2 June 2023 at 15:00 in REC GS.08
Deep learning models are increasingly used in automating detection and classification tasks and quite successfully so. Examples range from image classification, x-ray interpretations to eye-movement event detection. In all these cases, there is also much left to be desired. Interpretability & reproducibility of modeling exercises are hard to come by in these networks, dataset training bias is a pervasive problem. A more classical approach to these problems suffers less from these drawbacks. I will present work we did in model-based classification of eye-movements. The modeling work is based on good-old-fashioned hidden Markov models which prove to be robust, interpretable, extendable, and replicable & reproducible. The current approach also outperforms other commonly used algorithms in this area.
We developed gazeHMM, an algorithm that uses a hidden Markov model as a generative model, has few critical parameters to be set by users, and does not require human-coded data as input. The algorithm classifies gaze data into fixations, saccades, and optionally post-saccadic oscillations and smooth pursuits. I will present an overview of some of the problems with deep-learning approaches to eye-movement classification and discuss the hidden Markov alternative to this.