A5029721579- Optical Network Technologies
- Advanced Fiber Laser Technologies
- Surgical Simulation and Training
- Advanced Photonic Communication Systems
- Healthcare Operations and Scheduling Optimization
- Advanced Fiber Optic Sensors
- Neural Networks and Reservoir Computing
- Machine Learning in Healthcare
- Advanced X-ray and CT Imaging
- Artificial Intelligence in Healthcare and Education
- Musculoskeletal pain and rehabilitation
- Reservoir Engineering and Simulation Methods
- Photonic Crystal and Fiber Optics
- Human Pose and Action Recognition
- Optical Polarization and Ellipsometry
- Augmented Reality Applications
- Occupational Health and Safety Research
- Hospital Admissions and Outcomes
Delft University of Technology
2024-2025
Eindhoven University of Technology
2019-2020
Workflow insights can improve efficiency and safety in the Cardiac Catheterization Laboratory (Cath Lab). As manual analysis is labor-intensive, we aim for automation through camera monitoring. Literature shows that human poses are indicative of activities therefore workflow. a first exploration, evaluate how marker-less multi-human pose estimators perform Cath Lab. We annotated 2040 frames from ten multi-view coronary angiogram (CAG) recordings. Pose AlphaPose, OpenPifPaf OpenPose were run...
Efficient nonlinearity compensation in fiber-optic communication systems is considered a key element to go beyond the "capacity crunch". One guiding principle for previous work on design of practical schemes that fewer steps lead better systems. In this paper, we challenge assumption and show how carefully multi-step approaches provide performance-complexity trade-offs than their few-step counterparts. We consider recently proposed learned digital backpropagation (LDBP) approach, where...
In this article, we propose a model-based machine-learning approach for dual-polarization systems by parameterizing the split-step Fourier method Manakov-PMD equation. The resulting combines hardware-friendly time-domain nonlinearity mitigation via recently proposed learned digital backpropagation (LDBP) with distributed compensation of polarization-mode dispersion (PMD). We refer to as LDBP-PMD. train LDBP-PMD on multiple PMD realizations and show that it converges within 1% its peak dB...
This study evaluates the performance of deep learning models in prediction end time procedures performed cardiac catheterization laboratory (cath lab). We employed only clinical phases derived from video analysis as input to algorithms. Our results show that InceptionTime and LSTM-FCN yielded most accurate predictions. achieves Mean Absolute Error (MAE) values below 5 min Symmetric Percentage (SMAPE) under 6% at 60-s sampling intervals. In contrast, LSTM with attention mechanism standard...
The integration of medical technology in the operating room has revolutionized surgical workflows and team dynamics. However, this progress coincides with a critical global shortage nurses high turnover rate within existing nursing workforce, impacting patient care quality, nurses' well-being, hospital finances. This study investigates impact technological complexity on workload job satisfaction intra-operative nurses, focusing open surgery, minimally invasive robotic-assisted surgery...
Abstract Purpose Perioperative staff shortages are a problem in hospitals worldwide. Keeping the content and motivated is challenge busy hospital setting of today. New operating room technologies aim to increase safety efficiency. This causes shift from interaction with patients technology. Objectively measuring this could aid design supportive technological products, or optimal planning for high-tech procedures. Methods 35 Gynaecological procedures three different technology levels...
Workflow insights can enable safety- and efficiency improvements in the Cardiac Catheterisation Laboratory (Cath Lab). Human pose tracklets from video footage provide a source of workflow information. However, occlusions visual similarity between personnel make Cath Lab challenging environment for re-identification individuals. We propose human tracker that addresses these problems specifically, test it on recordings real coronary angiograms. This uses no information re-identification,...
For the efficient compensation of fiber nonlinearity, one guiding principles appears to be: fewer steps are better and more efficient.We challenge this assumption show that carefully designed multi-step approaches can lead performancecomplexity trade-offs than their few-step counterparts.
We propose a model-based machine-learning approach for polarization-multiplexed systems by parameterizing the split-step method Manakov-PMD equation. This performs hardware-friendly DBP and distributed PMD compensation with performance close to PMD-free case.
For the efficient compensation of fiber nonlinearity, one guiding principles appears to be: fewer steps are better and more efficient. We challenge this assumption show that carefully designed multi-step approaches can lead performance-complexity trade-offs than their few-step counterparts.
We propose a model-based machine-learning approach for polarization-multiplexed systems by parameterizing the split-step method Manakov-PMD equation. This performs hardware-friendly DBP and distributed PMD compensation with performance close to PMD-free case.