barrett’s esophagus (BE). We demonstrate that DeepCraftFuse outperforms state-of-the-art techniques on private and public datasets, reaching results of around 95% when distinguishing patients affected by BE that is either positive or negative to esophageal cancer.
Heavy smoke development represents an important challenge for operating physicians during laparoscopic procedures and can potentially affect the success of an intervention due to reduced visibility and orientation. Reliable and accurate recognition of smoke is therefore a prerequisite for the use of downstream systems such as automated smoke evacuation systems. Current approaches distinguish between non-smoked and smoked frames but often ignore the temporal context inherent in endoscopic video data. In this work, we therefore present a method that utilizes the pixel-wise displacement from randomly sampled images to the preceding frames determined using the optical flow algorithm by providing the transformed magnitude of the displacement as an additional input to the network. Further, we incorporate the temporal context at evaluation time by applying an exponential moving average on the estimated class probabilities of the model output to obtain more stable and robust results over time. We evaluate our method on two convolutional-based and one state-of-the-art transformer architecture and show improvements in the classification results over a baseline approach, regardless of the network used.
Training data for Neural Networks is often scarce in the medical domain, which often results in models that struggle to generalize and consequently showpoor performance on unseen datasets. Generally, adding augmentation methods to the training pipeline considerably enhances a model’s performance. Using the dataset of the Foot Ulcer Segmentation Challenge, we analyze two additional augmentation methods in the domain of chronic foot wounds - local warping of wound edges along with projection and blurring of shapes inside wounds. Our experiments show that improvements in the Dice similarity coefficient and Normalized Surface Distance metrics depend on a sensible selection of those augmentation methods.
Seit mehr als 25 Jahren ist der Workshop "Bildverarbeitung für die Medizin" als erfolgreiche Veranstaltung etabliert. Ziel ist auch 2024 wieder die Darstellung aktueller Forschungsergebnisse und die Vertiefung der Gespräche zwischen Wissenschaftlern, Industrie und Anwendern. Die Beiträge dieses Bandes - viele davon in englischer Sprache - umfassen alle Bereiche der medizinischen Bildverarbeitung, insbesondere die Bildgebung und -akquisition, Segmentierung und Analyse, Visualisierung und Animation, computerunterstützte Diagnose sowie bildgestützte Therapieplanung und Therapie. Hierbei kommen Methoden des maschinelles Lernens, der biomechanischen Modellierung sowie der Validierung und Qualitätssicherung zum Einsatz.
Significant deformations of bodies made from compliant magnetoactive elastomers (MAE) in magnetic fields make these materials promising for applications in magnetically controlled actuators for soft robotics. Reported experimental research in this context was devoted to the behaviour in the quasi-static magnetic field, but the transient dynamics are of great practical importance. This paper presents an experimental study of the transient response of apparent longitudinal and transverse strains of a family of isotropic and anisotropic MAE cylinders with six different aspect ratios in time-varying uniform magnetic fields. The time dependence of the magnetic field has a trapezoidal form, where the rate of both legs is varied between 52 and 757 kA/(s·m) and the maximum magnetic field takes three values between 153 and 505 kA/m. It is proposed to introduce four characteristic times: two for the delay of the transient response during increasing and decreasing magnetic field, as well as two for rise and fall times. To facilitate the comparison between different magnetic field rates, these characteristic times are further normalized on the rise time of the magnetic field ramp. The dependence of the normalized characteristic times on the aspect ratio, the magnetic field slew rate, maximum magnetic field values, initial internal structure (isotropic versus anisotropic specimens) and weight fraction of the soft-magnetic filler are obtained and discussed in detail. The normalized magnetostrictive hysteresis loop is introduced, and used to explain why the normalized delay times vary with changing experimental parameters.
The human nose serves as the primary gateway for air entering the respiratory system and plays a vital role in breathing. Nasal breathing difficulties are a significant health concern, leading to substantial healthcare costs for patients. Understanding nasal airflow dynamics is crucial for comprehending respiratory mechanisms. This article presents a detailed study using tomo-Particle Image Velocimetry (PIV) to investigate nasal airflow dynamics while addressing its accuracy. Embedded in the OpenNose project, the work described aims to provide a validation basis for different numerical approaches to upper airway flow. The study includes the manufacturing of a transparent silicone model based on a clinical CT scan, refractive index matching to minimize optical distortions, and precise flow rate adjustments based on physiological breathing cycles. This method allows for spatial high-resolution investigations in different regions of interest within the nasopharynx during various phases of the breathing cycle. The results demonstrate the accuracy of the investigations, enabling detailed analysis of flow structures and gradients. This spatial high-resolution tomo-PIV approach provides valuable insights into the complex flow phenomena occurring during the physiological breathing cycle in the nasopharynx. The study's findings contribute to advancements in non-free-of-sight experimental flow investigation of complex cavities under nearly realistic conditions. Furthermore, reliable and accurate experimental data is crucial for properly validating numerical approaches that compute this patient-specific flow for clinical purposes.
The use of chatbots based on large language models (LLMs) and their impact on society are influencing our learning experience platform Hochschul-Assistenz-System (HAnS). HAnS uses machine learning (ML) methods to support students and lecturers in the online learning and teaching processes [1]. This paper introduces LLM-based features available in HAnS which are using the transcript of our improved Automatic Speech Recognition (ASR) pipeline with an average transcription duration of 45 seconds and an average word error rate (WER) of 6.66% on over 8 hours of audio data of 7 lecture videos. A LLM-based chatbot could be used to answer questions on the lecture content as the ASR transcript is provided as context. The summarization and topic segmentation uses the LLM to improve our learning experience platform. We generate multiple choice questions using the LLM and the ASR transcript as context during playback in a period of 3 minutes and display them in the HAnS frontend.