Technische Hochschule Würzburg-Schweinfurt Publikationsserver OPUS
Not a member yet
5300 research outputs found
Sort by
Anomaly Detection for Dynamic Human-Robot Assembly: Application of an LSTM-based autoencoder to interpret uncertain human behavior in HRC
Get PDFZielsetzung und Alleinstellungsmerkmale der Initiative zur Prognose der quantitativen und qualitativen Entwicklung der Logistik in Deutschland
No full text
Automation Strategies for the Photogrammetric Reconstruction of Pipelines
Get PDFA responsible use of energy resources is currently more important than ever. For the effective insulation of industrial plants, a three-camera measurement system was, therefore, developed. With this system, the as-built geometry of pipelines can be captured, which is the basis for the production of a precisely fitting and effective insulation. In addition, the digital twin can also be used for Building Information Modelling, e.g. for planning purposes or maintenance work. In contrast to the classical approach of processing the images by calculating a point cloud, the reconstruction is performed directly on the basis of the object edges in the image. For the optimisation of the, initially purely geometrically calculated components, an adjustment approach is used. In addition to the image information, this approach takes into account standardised parameters (such as the diameter) as well as the positional relationships between the components and thus eliminates discontinuities at the transitions. Furthermore, different automation approaches were developed to facilitate the evaluation of the images and the manual object recognition in the images for the user. For straight pipes, the selection of the object edges in one image is sufficient in most cases to calculate the 3D cylinder. Based on the normalised diameter, the missing depth can be derived approximately. Elbows can be localised on the basis of coplanar neighbouring elements. The other elbow parameters can be determined by matching the back projection with the image edges. The same applies to flanges. For merging multiple viewpoints, a transformation approach is used which works with homologous components instead of control points and minimises the orthogonal distances between the component axes in the datasets
Familiarity with and Dissemination of Advance Directives in Germany: Results of a Representative Survey of the General Population
No full textMittels einer Patientenverfügung können Personen für den Fall der Einwilligungsunfähigkeit hinsichtlich zukünftiger medizinisch-pflegerischer Behandlungsentscheidungen vorsorgen. Es liegen aktuell keine Daten darüber vor, wie bekannt und verbreitet das Vorsorgedokument Patientenverfügung in der Allgemeinbevölkerung in Deutschland ist. Ziel der Studie war neben der Erfassung von Bekanntheit und Verbreitung auch mehr über die Gründe für die (Nicht-)Erstellung und über die Nutzung von Informations- und Unterstützungsangeboten zu erfahren. Es wurde eine Online-Befragung einer repräsentativen Bevölkerungsstichprobe (n=1000) durchgeführt. Die Datenauswertung erfolgte deskriptiv und mittels Regressionsanalysen. 92% der Befragten kennen das Instrument der Patientenverfügung, über 37% haben selbst ein solches Dokument erstellt. Die Wahrscheinlichkeit für die Erstellung einer Patientenverfügung steigt mit zunehmenden Alter. Die Gründe für die (Nicht-)Erstellung einer Patientenverfügung sind heterogen. Fast zwei Drittel aller Befragten haben sich bereits zum Thema informiert, dies geschah vorwiegend im Internet. Die Mehrheit der Befragten nimmt bzw. nahm keine Unterstützung bei der Erstellung der Patientenverfügung wahr. Die Ergebnisse liefern Anhaltspunkte für die Anpassung von Informations- und Unterstützungsangeboten.With an advance directive, people can make provisions for the case of incapacity to give consent with regard to future medical and nursing treatment decisions. Currently, there are no data available on how well known and widespread advance directives are in the population in Germany. The aim of the study was, in addition to record awareness and dissemination, to find out more about the reasons for (not) writing an advance directive and about information and support used by people. An online survey of a representative sample of the general population (n=1000) was conducted. The data were analysed descriptively and by means of regression analysis. The survey showed that 92% of the sample knew about advance directives, and 37% had already created one. The probability of having already written an advance directive increases with increasing age. The reported reasons for (not) writing were heterogeneous. Almost 2/3 of all respondents had already accessed information on this topic, mainly via the Internet. The majority of those surveyed was not aware of any support available in drafting the advance directive. These findings provide suggestions for tailoring information and support services
Material stacking problem detection with Mask R-CNN for Storage safety
No full textPurpose of this paper:
Image processing technology has gained much improvement in recent years. In smart warehousing, most focus is on warehouse operations to improve efficiency and save human labors. However, in put-away, re-warehousing or picking process, after being handled by forklifts or laborers, the stacking of inventory items may change its shape and balance due to deviation, compression, tilting, etc., which may jeopardize the safety of stored goods and even people working in the warehouse. If there is a system that could monitor the stacking of inventory items all the time and could alarm managers should the stacking tilts or deforms to a certain level, inventory safety could be vastly improved. This study is on smart warehouse safety problems emphasizing at goods stacking to avoid the possibility of falling or collapse through image processing via Mask R-CNN. Our experiment is limited to items that form a rectangular block on a pallet, such as wooden bars, cartons or any box-shaped items.
Design/methodology/approach STS:
Mask R-CNN is a deep learning software and can be used in a wide range of applications. In this study, we used Mask R-CNN to detect the images of stacked items to see if the stacking is stable. We took photos from a warehouse and divided them into three classes – training, validation and production. VGG Image Annotator (VIA) was used for object annotation. To detect the tilt degree of stacked items, we derived formulation from book- stacking problems and retrieved dot coordinates of square frames encompassing objects in an image from the result of Mask R-CNN for calculation.
Findings:
Because there is a limited number of photos for training, validation and production, we applied image enhancement techniques such as flipping, affinity, multiplication, etc. to increase the total number of images to avoid over-fitting during the training process. The trained Mask R-CNN network demonstrated its capability in framing objects and after retrieving the dot coordinates of the frames, it could compute the degree of tilt as a reference for block stacking alarm.
Value:
The paper presents a relatively rare study of applying deep learning techniques on images as applied to material stacking safety problems. It contributes to a special smart warehousing domain. The same technique can be applied to inventory counting and help improve labor-saving in counting and in locating items in a warehouse.
Research limitations/implications:
Due to the limited number of images and restricted angles of taking the images, Mask R- CNN may not be so capable in framing objects of special angles of images. More images with diverse angles of them should be obtained for training to improve the capability of the trained network.
Practical implications:
Successful implementation of the technology developed in this study in a warehouse monitoring system can help industries in smart detection of improper stacking to assist human in improving the accuracy of safety judgement and can also save labors in reviewing images or records of a warehouse
Question-Answering System for Coffee Machines
Get PDFOur study presents a comprehensive Question Answering (QA) system for coffee machine related questions. The system covers a wide range of topics such as maintenance, usage, and troubleshooting of coffee machines, offering quick and accurate answers to the users through its intuitive interface and natural language processing capabilities. The system provides a seamless experience for coffee machine owners and users to access the information they need, ensuring smooth operation of their machines and allowing them to enjoy their favorite beverages with ease. To evaluate the performance of these models, we fine-tuned a range of BERT-based Transformers on a manually created dataset of 653 question-answer pairs. In conclusion, our findings demonstrate the feasibility of using NLP Question Answering models to deliver technical answers about coffee machines, and highlight the importance of fine-tuning these models on task-specific data
