276557 research outputs found
Sort by
Sensing the path to mobility: Advancing gait rehabilitation with sensor technology
No full textContains fulltext :
314291.pdf (Publisher’s version ) (Open Access)This thesis focuses on the development and evaluation of algorithms based on wearable sensors (IMUs) to assess gait patterns and provide feedback for individuals with gait impairments. A sensor-based algorithm demonstrated high accuracy in measuring gait parameters like step length and timing in both healthy individuals and people with stroke. Additionally, the impact of speed changes around turns on gait characteristics was examined. Building on these findings, the algorithm was extended to estimate two additional gait characteristics: foot strike angle and forward propulsion. While the foot strike angle was measured with great accuracy, forward propulsion appeared to be more complex, highlighting the need for advanced techniques. The developed algorithms were applied on individuals with knee osteoarthritis. Those awaiting knee replacement surgery exhibited slightly slower walking speeds on average, although there was significant variability within the group.
Dit proefschrift richt zich op de ontwikkeling en evaluatie van algoritmen op basis van draagbare sensoren om looppatronen te beoordelen en feedback te geven aan mensen met loopbeperkingen. Een sensorgebaseerd algoritme toonde een hoge nauwkeurigheid bij het meten van loopparameters zoals paslengte en timing, bij zowel gezonde personen als bij mensen die een beroerte hebben gehad. Daarnaast werd het effect van snelheidsveranderingen op de loopkenmerken bij het maken van bochten onderzocht. Voortbouwend op deze bevindingen werd het algoritme uitgebreid om twee extra loopkenmerken te schatten: de hoek van de voetlanding en de voortstuwing. Terwijl de hoek van de voetlanding met grote nauwkeurigheid kon worden gemeten, bleek de voortstuwing complexer, wat de noodzaak van geavanceerde technieken benadrukt. De ontwikkelde algoritmen werden toegepast op mensen met knie-artrose. Degenen die wachtten op een knievervangende operatie vertoonden gemiddeld iets tragere loopsnelheden, hoewel er binnen de groep aanzienlijke variabiliteit was.Radboud University, 15 januari 2025Promotor : Keijsers, G.P.J. Co-promotor : Smulders, K.222 p
From settlement to award. Challenges and opportunities of consent awards
No full textContains fulltext :
317892.pdf (Publisher’s version ) (Open Access
Optimization of the automated Sunnybrook Facial Grading System - Improving the reliability of a deep learning network with facial landmarks.
No full textContains fulltext :
315455.pdf (Publisher’s version ) (Open Access)OBJECTIVE: The Sunnybrook Facial Grading System (SFGS) is a well-established grading system to assess the severity and progression of a unilateral facial palsy. The automation of the SFGS makes the SFGS more accessible for researchers, students, clinicians in training, or other untrained co-workers and could be implemented in an eHealth environment. This study investigated the impact on the reliability of the automated SFGS by adding a facial landmark layer in a previously developed convolutional neural network (CNN). METHODS: An existing dataset of 116 patients with a unilateral peripheral facial palsy and 9 healthy subjects performing the SFGS poses was used to train a CNN with a newly added facial landmark layer. A separate model was trained for each of the 13 elements of the SFGS and then used to calculate the SFGS subscores and composite score. The intra-class coefficient of the automated grading system was calculated based on three clinicians experienced in the grading of facial palsy. RESULTS: The inter-rater reliability of the CNN with the additional facial landmarks increased in performance for all composite scores compared to the previous model. The intra-class coefficient for the composite SFGS score increased from 0.87 to 0.91, the resting symmetry subscore increased from 0.45 to 0.62, the symmetry of voluntary movement subscore increased from 0.89 to 0.92, and the synkinesis subscore increased from 0.75 to 0.78. CONCLUSION: The integration of a facial landmark layer into the CNN significantly improved the reliability of the automated SFGS, reaching a performance level comparable to human observers. These results were attained without increasing the dataset underscoring the impact of incorporating facial landmarks into a CNN. These findings indicate that the automated SFGS with facial landmarks is a reliable tool for assessing patients with a unilateral peripheral facial palsy and is applicable in an eHealth environment.01 januari 202
