3633 research outputs found
Sort by
BiGSiD: bionic grasping with edge-AI slip detection
No full textObject grasping is a crucial task for robots, inspired by nature, where humans can flexibly grasp any object and detect whether it is slipping from grasp or not, more by the sense of touch than vision. In this work we present a bionic gripper with an Edge-AI device that is able to dexterously grasp the handled objects, sense and predict their slippage. In this paper, a bionic gripper with tactile sensors and a time-of-flight sensor is developed. We propose a LSTM model which is used to detect (incipient) slip/slippage, where a 6 degree-of-freedom robot manipulator is used for data collection and testing. The aim of this paper is to develop an efficient slip detection system which we can deploy on the edge device on our gripper, so it can be a stand-alone product that can be attached to almost any robotic manipulator. We have collected a dataset, trained the model and achieved a slip detection accuracy of 95.34%. Due to the efficiency of our model we were able to implement the slip detection on an edge device. We use the Nvidia Jetson AGX Orin development board to show the inference/prediction in a real-time scenario. We demonstrate in the our experiments how the on-gripper slip detection capability allows more robust grasping as the grip force is adjusted in response to a slippage
Differentiation of salivary gland and salivary gland tumor tissue via Raman imaging combined with multivariate data analysis
Get PDFSalivary gland tumors (SGTs) are a relevant, highly diverse subgroup of head and neck tumors whose entity determination can be difficult. Confocal Raman imaging in combination with multivariate data analysis may possibly support their correct classification. For the analysis of the translational potential of Raman imaging in SGT determination, a multi-stage evaluation process is necessary. By measuring a sample set of Warthin tumor, pleomorphic adenoma and non-tumor salivary gland tissue, Raman data were obtained and a thorough Raman band analysis was performed. This evaluation revealed highly overlapping Raman patterns with only minor spectral differences. Consequently, a principal component analysis (PCA) was calculated and further combined with a discriminant analysis (DA) to enable the best possible distinction. The PCA-DA model was characterized by accuracy, sensitivity, selectivity and precision values above 90% and validated by predicting model-unknown Raman spectra, of which 93% were classified correctly. Thus, we state our PCA-DA to be suitable for parotid tumor and non-salivary salivary gland tissue discrimination and prediction. For evaluation of the translational potential, further validation steps are necessary
Panic in the lab: the effect of extreme external risks and bolstering cooperation in public goods games
No full textRare but extreme events, such as pandemics, terror attacks, and stock market collapses, pose a risk that could undermine cooperation in societies and groups. We extend the public goods game (PGG) to investigate the relationship between rare but extreme external risks and cooperation in a laboratory experiment. By incorporating risk as an external random variable in the PGG, independent of the participants’ contributions, we preserve the economic equilibrium of non-cooperation in the original game. Furthermore, we examine whether cooperation can be restored by the relatively simple intervention of informing about countermeasures while keeping the actual risk constant. Our experimental results reveal that on average extreme risks indeed decrease contributions by about 20%; however, countermeasure information increases contributions by about 10%. Specifically, in the first interactions, cooperation levels can even reach those observed in the riskless baseline. Our results suggest that countermeasure information could help reinforce social cohesion and resilience in the face of rare but extreme risks
Exploring the impact of work arrangements on employee well-being in the post-pandemic workplace: The role of perceived flexibility, work-life balance, and managerial support
Get PDFThe goal of this research was to understand the impact of different work arrangements (e.g. remote, hybrid, or on-premise) on employee well-being, considering the changes brought about by the pandemic. The study utilized a large sample of white-collar employees, with a focus on the mediating role of perceived flexibility and the moderating effect of managerial support in the relationship between work arrangements and employee well-being. As companies currently (re-)design their work arrangements there is a lot of insecurity on how especially remote and hybrid work influences the workforce and some companies are caught in a zig-zag course of overhauling their policies. Our findings suggest that employee well-being is mediated by location flexibility and work-life balance. However, the study also reveals challenges faced by remote workers, as the intense telecommuting was associated with lower employee well-being. The study also emphasizes the major role of managerial support in promoting employee well-being
NeuroIGN: explainable multimodal image-guided system for precise brain tumor surgery
