A5086447602- Face recognition and analysis
- Artificial Intelligence in Healthcare and Education
- Cutaneous Melanoma Detection and Management
- 3D Shape Modeling and Analysis
- Ethics and Social Impacts of AI
- Human Pose and Action Recognition
- AI in cancer detection
- Face and Expression Recognition
- Disaster Response and Management
- Face Recognition and Perception
- Image Enhancement Techniques
- Adversarial Robustness in Machine Learning
- COVID-19 diagnosis using AI
- AI in Service Interactions
- Social Robot Interaction and HRI
- Video Surveillance and Tracking Methods
- Death Anxiety and Social Exclusion
- Generative Adversarial Networks and Image Synthesis
- Radiology practices and education
- Digital Media Forensic Detection
- Single-cell and spatial transcriptomics
- Cardiac Arrest and Resuscitation
Eindhoven University of Technology
2020-2023
Philips (Netherlands)
2023
Ludwig-Maximilians-Universität München
2021
Robots increasingly act as our social counterparts in domains such healthcare and retail. For these human-robot interactions (HRI) to be effective, a question arises on whether we trust robots the same way humans. We investigated determinants competence warmth, known influence interpersonal development, development HRI, what role anthropomorphism plays this interrelation. In two online studies with 2 × between-subjects design, of robot (Study 1) warmth 2) HRI. Each study explored respective...
This paper documents how an ethically aligned co-design methodology ensures trustworthiness in the early design phase of artificial intelligence (AI) system component for healthcare. The explains decisions made by deep learning networks analyzing images skin lesions. trustworthy AI developed here used a holistic approach rather than static ethical checklist and required multidisciplinary team experts working with designers their managers. Ethical, legal, technical issues potentially arising...
Artificial Intelligence (AI) has the potential to greatly improve delivery of healthcare and other services that advance population health wellbeing. However, use AI in also brings risks may cause unintended harm. To guide future developments AI, High-Level Expert Group on set up by European Commission (EC), recently published ethics guidelines for what it terms “trustworthy” AI. These are aimed at a variety stakeholders, especially guiding practitioners toward more ethical robust...
This article's main contributions are twofold: 1) to demonstrate how apply the general European Union's High-Level Expert Group's (EU HLEG) guidelines for trustworthy AI in practice domain of healthcare and 2) investigate research question what does "trustworthy AI" mean at time COVID-19 pandemic. To this end, we present results a post-hoc self-assessment evaluate trustworthiness an system predicting multiregional score conveying degree lung compromise patients, developed verified by...
Abstract Building artificial intelligence (AI) systems that adhere to ethical standards is a complex problem. Even though multitude of guidelines for the design and development such trustworthy AI exist, these focus on high-level abstract requirements systems, it often very difficult assess if specific system fulfills requirements. The Z-Inspection® process provides holistic dynamic framework evaluate trustworthiness at different stages lifecycle, including intended use, design, development....
We present a set of deep learning models aimed at solving the hair counting problem in human skin images. All are end-to-end, providing mapping from input image to single scalar corresponding number hair. The list corresponds most common architectures that worked over-time various applications, where some networks were adapted output count. Results show autoencoder with skip connections work best for such end-to-end task, hinting increased performance when multi-task is used. With results...
While 3D body models have been vastly studied in the last decade, acquiring accurate from sparse information about subject and few computational resources is still a main open challenge.In this paper, we propose methodology for finding most relevant anthropometric measurements facial shape features prediction of an arbitrary segmented part.For evaluation, selected 12 that are easy to obtain or measure including age, gender, weight height; augmented them with parameters extracted scans.For...
This report is a methodological reflection on Z-Inspection$^{\small{\circledR}}$. Z-Inspection$^{\small{\circledR}}$ holistic process used to evaluate the trustworthiness of AI-based technologies at different stages AI lifecycle. It focuses, in particular, identification and discussion ethical issues tensions through elaboration socio-technical scenarios. uses general European Union's High-Level Expert Group's (EU HLEG) guidelines for trustworthy AI. illustrates both researchers...
Modeling and representing 3D shapes of the human body face is a prominent field due to its applications in healthcare, clothes, movie industry. In our work, we tackled problem synthesis by reducing meshes 2D image representations. We show that can naturally be modeled on grid. At same time, for more challenging geometries, proposed novel non-bijective 3D-2D conversion method mesh as plurality rendered projections Then, trained state-of-the-art vector-quantized variational autoencoder...
Skin cancer affects more than 3 million people only in the US. Comprehensive microscopic databases include around 30 thousand samples, limiting richness of patterns that can be presented to machine learning. To this end, generative models such as GANs have been proposed for creating realistic synthetic images but, despite their popularity, they are often difficult train and control. Recently an autoregressive approach based on a quantized autoencoder showed state art performances while being...
This report shares the experiences, results and lessons learned in conducting a pilot project ``Responsible use of AI'' cooperation with Province Friesland, Rijks ICT Gilde-part Ministry Interior Kingdom Relations (BZK) (both The Netherlands) group members Z-Inspection$^{\small{\circledR}}$ Initiative. took place from May 2022 through January 2023. During pilot, practical application deep learning algorithm province Fr\^yslan was assessed. AI maps heathland grassland by means satellite...