Galileo, mathematics and the manifold of experience
No full textItem does not contain fulltextSymposium “Symbolic Intentionality and Symbolic Technologies”, 30 januari 2025Invited lectur
Aantastbaarheid van rechtshandelingen na schending van het Unierechtelijke financiële recht
No full textContains fulltext :
318355.pdf (Publisher’s version ) (Closed access)Radboud University, 23 april 2025Promotores : Sieburgh, C.H., Verhagen, H.L.E.XXIX, 529 p
Modular Criticality Analysis for Dynamic Fault Trees
No full textContains fulltext :
316737.pdf (Publisher’s version ) (Open Access
Automated grading of peripheral facial palsy
No full textContains fulltext :
317677.pdf (Publisher’s version ) (Open Access)The Sunnybrook Facial Grading System (SFGS) is a recommended grading system to determine the severity of a facial palsy. The quality of grading depends on the experience of the observer due to the SFGS learning curve. This makes the SFGS less accessible to researchers, students, trainee clinicians, other untrained co-workers, or for the implementation of home monitoring of patients. This dissertation shows that a relatively inexpensive webcam-sized camera system can be successfully used to create three-dimensional video recordings to determine changes in the facial surface. Additionally, an automated SFGS was implemented, with the results showing that the reliability of the automated SFGS is comparable to that of human evaluators experienced in performing the SFGS. This represents a first step towards the implementation of an automated SFGS, which can be used in clinics, research, or at home in an eHealth environment.Radboud University, 07 april 2025Promotores : Maal, T.J.J., Marres, H.A.M. Co-promotores : Ingels, K.J.A.O., Speksnijder, C.M.173 p
Copenhagen consensus statements on workplace health enhancing physical activity programmes
No full textContains fulltext :
316556.pdf (Publisher’s version ) (Open Access)Workplace health enhancing physical activity (HEPA) programmes are associated with physical activity promotion and reduction of sedentary time among employees. Whilst the workplace is often considered an appropriate setting for such programmes, however, ethical and implementation challenges remain. Furthermore, debate still exists concerning programme rationale, efficacy, effectiveness, and impact. In 2024, 24 researchers from twelve countries collaborated to establish evidence-based consensus statements concerning such programmes. The consensus was developed through an iterative process involving experts from sociology, psychology, sport policy, physiology and promoting and assessing movement behaviours. In total 36 consensus statements and 23 areas identified for further research were produced. A broad definition of HEPA was adopted that included structured and unstructured activities, whilst HEPA was distinguished from occupational and leisure-time activities. Consensus highlighted, for example, the importance of multi-level approaches to programme implementation, the need for managerial support, and the need to tailor programme design. The consensus also demonstrated the need for more research on the long-term impacts of workplace HEPA programmes, to investigate the potential role of technology, and to further understand the influence of socio-cultural and individual factors on participation.11 p
Developing and evaluating the extended epistemic vigilance framework
No full textContains fulltext :
316600.pdf (Publisher’s version ) (Open Access
Pace or plummet? How psychological contract breach shapes employee performance over time
No full textContains fulltext :
317883.pdf (Publisher’s version ) (Open Access)This study examines how psychological contract breach (PCB) influences employee performance trajectories over a year. By analyzing supervisor-rated performance across four intervals, two performance trajectories were identified: "Steady Achievers" (95.5%), who maintained high performance, and "Ebb and Flow Achievers" (4.5%), whose performance initially rose but later declined. PCB was associated with lower baseline performance in both groups, with "Ebb and Flow Achievers" experiencing less growth and sharper declines. These findings challenge the assumption of uniform consequences of PCB, offering a nuanced, trajectory-based perspective that captures the evolving and differential effects of PCB on employee performance over time. Moreover, they highlight the need for tailored support, including regular check-ins, accountability partnerships, and wellness resources.17 maart 202512 p