PhD Candidate at Amsterdam UMC and the University of Amsterdam. I research the application of computer vision/deep learning algorithms to process high-dimensional (3D+time) CT perfusion data for treatment decision support for patients suffering from an acute ischemic stroke.

Research internship at Nikhef (National Institute for Subatomic Physics) as a member of the dark matter research group. I conducted a research project applying Deep Neural Networks to XENON1T, a leading direct detection dark matter experiment. In this work, I developed a new algorithm that improves the vertex position reconstruction, one of the experiment's core algorithms, significantly. In addition, I developed another algorithm that extends the experimental reach in the low-energy domain, an important global research area with favourable prospects for a future publication. The work may be applicable to other analyses in this field of research as well. Grade: 9/10.

Research internship at the Computational Intelligence Group of the Department of Computer Science (VU Amsterdam). My thesis 'Evolving Neural Networks for Real-Time Object Recognition' presents an evolutionary approach to obtain deep neural networks with acceptable accuracy for real-time object recognition on low-performance computing hardware. Accepted as a paper to the 2019 IEEE Symposium Series on Computational Intelligence. Grade: 8.5/10.Publication:Gongjin Lan, Lucas De Vries, and Shuai Wang, Evolving neural network for real-time object recognition, 2019 IEEE Symposium Series on Computational Intelligence (SSCI), IEEE, 2019. DOI: 10.1109/SSCI44817.2019.9002863

Performing a spectral analysis on X-ray data to detect highly ionized outflows from the inner regions of supermassive black holes. Grade: 8/10.