Register now After registration you will be able to apply for this opportunity online.
Automated Machine Learning assisted Performance Assessment during Medical Device Handling using Eye Tracking
In order to validate intended functionality and to guarantee patient safety, usability testing is indispensable in the development of medical devices. Eye Tracking Technology allows to quantify cognitive processes and therefore provides valuable insights into the user’s though processes during medical device usage. Recently, advances in machine learning has shown vast improvements for gaze guided human action recognition (HAR), potentially enabling the complete automation of performance assessment during usability evaluations.
Keywords: human action recognition; Eye Tracking; Machine Learning; Object Detection; Usability Evaluation; Medical Devices;Performance Assessment; Task Sequencing
The concept of the learning curve has been widely applied to augment the training of novices and
has been a central point in the pursuit of decrypting explicit competence measures of expert
operators. Eye tracking (ET) technology has been increasingly used to study characteristic
behavioral patterns of operators with different expertise. Recent advances have shown that the
visual behavior of experts do not change within the same handling task over time, while novices eye
movements gradually develop towards those of the expert. These findings are, however, yet to be
leverage for the analysis of product usability and ease-of-use.
The goal of this project is to investigate the possibility of determining the intuitiveness of a medical
device prototype based on the learning curve analysis of eye movement data.
The concept of the learning curve has been widely applied to augment the training of novices and has been a central point in the pursuit of decrypting explicit competence measures of expert operators. Eye tracking (ET) technology has been increasingly used to study characteristic behavioral patterns of operators with different expertise. Recent advances have shown that the visual behavior of experts do not change within the same handling task over time, while novices eye movements gradually develop towards those of the expert. These findings are, however, yet to be leverage for the analysis of product usability and ease-of-use. The goal of this project is to investigate the possibility of determining the intuitiveness of a medical device prototype based on the learning curve analysis of eye movement data.
•Testing, Validation & Improvement of HAR algorithm on new industry use cases.
•New recordings of a medical device handling to test the accuracy and robustness of the system
•Providing innovative approaches to the problems at hand
•Working with medical devices from a leading industry partner
•Testing, Validation & Improvement of HAR algorithm on new industry use cases. •New recordings of a medical device handling to test the accuracy and robustness of the system •Providing innovative approaches to the problems at hand •Working with medical devices from a leading industry partner
• Experience with object oriented programming (python, C++..) • Interest in machine learning and/or computer vision desirable • Interest in human behavior and product usability • Creativity and an affinity for hands-on work • Motivation and an independent work style
The chair of Product Development
and Engineering Design at the
ETH Zurich considers itself a center
for system-oriented product
development and innovation. Our
aspiration consists on the one hand
of the advancement and investigation
of methods and processes of
product development and on the
other hand of the development of
new technical systems. The purpose
of our daily work is to contribute
to the innovative ability and
competitiveness of Switzerland.
The chair of Product Development and Engineering Design at the ETH Zurich considers itself a center for system-oriented product development and innovation. Our aspiration consists on the one hand of the advancement and investigation of methods and processes of product development and on the other hand of the development of new technical systems. The purpose of our daily work is to contribute to the innovative ability and competitiveness of Switzerland.
• Semester/Master Thesis • Collaboration with a leading swiss medical device manufacturer
Felix Wang (PhD Candidate)
wangfe@ethz.ch
LEE O 207
Leonhardstrasse 21, 8092 Zürich
Felix Wang (PhD Candidate) wangfe@ethz.ch LEE O 207 Leonhardstrasse 21, 8092 Zürich
AusschreibungFS22.pdf
