Advanced topics in eye tracking: Classification of eye movements

Daniel Scheffold, a Tobii Certified Instructor from Tobii Pro has started a 4-part series of advanced topics in eye tracking.logo_pro

Check it out below!


This is the first part of four in our mini-series on advanced topics in eye tracking. We begin with a topic that is fundamental to the technique: classification of eye movements.
 
Why do we need to classify eye movements in the first place?
 
Most modern eye trackers are video-based. Images of the eye captured at regular intervals, the sampling rate, are processed to calculate instantaneous gaze position. This discrete data stream must then be converted back to the informative, continuous eye movements for analysis. This digital-to-analog conversion is accomplished by passing the raw gaze samples through an event detection algorithm called the fixation filter.
 
Fixation filters can come with adjustable parameters to enable tailoring their characteristics to specific circumstances. Choosing the appropriate parameters is of fundamental importance in properly classifying eye movements and calculating valid metrics based on the resulting fixations and saccades.

How do I apply it?
 
There are a variety of fixation filters and researchers may choose based on those commonly used in their field. If using Tobii Pro Studio for analysis, you can choose from several with varying levels of complexity and adjustability.
 
The Tobii Pro Studio default is the Tobii I-VT fixation filter. As a classification filter that operates on the velocity of eye movement, it is effective and commonly used in human behavior research.
You can find the algorithm description here: Download White Paper: Tobii I-VT Fixation Filter

Tip: As reviewers get more demanding and want to understand better how you processed your data, we encourage you to cite this White Paper and the parameters chosen in your methodology section if you use this filter.

Our White Paper on the Default Values Tobii I-VT Filter describes how we determined the optimal parameter values of the Tobii I-VT Fixation Filter.

As this is a generic eye movement filter, it is reasonable to review and validate the parameters of your eye movement filter empirically. You find a great hands-on guide for this is in Chapter 5.3, pp. 153 in “Eye Tracking – A Comprehensive Guide to Methods and Measures” from Holmqvist & Nyström et al. (Oxford University Press, 2011). In Tobii Pro Studio, the Velocity Chart can aid you in this process (see Tobii Pro Studio manual Appendix 14.2)

To summarize, how you classify eye movements in your data is an extremely important step in your research and can have a massive influence on the calculated measures, so choose carefully.

Recommended reading:
Chapter 5, Estimating Oculomotor Events from Raw Data Samples, Holmqvist & Nyström et al., 2011.


If you’d like to learn the basics of eye movements and events (e.g. what are fixations, saccades, smooth pursuit, vergence, VOR), we touched base on it in this article here.

Next up…we will be taking a deeper look at the three different spaces used in eye tracking and how they relate to drawing areas-of-interest. Watch out for the article on eyetracking.com.sg!

Objective Experience speaks at Agile Singapore Conference 2016

Join our senior eye-tracking consultant, Lynette Goh, at the Agile Singapore Conference 2016, for a talk on using eye-tracking in Agile testing environments.


Eyes are the windows to our souls: how eye tracking aids UX in agile environments

Date: Tuesday, October 6

Time: 11:30am – 12:15pm

Venue: Hotel Fort Canning


agile-singapore-2016
For more details on the event, visit here for the full list of talks/activities you can attend at the conference.

Our favourite read: Eye Tracking the User Experience: A Practical Guide to Research by Aga Bojko

Among all the books that discuss about eye-tracking and user experience, our personal favourite has to be:

eye-tracking-the-user-experience

Eye Tracking the User Experience

A Practical Guide to Research

By Aga Bojko

As you might have expected, this book will teach readers how to do eye-tracking studies the right way, choosing the right device, analysing and presenting the right way, and so on and so forth…..Yes, it virtually covers every aspect of what you need to know and consider before adding eye-tracking to your research toolkit.

Richly illustrated and clearly witten, this book stands apart from similar books in that it presents information in an approachable and accessible way. Despite all the technical bits, reading it certainly did not give us the feelings of reading a textbook!

 

However, the main reason why we like this book is the main theme that runs throughout the book: “Think first, Track later”. Aga Bokjo advocates that eye-tracking will not always be the most appropriate research methodology, unless the data it generates can be used to answer particular research objectives. Check out an excerpt for the book here.

By being brutally honest about the real benefits and limitations of eye-tracking, this book offers a refreshing take on the controversial research method. Coming from a background that blends rigorous academic research with an abundance of UX industry experience, Aga Bokjo gives us “actionable insights” and guidance to adopting (or not) the eye-tracking research methodology. Because of the scientific rigour that Aga Bokjo tries to instill in readers, this book appeals not only to the UX industry, but to the academic world as well.

Do you want to find out how eye tracking can help your research? Do drop by Objective Experience and pick up a copy of the book. Alternatively drop us an email at info@objectiveexperience.com for a knowledge sharing session.

Monash University’s Department of Marketing to Host Eye Tracking Research Interest Group Meeting

Do you have an interest in eye tracking and behavioural research?

