skip to main content


Title: Crossed Eyes: Domain Adaptation for Gaze-Based Mind Wandering Models
The effectiveness of user interfaces are limited by the tendency for the human mind to wander. Intelligent user interfaces can combat this by detecting when mind wandering occurs and attempting to regain user attention through a variety of intervention strategies. However, collecting data to build mind wandering detection models can be expensive, especially considering the variety of media available and potential differences in mind wandering across them. We explored the possibility of using eye gaze to build cross-domain models of mind wandering where models trained on data from users in one domain are used for different users in another domain. We built supervised classification models using a dataset of 132 users whose mind wandering reports were collected in response to thought-probes while they completed tasks from seven different domains for six minutes each (five domains are investigated here: Illustrated Text, Narrative Film, Video Lecture, Naturalistic Scene, and Reading Text). We used global eye gaze features to build within- and cross- domain models using 5-fold user-independent cross validation. The best performing within-domain models yielded AUROCs ranging from .57 to .72, which were comparable for the cross-domain models (AUROCs of .56 to .68). Models built from coarse-grained locality features capturing the spatial distribution of gaze resulted in slightly better transfer on average (transfer ratios of .61 vs .54 for global models) due to improved performance in certain domains. Instance-based and feature-level domain adaptation did not result in any improvements in transfer. We found that seven gaze features likely contributed to transfer as they were among the top ten features for at least four domains. Our results indicate that gaze features are suitable for domain adaptation from similar domains, but more research is needed to improve domain adaptation between more dissimilar domains.  more » « less
Award ID(s):
1920510
NSF-PAR ID:
10284387
Author(s) / Creator(s):
Date Published:
Journal Name:
ETRA '21 Full Papers: ACM Symposium on Eye Tracking Research and Applications
Page Range / eLocation ID:
1 to 12
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. null (Ed.)
    The DeepLearningEpilepsyDetectionChallenge: design, implementation, andtestofanewcrowd-sourced AIchallengeecosystem Isabell Kiral*, Subhrajit Roy*, Todd Mummert*, Alan Braz*, Jason Tsay, Jianbin Tang, Umar Asif, Thomas Schaffter, Eren Mehmet, The IBM Epilepsy Consortium◊ , Joseph Picone, Iyad Obeid, Bruno De Assis Marques, Stefan Maetschke, Rania Khalaf†, Michal Rosen-Zvi† , Gustavo Stolovitzky† , Mahtab Mirmomeni† , Stefan Harrer† * These authors contributed equally to this work † Corresponding authors: rkhalaf@us.ibm.com, rosen@il.ibm.com, gustavo@us.ibm.com, mahtabm@au1.ibm.com, sharrer@au.ibm.com ◊ Members of the IBM Epilepsy Consortium are listed in the Acknowledgements section J. Picone and I. Obeid are with Temple University, USA. T. Schaffter is with Sage Bionetworks, USA. E. Mehmet is with the University of Illinois at Urbana-Champaign, USA. All other authors are with IBM Research in USA, Israel and Australia. Introduction This decade has seen an ever-growing number of scientific fields benefitting from the advances in machine learning technology and tooling. More recently, this trend reached the medical domain, with applications reaching from cancer diagnosis [1] to the development of brain-machine-interfaces [2]. While Kaggle has pioneered the crowd-sourcing of machine learning challenges to incentivise data scientists from around the world to advance algorithm and model design, the increasing complexity of problem statements demands of participants to be expert data scientists, deeply knowledgeable in at least one other scientific domain, and competent software engineers with access to large compute resources. People who match this description are few and far between, unfortunately leading to a shrinking pool of possible participants and a loss of experts dedicating their time to solving important problems. Participation is even further restricted in the context of any challenge run on confidential use cases or with sensitive data. Recently, we designed and ran a deep learning challenge to crowd-source the development of an automated labelling system for brain recordings, aiming to advance epilepsy research. A focus of this challenge, run internally in IBM, was the development of a platform that lowers the barrier of entry and therefore mitigates the risk of excluding interested parties from participating. The challenge: enabling wide participation With the goal to run a challenge that mobilises the largest possible pool of participants from IBM (global), we designed a use case around previous work in epileptic seizure prediction [3]. In this “Deep Learning Epilepsy Detection Challenge”, participants were asked to develop an automatic labelling system to reduce the time a clinician would need to diagnose patients with epilepsy. Labelled training and blind validation data for the challenge were generously provided by Temple University Hospital (TUH) [4]. TUH also devised a novel scoring metric for the detection of seizures that was used as basis for algorithm evaluation [5]. In order to provide an experience with a low barrier of entry, we designed a generalisable challenge platform under the following principles: 1. No participant should need to have in-depth knowledge of the specific domain. (i.e. no participant should need to be a neuroscientist or epileptologist.) 2. No participant should need to be an expert data scientist. 