3d density estimation using normalizing flows and its application to 3d reconstruction in cryo-EM

Generative models enable the researchers to address multiple problems spanning from noise removal to generating novel samples with properties of the domain. Generative models are commonly studied for images and in this project the idea will be expanded to 3D structures or volumes. Single-particle cryo-electron microscopy (cryo-EM) is a technique to estimate accurate 3D structures […]

Read More
Integrating Constraint Programming Scheduling into an AI Planner

OPTIC is a state of the art piece of research software designed to allow computers to autonomously plan complex tasks, such as construction projects, rail timetables and other planning and scheduling tasks. Currently, OPTIC handles the scheduling process using a technique known as Mixed Integer Programming (MIP). In this project, the aim will be to […]

Read More
Human Body Capture and Prediction from Rehearsed Live Performances

We address the problem of 3D human body motion capture and prediction to be used in the context of a live music concert performances. The difficulty of capturing the motion of a performer in this context comes from the harsh environment in which it takes place that includes strong and varying lighting, smoke generators, and […]

Read More
Machine learning-based data analysis for cancer targeted gene panels

Cancer develops from the accumulation of mutations in key genes, which drive disease progression in individual patients. Currently, cancer genomic analysis results in the reporting of dozens to hundreds of mutations and other genomic alterations, without providing any indication of which genes are the most functional, and relevant for the survival of the cancer cell. […]

Read More
High-throughput phenotyping of plant health using machine learning and computer vision

Phenotyping is used to develop new strains of plants, understand plant-affecting diseases (phyto-pathology) and evaluate the effects of various substances on plants. A growing variety of sensors and sensor technology is used to gather data used for phenotyping, in a non-destructive manner, and this overall process of data acquisition and analysis is being automated, leading […]

Read More
Linking Desktop and Mobile Devices to Back-end Systems Using HTML5

Recently, more researchers and developers are looking towards HTML5 mobile applications as a solution for targeting multiple devices and platforms. This is because the browser is becoming the default platform and its de facto standards are HTML5 and JavaScript. In the enterprise, compelling HTML5 mobile web applications that promise to offer the same functionality as […]

Read More
Verifying Security Properties in Modular Systems

Security is a huge concern in our digital society, especially with distributed systems like the Internet. Services deployed on such systems are frequently subject to malicious attacks; thus, verifying and enforcing its security is essential. One way of doing this is by using models like finite state automata. Past literature has explored how a system […]

Read More
Integration of scientific workflows in Geosciences

The 12-week research work will make a novel contribution to a large project called the Model Integration (MINT) framework, which in turn will improve the integration of scientific models in Environmental and Earth Sciences. Furthermore, this contribution to the MINT project will be a combination of best practices in reproducible research, Machine Learning, and domain […]

Read More
DreamWafer Intelligent Rapid Prototyping Platform for Electronic Systems

The WaferBoard™ is a “waffle iron” for prototyping electronic systems. In the envisioned concept, the user simply place components in the WaferBoard™ and close the cover. ”WaferBoard™ then senses the component contacts and recognizes the components and interconnects them. The prototype is now ready to be brought up and run. The candidate will do research […]

Read More