• 2020-2024close
• Closed Access close
• Research software close
• Other research products close
• NEANIAS Space Research Community close

Understanding how trained deep neural networks achieve their inferred results is challenging but important for relating how patterns in the input data affect other patterns in the output results. We present a visual analytics approach to this problem that consists of two mappings. The so-called forward mapping shows the relative impact of user-selected input patterns to all elements of the output. The backward mapping shows the relative impact of all input elements to user-selected patterns in the output. Our approach is generically applicable to any regressor mapping between two multidimensional real-valued spaces (input to output), is simple to implement, and requires no specific knowledge of the regressor's internals. We demonstrate our method for two applications using image data-a MRI T1-to-T2 generator and a MRI-to-pseudo-CT generator.

Vrijdag 12 mei wordt voor het eerst het Fontys XR Event gehouden. Een kans voor docenten en studenten om kennis te maken en te delen over de toepassingen in het onderwijs van deze virtuele toolbox. XR staat voor Extended Reality. En die bestaat uit de technologieën Virtual reality (VR) en Augmented Reality (AR) en Mixed Reality. De eerste kent iedereen wel via de VR-brillen waarbij je je afgesloten van de buitenwereld in een virtuele wereld begeeft. Bij AR zie je de echte wereld maar is er iets aan toegevoegd. Denk bijvoorbeeld aan Pokemon Go of, dichter bij huis, de AR waarbij je de nieuwbouw van Fontys op campus Rachelsmolen via je smartphone al kunt zien.

Statistical Distribution (smart-dist) Package providing tools for Binomial, Gaussian distribution & Time Series (i.e. financial analytics) Data in Research Data Analytics User Count 3000+ Downloads from Source Published (smart-dist) Project Source Documentation Package Analysis Publisher Python Software Foundation (Python Package Index) Installation pip install smart-dist License MIT License

Manuale della programmazione software del modulo WheelchairController (che implementa una sedia a rotelle virtuale), progetto PDT 2/1-Rientr@: "Ambienti virtuali per facilitare il rientro al lavoro dopo incidente". Il manuale spiega tutte le funzionalità della libreria software (WheelchairControl) per l'uso del WheelchairController in un'applicazione client.

Major news outlets increasingly use immersive techniques in their journalistic productions. The idea is that, through the application of immersive technologies, the news consumer can engage with and be part of the story. However, we do not know, to what extent this promise is actually fulfilled in productions currently accessible to news audiences. This study uses a multi-step approach to fill this knowledge gap.

Introduction The subjective visual vertical (SVV) test evaluates subject’s perception of verticality and its deviations from the true earth’s gravitational vertical. It is a sensitive test of vestibular function and condition of central multisensory integration which is responsible for processing afferent inputs from various receptors of spatial orientation. Therefore the SVV reflects both peripheral and central vestibular function. Multiple sclerosis (MS) patients show significant deviations of the SVV most likely due the altered central integration of sensory inputs. Most prior studies measure SVV in upright head possition, therefore we aim to investigate possible SVV misperception during lateral head tilts for MS patients. Head tilts of 30 degree create conditions of noisy vestibular and somatosensory inputs needing higher degree of central integration thus we expect to find larger deviations of SVV for these patients and further confirm the importance of peripheral and central components for spatial orientation. Aim To measure the subjective visual vertical for multiple sclerosis patients in both upright and head tilt conditions and to evaluate its correlations with course of the disease. Methods The study group consists of MS patients with relapsing remitting form who are included in the study during the exacerbation of disease. Healthy volunteers without vestibular and neurological impairments will form the control group. The SVV is measured utilizing a portable virtual – reality based system QUEST 2 which enables to perform the test in static and dynamic conditions as well as during 30 degree lateral head tilts. Systematic errors during head tilt, i.e., A-effect and E-effect were also measured (E-effect is a typical SVV response during head tilts of ± 30°). Statistical analysis is performed using IBM SPSS 27.0. The Nonparametric Mann-Whitney U or Kruskal-Wallis tests were applied to compare quantitative data among independent groups. In all of the tests, the differences and relationships were considered statistically significant if P<0.05. Results Currently, 14 MS patients and 14 controls are enrolled in the study. SVV misperception was significantly higher in upright head position with dynamic conditions for MS patients. SVV misperception did not differ in static upright testing between MS and control groups. SVV misperception was significantly higher during lateral head tilts when compared to upright testing for both groups, but did not differ between groups. We found bilateral E – effect for 100% of the control group participants. The presence of A – effect was found on at least one of the tests (static or dynamic) for 8 (57%) MS patients: 3 bilateral and 5 unilateral Conclusions/discussion Upright SVV testing in dynamic conditions is more sensitive than static testing for detection of abnormalities in verticality perception for MS patients which is in line with previous data. Asymmetrical and noisy vestibular and proprioceptive signals lead to higher SVV errors during head-tilted SVV testing. MS patients did not show significantly higher misperception of verticality during lateral head tilts compared to healthy controls – opposite to our hypothesis. The presence of pathological A – effect could be potentially helpful for detecting central lesions with the SVV test. We conclude that clinicians should focus on the side to which the SVV deviates rather than the magnitude of perceptual errors when testing SVV in head tilt conditions.

Schizophrenia, a health and social problem of enormous importance and cost, is a serious mental disorder that has defiedresearchers for many years. Virtual and augmented reality (VR/AR) is proving to be a powerful experimental tool to study such complex cognitive processes. But there are no VR/AR tools for the systematic treatment of schizophrenia. Avatars do not incorporate adaptation, learning and evolution able to produce natural communication and interaction with humans. To significantly advance the state of art, it is proposed to supplement VR/AR with brain-computer interfaces (BCI) based onobtaining electrical brain signals. The project “Human-avatar symbiosis in cognitive cybertherapies: Proof of concept for auditory verbal hallucinations” assesses whether, through the complementary use of VR/AR and BCI, it is possible to achieve human-machine symbiosis (between a patient who hears voices and “his/her” avatar), which would provide an unforeseen advance. It relies on automatic adaptation, learning and evolution over BDI (beliefs-desires-intentions) models, proper of the intelligent agency paradigm inspired in social behaviour. The proof of concept will show if the proposal is an alternative/complement to conventional therapies of auditory verbal hallucinations and can guide the patient from a negative socio-emotional behaviour toward successful social situations

Statistical Visualisation Package (VizPack), providing the necessary tools for plotting visualisations in Research Data Analytics. User Count 3000+ Downloads from Source Published (VizPack) Project Source Documentation Package Analysis Publisher Python Software Foundation (Python Package Index) Installation pip install vizpack License MIT License