3. No participant should need more than basic programming knowledge. (i.e. no participant should need to learn how to process fringe data formats and stream data efficiently.) 4. No participant should need to provide their own computing resources. In addition to the above, our platform should further • guide participants through the entire process from sign-up to model submission, • facilitate collaboration, and • provide instant feedback to the participants through data visualisation and intermediate online leaderboards. The platform The architecture of the platform that was designed and developed is shown in Figure 1. The entire system consists of a number of interacting components. (1) A web portal serves as the entry point to challenge participation, providing challenge information, such as timelines and challenge rules, and scientific background. The portal also facilitated the formation of teams and provided participants with an intermediate leaderboard of submitted results and a final leaderboard at the end of the challenge. (2) IBM Watson Studio [6] is the umbrella term for a number of services offered by IBM. Upon creation of a user account through the web portal, an IBM Watson Studio account was automatically created for each participant that allowed users access to IBM's Data Science Experience (DSX), the analytics engine Watson Machine Learning (WML), and IBM's Cloud Object Storage (COS) [7], all of which will be described in more detail in further sections. (3) The user interface and starter kit were hosted on IBM's Data Science Experience platform (DSX) and formed the main component for designing and testing models during the challenge. DSX allows for real-time collaboration on shared notebooks between team members. A starter kit in the form of a Python notebook, supporting the popular deep learning libraries TensorFLow [8] and PyTorch [9], was provided to all teams to guide them through the challenge process. Upon instantiation, the starter kit loaded necessary python libraries and custom functions for the invisible integration with COS and WML. In dedicated spots in the notebook, participants could write custom pre-processing code, machine learning models, and post-processing algorithms. The starter kit provided instant feedback about participants' custom routines through data visualisations. Using the notebook only, teams were able to run the code on WML, making use of a compute cluster of IBM's resources. The starter kit also enabled submission of the final code to a data storage to which only the challenge team had access. (4) Watson Machine Learning provided access to shared compute resources (GPUs). Code was bundled up automatically in the starter kit and deployed to and run on WML. WML in turn had access to shared storage from which it requested recorded data and to which it stored the participant's code and trained models. (5) IBM's Cloud Object Storage held the data for this challenge. Using the starter kit, participants could investigate their results as well as data samples in order to better design custom algorithms. (6) Utility Functions were loaded into the starter kit at instantiation. This set of functions included code to pre-process data into a more common format, to optimise streaming through the use of the NutsFlow and NutsML libraries [10], and to provide seamless access to the all IBM services used. Not captured in the diagram is the final code evaluation, which was conducted in an automated way as soon as code was submitted though the starter kit, minimising the burden on the challenge organising team. Figure 1: High-level architecture of the challenge platform Measuring success The competitive phase of the "Deep Learning Epilepsy Detection Challenge" ran for 6 months. Twenty-five teams, with a total number of 87 scientists and software engineers from 14 global locations participated. All participants made use of the starter kit we provided and ran algorithms on IBM's infrastructure WML. Seven teams persisted until the end of the challenge and submitted final solutions. The best performing solutions reached seizure detection performances which allow to reduce hundred-fold the time eliptologists need to annotate continuous EEG recordings. Thus, we expect the developed algorithms to aid in the diagnosis of epilepsy by significantly shortening manual labelling time. Detailed results are currently in preparation for publication. Equally important to solving the scientific challenge, however, was to understand whether we managed to encourage participation from non-expert data scientists. Figure 2: Primary occupation as reported by challenge participants Out of the 40 participants for whom we have occupational information, 23 reported Data Science or AI as their main job description, 11 reported being a Software Engineer, and 2 people had expertise in Neuroscience. Figure 2 shows that participants had a variety of specialisations, including some that are in no way related to data science, software engineering, or neuroscience. No participant had deep knowledge and experience in data science, software engineering and neuroscience. Conclusion Given the growing complexity of data science problems and increasing dataset sizes, in order to solve these problems, it is imperative to enable collaboration between people with differences in expertise with a focus on inclusiveness and having a low barrier of entry. We designed, implemented, and tested a challenge platform to address exactly this. Using our platform, we ran a deep-learning challenge for epileptic seizure detection. 87 IBM employees from several business units including but not limited to IBM Research with a variety of skills, including sales and design, participated in this highly technical challenge. 
