Search

Today, the most convenient way of estimating an individual's blood-alcohol concentration requires a breathalyzer device and intense user cooperation, which severely limits the scope of potential applications. We develop and study a machine-learning model that detects alcohol inebriation based on a person's eye gaze and eye closure. We investigate the relative contribution of individual features derived from eye gaze and eye closure to the model. In order to train and experimentally evaluate the model, we collect— and share—a new data set with participants in baseline and alcohol-intoxicated states. We find that the model can in fact detect the consumption of a moderate amount of alcohol; the accuracy grows significantly with increasing blood alcohol concentration. The most relevant features turn out to relate to the velocity and acceleration profiles during fixations and saccades. From our proof-of-concept study, we can conclude that contactless inebriation detection based on eye gaze is in fact possible, albeit data need to be collected on an industrial scale to reach practical applicability. Potential applications of contactless inebriation detection include the detection of impaired drivers or operators of other hazardous machinery as well as health-monitoring applications. [ABSTRACT FROM AUTHOR]

We present a new machine learning benchmark for reading task classification with the goal of advancing EEG and eye-tracking research at the intersection between computational language processing and cognitive neuroscience. The benchmark task consists of a cross-subject classification to distinguish between two reading paradigms: normal reading and task-specific reading. The data for the benchmark is based on the Zurich Cognitive Language Processing Corpus (ZuCo 2.0), which provides simultaneous eye-tracking and EEG signals from natural reading of English sentences. The training dataset is publicly available, and we present a newly recorded hidden testset. We provide multiple solid baseline methods for this task and discuss future improvements. We release our code and provide an easy-to-use interface to evaluate new approaches with an accompanying public leaderboard: www.zuco-benchmark.com. [ABSTRACT FROM AUTHOR]

Distributional properties of fixations and saccades are known to constitute biometric characteristics. Additionally, high-frequency micro-movements of the eyes have recently been found to constitute biometric characteristics that allow for faster and more robust biometric identification than just macro-movements. Micro-movements of the eyes occur on scales that are very close to the precision of currently available eye trackers. This study therefore characterizes the relationship between the temporal and spatial resolution of eye tracking recordings on one hand and the performance of a biometric identification method that processes micro-and macro-movements via a deep convolutional network. We find that that the deteriorating effects of decreasing both, the temporal and spatial resolution are not cumulative. We observe that on low-resolution data, the network reaches performance levels above chance and outperforms statistical approaches. [ABSTRACT FROM AUTHOR]

Eye movements can be used to analyze a viewer's cognitive capacities or mental state. Neural networks that process the raw eye-tracking signal can outperform methods that operate on scan paths preprocessed into fixations and saccades. However, the scarcity of such data poses a major challenge. We therefore develop SP-EyeGAN, a neural network that generates synthetic raw eye-tracking data. SP-EyeGAN consists of Generative Adversarial Networks; it produces a sequence of gaze angles indistinguishable from human ocular micro- and macro-movements. We explore the use of these synthetic eye movements for pre-training neural networks using contrastive learning. We find that pre-training on synthetic data does not help for biometric identification, while results are inconclusive for the detection of ADHD and gender classification. However, for the eye movement-based assessment of higher-level cognitive skills such general reading comprehension, text comprehension, and the distinction of native from non-native readers, pre-training on synthetic eye-gaze data improves the models' performance and even advances the state-of-the-art for reading comprehension. The SP-EyeGAN model, pre-trained on GazeBase, along with the code for developing your own raw eye-tracking machine learning model with contrastive learning, is available at https://github.com/aeye-lab/sp-eyegan. [Display omitted] • Neural embeddings of eye movements can be used as input to any model. • SP-EyeGAN establishes new state-of-the-art performance on text comprehension. • Performance of gender classification is effected by the number of training samples. [ABSTRACT FROM AUTHOR]