Fakultät Informatik und Mathematik
Refine
Year of publication
Document Type
- conference proceeding (article) (437)
- Article (392)
- Part of a Book (87)
- conference proceeding (presentation, abstract) (87)
- conference proceeding (volume) (23)
- Preprint (22)
- Book (21)
- Report (16)
- Working Paper (11)
- conference talk (8)
Is part of the Bibliography
- no (1127)
Keywords
- Bildgebendes Verfahren (22)
- Deep Learning (20)
- Produktionsplanung (18)
- Betriebliches Informationssystem (16)
- Künstliche Intelligenz (16)
- Diagnose (14)
- Gebärmutterhalskrebs (14)
- Informationstechnik (14)
- Maschinelles Lernen (14)
- Artificial Intelligence (13)
Institute
- Fakultät Informatik und Mathematik (1127)
- Labor für Technikfolgenabschätzung und Angewandte Ethik (LaTe) (183)
- Regensburg Medical Image Computing (ReMIC) (158)
- Institut für Sozialforschung und Technikfolgenabschätzung (IST) (144)
- Fakultät Angewandte Sozial- und Gesundheitswissenschaften (97)
- Labor Empirische Sozialforschung (93)
- Regensburg Strategic IT Management (ReSITM) (88)
- Labor für Digitalisierung (LFD) (84)
- Labor eHealth (eH) (66)
- Regensburg Center of Health Sciences and Technology - RCHST (57)
Begutachtungsstatus
- peer-reviewed (489)
- begutachtet (5)
Control and Automation of services of the urban infrastructure offered to citizens and tourists are elementary parts of a smart city. But both rely on a stable supply of data from sensors spread across the whole city, e. g., the fill level sensors of waste bins needed for a waste management tool which we developed in a collaboration with the Regensburg city council for the on-demand collection of waste bins. Europe has a lot of historic cities like Regensburg with narrow streets and huge building walls, some made from granite and fieldstones, which often represents an insurmountable obstacle to wireless data transmission. The reduction of the road traffic volume poses an additional challenge for city planners. By means of networked planning and simulation software, the situation, state and efficiency of citywide logistic services can be monitored and optimized. In the course of such optimizations, we propose the combination of digital and logistic services. As an example, we show that monitoring state information, such as the waste bin fill levels, can be accomplished using the same vehicles and the same planning software, that is used for luggage transportation. Moreover, we describe how we adapted a solver for a variant of the TSP, namely the prize-collecting traveling salesman, to optimize the route planning dynamically.
Small and medium-sized enterprises (SMEs) increasingly need to manage nformation technology (IT) effectively in order to remain competitive. However, compared to larger organizations, SMEs often face challenges in terms of resources and employer attractiveness, and regularly do not have the need to employ a Chief Information Officer (CIO) on a full-time basis. To address this issue, a growing number of global experts have begun to provide CIO services on a part-time basis for multiple clients simultaneously. This approach allows SMEs to tap into the expertise of experienced IT leaders at a fraction of the cost and without committing to long-term arrangements. While these professionals, known as “Fractional CIOs”, have proven their value in the field, there has been a lack of academic research on this emerging trend. Therefore, we carried out a comprehensive research project between 2020 and 2023, involving 62 Fractional CIOs from 10 countries. The research produced a definition, different types of engagements, and success factors for Fractional CIOs and their engagements. This paper summarizes these findings for a wider audience of academics and practitioners.
Der zweite ITG-Workshop „Sprachassistenten – Anwendungen, Implikationen, Entwicklungen“ fand am 5. März 2024 in Regensburg statt. Er bot eine organisatorische und inhaltliche Fortführung des ersten Workshops vor vier Jahren in Magdeburg 2020. Auch in diesem Jahr war er wieder der Konferenz Elektronische Sprachsignalverarbeitung angegliedert. Auf dem Workshop wurden vielfältige und interdisziplinäre Beiträge in eingeladenen Vorträgen und als eingereichte Poster präsentiert. Durch die gute Mischung von Beitragenden sowohl aus der Hochschullandschaft als auch aus der Industrie wurden die verschiedensten Aspekte anwendungsnah diskutiert.
One of the tasks PAULE[1, 2] solves is finding suitable control parameter (cp-)trajectories for a given target acoustic. These cp-trajectories can be used to synthesize speech with the articulatory speech synthesizer of the VocalTractLab (VTL) [3]. If the target acoustic contains substantial microphone noise or other background noises, occasionally PAULE optimizes not for the speech in the target, but for this background noises. By adding a speech/non-speech classifier to the feedback and planning-loop in PAULE this resynthesis of background noises should be mitigated. Unfortunately, the improvements were minor, which might be due to uninformative gradients of the classifier. The importance of informative gradients and the use classifiers to adapt PAULE to different tasks are explained and discussed.
There is high confidence for the hypothesis that in speech perception the cycles of a θ-oscillation segment the auditory signal into syllables [8]. Yet the functionality of the oscillator generating the θ-oscillation is unknown. We follow the finding that, within an auditory scene, speech is perceived as a stream given by temporal coherence [12]. We work with the hypotheses that the θ-oscillator is driven by temporal features providing this coherence. We propose a new temporal feature called O-distance, which detects the onset of a syllable - the starting point to of a θ-cycle–triggered by the temporal distance from to to the instance of the maximal rise of the loudness curve of the vowel. To extract to from the auditory signal, we use the statistical properties of this distance based on the C-center hypothesis [25], which predicts a close temporal relation of the onset consonants to the onset of a vowel. The statistics are derived from reference O-distance extracted from an articulatory database, where the minima and maxima of the loudness are related to maxima and minima of the lower incisor and tongue tip. To judge the quality of the O-distance extracted from the auditory signal, we regard the temporal deviation of the O-distance to the reference O-distance. Currently we achieve a mean deviation of 34ms.
This paper addresses the challenges and advancements in speech recognition for singing, a domain distinctly different from standard speech recognition. Singing encompasses unique challenges, including extensive pitch variations, diverse vocal styles, and background music interference. We explore key areas such as phoneme recognition, language identification in songs, keyword spotting, and full lyrics transcription. I will describe some of my own experiences when performing research on these tasks just as they were starting to gain traction, but will also show how recent developments in deep learning and large-scale datasets have propelled progress in this field. My goal is to illuminate the complexities of applying speech recognition to singing, evaluate current capabilities, and outline future research directions.
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.