arXiv subjects

Daniel Eckhoff

Publications and source records attributed to Daniel Eckhoff.

2 recordsLinked to original sources

arXiv2022

Virtual Reality Therapy for the Psychological Well-being of Palliative Care Patients in Hong Kong

In this paper we introduce novel Virtual Reality (VR) and Augmented Reality (AR) treatments to improve the psychological well being of patients in palliative care, based on interviews with a clinical psychologist who has successfully implemented VR assisted interventions on palliative care patients in the Hong Kong hospital system. Our VR and AR assisted interventions are adaptations of traditional palliative care therapies which simultaneously facilitate patients communication with family and friends while isolated in hospital due to physical weakness and COVID-19 related restrictions. The first system we propose is a networked, metaverse platform for palliative care patients to create customized virtual environments with therapists, family and friends which function as immersive and collaborative versions of 'life review' and 'reminiscence therapy'. The second proposed system will investigate the use of Mixed Reality telepresence and haptic touch in an AR environment, which will allow palliative care patients to physically feel friends and family in a virtual space, adding to the sense of presence and immersion in that environment.

cs.HC↗

arXiv2018

Cardiopulmonary resuscitation quality parameters from motion capture data using Differential Evolution fitting of sinusoids

Cardiopulmonary resuscitation (CPR) is alongside electrical defibrillation the most crucial countermeasure for sudden cardiac arrest, which affects thousands of individuals every year. In this paper, we present a novel approach including sinusoid models that use skeletal motion data from an RGB-D (Kinect) sensor and the Differential Evolution (DE) optimization algorithm to dynamically fit sinusoidal curves to derive frequency and depth parameters for cardiopulmonary resuscitation training. It is intended to be part of a robust and easy-to-use feedback system for CPR training, allowing its use for unsupervised training. The accuracy of this DE-based approach is evaluated in comparison with data of 28 participants recorded by a state-of-the-art training mannequin. We optimized the DE algorithm hyperparameters and showed that with these optimized parameters the frequency of the CPR is recognized with a median error of $\pm 2.9$ compressions per minute compared to the reference training mannequin.

cs.NE↗