Register now After registration you will be able to apply for this opportunity online.
Investigating the Transient Effects of Alcohol Intake on Movement Planning Abilities using Deep Learning
This thesis aims to utilize deep learning techniques to analyze eye-tracking data during a goal-directed upper limb task, particularly focusing on participants under the influence of alcohol. The objective is to develop digital health metrics that can elucidate differences in movement planning.
Keywords: Deep Learning, Eye Tracking, Alcohol, Algorithm, Computer Vision, Technology-assisted Assessment, Upper Limb, Movement Planning, Study, Data Analysis
We performed a study involving 50 healthy participants, who underwent various clinical assessments, balance tests, and the Virtual Peg Insertion Test (VPIT), a technology-based upper limb assessment, linked to an eye-tracking device. These assessments were carried out at four distinct time points: with Breath Alcohol Content (BAC) levels of 0.0 ‰, 0.6‰, 1.0‰, and after a two-hour period of sobering up. The study aimed to 1. potentially create a controlled model simulating ataxic patients and 2. explore the temporary effects of alcohol on upper limb function.
To gain insights into movement planning abilities during alcohol consumption, a deep learning-based algorithm is to be devised, focusing on analyzing eye movements during the VPIT. Subsequently, digital health metrics will be formulated to describe movement planning based on the algorithm's outputs.
We performed a study involving 50 healthy participants, who underwent various clinical assessments, balance tests, and the Virtual Peg Insertion Test (VPIT), a technology-based upper limb assessment, linked to an eye-tracking device. These assessments were carried out at four distinct time points: with Breath Alcohol Content (BAC) levels of 0.0 ‰, 0.6‰, 1.0‰, and after a two-hour period of sobering up. The study aimed to 1. potentially create a controlled model simulating ataxic patients and 2. explore the temporary effects of alcohol on upper limb function. To gain insights into movement planning abilities during alcohol consumption, a deep learning-based algorithm is to be devised, focusing on analyzing eye movements during the VPIT. Subsequently, digital health metrics will be formulated to describe movement planning based on the algorithm's outputs.
The goal of this project is to develop a deep learning algorithm and associated digital health metrics for analyzing data from the alcohol study.
The goal of this project is to develop a deep learning algorithm and associated digital health metrics for analyzing data from the alcohol study.
- Conduct research on potential deep learning algorithms
- Develop a deep learning algorithm
- Develop digital health metrics
Analyze eye-tracking data from the alcohol study
- Conduct research on potential deep learning algorithms - Develop a deep learning algorithm - Develop digital health metrics Analyze eye-tracking data from the alcohol study
- Background in computer science, engineering,
or related fields
- Proficient programming skills in Python
- Experience with deep learning methodologies
- Motivated, independent, and creative working
- Excellent proficiency in English and/or German
- Background in computer science, engineering, or related fields - Proficient programming skills in Python - Experience with deep learning methodologies - Motivated, independent, and creative working - Excellent proficiency in English and/or German
If you are interested or have any further questions, please contact:
Nadine Domnik (nadine.domnik@hest.ethz.ch).
Please include a short motivational letter, your CV, and transcripts of records in your application.
If you are interested or have any further questions, please contact: Nadine Domnik (nadine.domnik@hest.ethz.ch). Please include a short motivational letter, your CV, and transcripts of records in your application.