Join esteemed speakers from Monash University at their (interdisciplinary) eye-tracking research interest group meeting on Friday 2 September, hosted by the Department of Marketing. The aim is to present and discuss current eye tracking research and help generate a research agenda.

monashspeakers

Panel of Speakers (left to right):

  1. Dr Kristian Rotaru (Department of Accounting)
  2. Professor Kyle Murray (Department of Marketing)
  3. Dr Dominic Thomas (Department of Marketing)

The topic of discussion will be on how to make sense of pupil dilation data. Pupil dilations are proxy measures of arousal. This session will present and discuss issues encountered and exploratory findings from two projects that use pupil dilation data extracted from eye-tracking recordings.


Date: Friday, September 2

Time: 2:30-4:30pm

Venue: Monash University, Building S, Level 3, Ramler Room, 26 Sir John Monash Drive, Caulfield East 3145

To RSVP, please fill out this form by close of business, Thursday 1 September.
Please remember to sign the attendance list when you arrive at the event.


Click here to check if you have already RSVPed.
If you can no longer attend, please update your RSVP here.

For any further queries, please email nicky.auster@monash.edu

Objective Eye Tracking at AS4SAN conference in Sydney

Objective Eye Tracking was a Gold Exhibition Partner for this conference. The conference was held at the University of Technology, Sydney.

AS4SAN is an interdisciplinary society devoted to the study of central nervous system mechanisms (e.g. neural, hormonal, cellular, genetic) underlying social and affective behaviour in the context of both normal development and functioning and clinical disorders.

IMG_20160624_090553

We were doing demos of the Tobii Glasses 2 as well as other screen mounted eye trackers. We also had a 15 minute presentation slot to talk a bit about how eye trackers work and where they can be used. Thanks to all the professors, students and other delegates who stopped by to say hello and share your ideas.

IMG_20160623_111759 IMG_20160624_090732

Video Highlights from Understanding Human Behavior with Eye Tracking workshop

The Understanding Human Behavior with Eye Tracking workshop was held in the Institute on Asian Consumer Insight (ACI) in Nanyang School of Business (Nanyang Technological University) on 21 March 2016. Check out the highlights in the videos below! We’ve also included the interviews with the individual speakers had with our CEO and ACI Fellow, James Breeze.

Three speakers (Dr. Adam Roberts, Haojiang Ying, and Shannon Chia) spoke about how people navigated in indoor environments using certain architectural cues, how people paid covert attention to and perceived emotions with limited facial information, and what athletes paid attention to while playing their sport (badminton) when compared to novices.

Interview with Dr. Adam Roberts

Interview with Ying Haojiang

Interview with Shannon Chia

The Eye Tracking way: a new training and assessment method

“Many traditional assessment strategies in medical education rely on tabulating learners’ scores in order to obtain grades,” says Dr. Szulewski (Queen’s University Professor, Emergency Medicine). “In the real world, medical learners are faced with the need to make many decisions in a short time period, which increases their cognitive load and puts a strain on working memory. We have shown that we can now measure cognitive load in an unobtrusive way during medical assessments.”

There has been increasing interest in using alternative methods to teach and assess medical students and young doctors. Is there a better way to show medical students what exactly they need to look out for when diagnosing a patient or conducting a surgery other than diagrams and auditory listening? Written and practical examinations also have its shortfalls, especially since the actual working environment these future doctors will work in are high-pressured and the decision-making process differs when they are in a high-pressured setting versus an examination laboratory in a university.

Already there are some educators looking towards eye tracking as a tool to help teach medical subjects and assess students with. How is that done?

Visual learning

Educators are able to easily show visually by way of videos that contain eye tracking gaze data what students are supposed to see and do. Students can observe, mimic, and adapt what their educators do much more easily this way than compared to educators describing their techniques by finger-pointing.

Novice versus Experienced

Assessment is a major component in any form of learning. Eye tracking metrics can be used to assess who is a novice practitioner and who is more experienced. In the University of Arizona, Krupinski et al. (2006) have tried using eye tracking on light microscopy for diagnostic pathology and found differences between fully trained pathologists and medical students/residents. Others have also tested the usage of eye tracking to assess surgical skills (e.g. Lee et al., 2010; Zheng, Jiang & Atkins, 2015), abnormalities search on radiographs (e.g. Turgeon & Lam, 2016), ultrasound-guided regional anesthesia (UGRA) (e.g., Harrison et al., 2016) and even optic disc examinations (e.g. O’Neill et al., 2011). As research progresses, algorithms can be developed to assess medical students’ performance in their diagnostic and even surgical tasks. Having a quantifiable tool to assess expertise can be a useful in comparing educational interventions, which can potentially improve the rate at which students developed expertise.

The potential of eye tracking being established as a valid and reliable method of teaching and assessment grows as more research is being done in this area. With products like the Tobii Pro Glasses 2, this method becomes increasingly accessible in a natural environment.
The future of education is here.