Location: Eindhoven (High Tech Campus)
Type: Internship (full time)
Start date: August/September 2020
Duration: 6-12 months
It can be discussed to make this assignment suitable for thesis.
In this role, you have the opportunity to
Derive context information in an Intensive Care Unit (ICU) that can be used to enhance care algorithms but also to learn about what is going on around an ICU patient. The new video-based algorithms are developed using ICU clinical data.
You are responsible for
Review of current literature on existing methods.
Design algorithm(s) to track activities of different stakeholders in the room.
Test, validate and benchmark the algorithm with provided lab data and potentially clinical data.
Create a demo to demonstrate the functionality of the algorithms.
Documentation of results and report in detail on your scientific and algorithmic work and discuss next steps.
You are a part of
The Patient Care & Measurements department is an international team of 40+ highly skilled and enthusiastic professionals representing various clinical, scientific, engineering and business disciplines. You will work closely together with team members working on (3D) camera algorithms.
To succeed in this role, you should have the following skills and experience
You are studying towards your Master in Sciences in Electrical Engineering, Computer Science, Biomedical Engineering
A good knowledge of image/video processing, computer vision and machine learning
Knowledge and proven background/skills programming skills (MATLAB, C/C++, Python, or comparable)
Fluent in oral and written English
Take responsibilities and act on these
You are enthusiastic, focused and have a result-driven mind-set
In return, we offer you
The opportunity to gain experience at Philips Research were we are working towards new solutions to improve the patient care in intensive care unit (ICU). For this, we are developing new innovative video-based algorithms for example to early detect delirium in ICU patients. In an ICU, there is a lot of interaction between the different clinical stakeholders/visitors and the patient. For the development of robust and reliable algorithms, it is important to understand more on the context during the measurement.