No full textPrecise neurosurgical guidance is critical for successful brain surgeries and plays a vital role in all phases of image-guided neurosurgery (IGN). Neuronavigation software enables real-time tracking of surgical tools, ensuring their presentation with high precision in relation to a virtual patient model. Therefore, this work focuses on the development of a novel multimodal IGN system, leveraging deep learning and explainable AI to enhance brain tumor surgery outcomes. The study establishes the clinical and technical requirements of the system for brain tumor surgeries. NeuroIGN adopts a modular architecture, including brain tumor segmentation, patient registration, and explainable output prediction, and integrates open-source packages into an interactive neuronavigational display. The NeuroIGN system components underwent validation and evaluation in both laboratory and simulated operating room (OR) settings. Experimental results demonstrated its accuracy in tumor segmentation and the success of ExplainAI in increasing the trust of medical professionals in deep learning. The proposed system was successfully assembled and set up within 11 min in a pre-clinical OR setting with a tracking accuracy of 0.5 (± 0.1) mm. NeuroIGN was also evaluated as highly useful, with a high frame rate (19 FPS) and real-time ultrasound imaging capabilities. In conclusion, this paper describes not only the development of an open-source multimodal IGN system but also demonstrates the innovative application of deep learning and explainable AI algorithms in enhancing neuronavigation for brain tumor surgeries. By seamlessly integrating pre- and intra-operative patient image data with cutting-edge interventional devices, our experiments underscore the potential for deep learning models to improve the surgical treatment of brain tumors and long-term post-operative outcomes
Biofabrication's contribution to the evolution of cultured meat
Get PDFCultured Meat (CM) is a growing field in cellular agriculture, driven by the environmental impact of conventional meat production, which contributes to climate change and occupies ≈70% of arable land. As demand for meat alternatives rises, research in this area expands. CM production relies on tissue engineering techniques, where a limited number of animal cells are cultured in vitro and processed to create meat-like tissue comprising muscle and adipose components. Currently, CM is primarily produced on a small scale in pilot facilities. Producing a large cell mass based on suitable cell sources and bioreactors remains challenging. Advanced manufacturing methods and innovative materials are required to subsequently process this cell mass into CM products on a large scale. Consequently, CM is closely linked with biofabrication, a suite of technologies for precisely arranging cellular aggregates and cell-material composites to construct specific structures, often using robotics. This review provides insights into contemporary biomedical biofabrication technologies, focusing on significant advancements in muscle and adipose tissue biofabrication for CM production. Novel materials for biofabricating CM are also discussed, emphasizing their edibility and incorporation of healthful components. Finally, initial studies on biofabricated CM are examined, addressing current limitations and future challenges for large-scale production
Towards an augmented reality system supporting nail implantation for tibial fractures
No full textThis paper discusses the development and application of an augmented reality (AR) system for assisting in nail implantation procedures for complex tibial fractures. Traditional procedures involve extensive x-ray usage from various angles, leading to increased radiation exposure and prolonged surgical times. The study presents a method using pre- and post-operative computed tomography (CT) data sets and a convolutional neural network (CNN) trained on segmented bone and metal objects. The augmented reality system overlays accurate 3D representations of bony fragments and implants onto the surgeon's view, aiming to reduce radiation exposure and intervention time. The study demonstrates successful segmentation of bone and metal objects in cases of heavy metal artifacts, achieving promising results with a relatively low number of training sets. The integration of this system into the clinical workflow could potentially improve surgical outcomes, significantly reduce radiation time, and therefore improve patient safety
Der Leib als Resonanzmedium – oder warum Beziehungsarbeit Kraft braucht : eine anthropologische Grundlegung von Resonanzerfahrungen
Get PDFWeit mehr als Erwachsene scheinen Kinder sich in einer Offenheit zu begegnen, welche fast schon zu direkten gemeinsamen Gefühlen und Bewegungsimpulsen führen kann. Aber auch wir erleben, dass Leid berührt, die Chemie stimmt, eine Party mitreißt, eine Situation runterzieht oder Lachen und Gähnen ansteckend wirken. Für helfende Berufe sind diese Phänomene in der Gestaltung einer gelingenden Arbeitsbeziehung von grundsätzlichem Interesse. Ihre Basis liegt in der Fähigkeit, sich auf das Gegenüber so einzulassen, dass wir Stimmungen aufnehmen können und uns so einstimmen, um dann gemeinsam einen Veränderungsprozess zu beginnen. Nachhaltige Hilfe muss kooperativ gestaltet werden und ist als ein komplexes Resonanzgeschehen zu verstehen, welches zentral durch das Einstimmen der Kontaktpersonen getragen wird.