    more » « less
  2. We present and evaluate methods to redirect desktop inputs such as eye gaze and mouse pointing to a VR-embedded avatar. We use these methods to build a novel interface that allows a desktop user to give presentations in remote VR meetings such as conferences or classrooms. Recent work on such VR meetings suggests a substantial number of users continue to use desktop interfaces due to ergonomic or technical factors. Our approach enables desk-top and immersed users to better share virtual worlds, by allowing desktop-based users to have more engaging or present "cross-reality" avatars. The described redirection methods consider mouse pointing and drawing for a presentation, eye-tracked gaze towards audience members, hand tracking for gesturing, and associated avatar motions such as head and torso movement. A study compared different levels of desktop avatar control and headset-based control. Study results suggest that users consider the enhanced desktop avatar to be human-like and lively and draw more attention than a conventionally animated desktop avatar, implying that our interface and methods could be useful for future cross-reality remote learning tools. 
    more » « less
  3. null (Ed.)
    Stack Overflow is commonly used by software developers to help solve problems they face while working on software tasks such as fixing bugs or building new features. Recent research has explored how the content of Stack Overflow posts affects attraction and how the reputation of users attracts more visitors. However, there is very little evidence on the effect that visual attractors and content quantity have on directing gaze toward parts of a post, and which parts hold the attention of a user longer. Moreover, little is known about how these attractors help developers (students and professionals) answer comprehension questions. This paper presents an eye tracking study on thirty developers constrained to reading only Stack Overflow posts while summarizing four open source methods or classes. Results indicate that on average paragraphs and code snippets were fixated upon most often and longest. When ranking pages by number of appearance of code blocks and paragraphs, we found that while the presence of more code blocks did not affect number of fixations, the presence of increasing numbers of plain text paragraphs significantly drove down the fixations on comments. SO posts that were looked at only by students had longer fixation times on code elements within the first ten fixations. We found that 16 developer summaries contained 5 or more meaningful terms from SO posts they viewed. We discuss how our observations of reading behavior could benefit how users structure their posts. 
    more » « less
  4. Cross-domain collaborative filtering recommenders exploit data from other domains (e.g., movie ratings) to predict users’ interests in a different target domain (e.g., suggest music). Most current cross-domain recommenders focus on modeling user ratings but pay limited attention to user reviews. Additionally, due to the complexity of these recommender systems, they cannot provide any information to users to support user decisions. To address these challenges, we propose Deep Hybrid Cross Domain (DHCD) model, a cross-domain neural framework, that can simultaneously predict user ratings, and provide useful information to strengthen the suggestions and support user decision across multiple domains. Specifically, DHCD enhances the predicted ratings by jointly modeling two crucial facets of users’ product assessment: ratings and reviews. To support decisions, it models and provides natural review-like sentences across domains according to user interests and item features. This model is robust in integrating user rating and review information from more than two domains. Our extensive experiments show that DHCD can significantly outperform advanced baselines in rating predictions and review generation tasks. For rating prediction tasks, it outperforms cross-domain and single-domain collaborative filtering as well as hybrid recommender systems. Furthermore, our review generation experiments suggest an improved perplexity score and transfer of review information in DHCD. 
    more » « less
  5. Educational VR may help students by being more engaging or improving retention compared to traditional learning methods. However, a student can get distracted in a VR environment due to stress, mind-wandering, unwanted noise, external alerts, etc. Student eye gaze can be useful for detecting these distraction. We explore deep-learning-based approaches to detect distractions from gaze data. We designed an educational VR environment and trained three deep learning models (CNN, LSTM, and CNN-LSTM) to gauge a student’s distraction level from gaze data, using both supervised and unsupervised learning methods. Our results show that supervised learning provided better test accuracy compared to unsupervised learning methods. 
    more » « less