Folgende Fragen leiten den Text: Wie ist es überhaupt möglich, dass wir in Resonanz treten können? Wie kann die Erfahrung von Resonanz begrifflich analysiert und beschrieben werden? Wie zeigt sich das in der pädagogischen Praxis? Die Reflexionen zielen auf die Möglichkeitsbedingungen von Resonanzerfahrungen. Ihren Ausgang nehmen sie in Hartmut Rosas Resonanzbestimmung, gehen dessen Verweise auf eine leibliche Fundierung nach und stecken von dort den Rahmen des Resonanzphänomens variierend ab. Ziel ist es, das Resonanzphänomen theoretisch tiefer zu fundieren und damit etwas transparenter zu machen. Im letzten Teil werden dann Verbindungen zur Bedeutung in der pädagogischen Beziehungsarbeit hergestellt
Arbeitswissenschaft und Innovationsmanagement : eine bibliometrisch begründete Annäherung
Get PDFArbeitswissenschaft und Innovationsmanagement sind Disziplinen mit unterschiedlicher wissenschaftlicher Tradition, verschiedenen Forschungscommunitys und prinzipiell anderen Zielsetzungen. Dennoch formulieren beide Disziplinen Gestaltungsanspruch für soziotechnische Systeme, wobei für beide relevante Forschungsgegenstände selten aus beiden Perspektiven gleichzeitig innerhalb einer Publikation adressiert werden. In einer bibliometrischen Studie haben wir 100 Konnektoren (Schlüsselwörter in Publikationen) identifiziert, die sowohl im Zusammenhang mit Arbeitswissenschaft als auch in Verbindung mit Innovationsmanagement verwendet wurden. Diese Konnektoren, wie beispielsweise Digitalisierung oder Künstliche Intelligenz laden geradezu ein, interdisziplinäre Forschung zu soziotechnischen Systemen im Sinne der arbeitenden Menschen und im Hinblick auf Produktivität durch Innovationen zu verstärken
Investigation of the tissue displacement through textile pressure on soft avatar in Browzwear’s VStitcher software
Get PDFNowadays, soft avatars are used in various fields to simulate the behavior of human soft tissues in different applications. Likewise, they are also utilized in the garment industry in order to achieve a realistic testing of the fit and functionality of tight-fitting clothing. Therefore it is important that avatars in CAD programs for clothing conform to the mechanical properties of human soft tissue. The accuracy of the avatars' properties in simulating the change in shape of human tissue is crucial here, which is caused by the contact pressure that compressive or tight-fitting garments exert onto the body. In this study, Browzwear’s VStitcher soft avatar Sofia was investigated and different body shapes resulting from being influenced by a legging with different levels of negative ease values were compared with non-affected natural avatar body shape. The examination of the soft avatar simulation shows that although a fast estimation of the tissue displacement can be predicted, there are some shape changes limitations compared to the natural behavior of human soft tissue