Technology Category
Computer Vision: Motion & TrackingCognitive Modeling & Cognitive Systems: Neural Spike CodingMachine Learning: Deep Generative Models & Autoencoders
Imputation of Missing Data in Smooth Pursuit Eye Movements Using a Self-Attention-based Deep Learning Approach
🤖 AI Summary
Smooth pursuit eye movement data frequently exhibit prolonged missing segments due to blinks and tracking loss, severely compromising reliable biomarker extraction for neurodegenerative disorders such as Parkinson’s disease. To address this, we propose the first deep temporal imputation framework integrating self-attention mechanisms with a domain-specific autoencoder, jointly modeling temporal dynamics and preserving spectral characteristics. Evaluated on 5,504 eye movement sequences from 172 Parkinson’s patients and healthy controls, our method achieves statistically significant improvements in MAE, MRE, and RMSE over state-of-the-art methods—particularly under long-duration gaps (>200 ms), where it maintains high robustness and physiological plausibility. Key innovations include: (i) the first application of self-attention to oculomotor gap imputation; and (ii) a structure-function co-designed autoencoder enabling joint time-frequency optimization. This framework delivers high-fidelity reconstructed data essential for clinical oculomotor biomarker analysis.
Technology Category
Application Category
📝 Abstract
Missing data is a relevant issue in time series, especially in biomedical sequences such as those corresponding to smooth pursuit eye movements, which often contain gaps due to eye blinks and track losses, complicating the analysis and extraction of meaningful biomarkers. In this paper, a novel imputation framework is proposed using Self-Attention-based Imputation networks for time series, which leverages the power of deep learning and self-attention mechanisms to impute missing data. We further refine the imputed data using a custom made autoencoder, tailored to represent smooth pursuit eye movement sequences. The proposed approach was implemented using 5,504 sequences from 172 Parkinsonian patients and healthy controls. Results show a significant improvement in the accuracy of reconstructed eye movement sequences with respect to other state of the art techniques, substantially reducing the values for common time domain error metrics such as the mean absolute error, mean relative error, and root mean square error, while also preserving the signal's frequency domain characteristics. Moreover, it demonstrates robustness when large intervals of data are missing. This method offers an alternative solution for robustly handling missing data in time series, enhancing the reliability of smooth pursuit analysis for the screening and monitoring of neurodegenerative disorders.
Problem
Research questions and friction points this paper is trying to address.
Imputing missing data in smooth pursuit eye movements
Using self-attention deep learning for time series gaps
Enhancing reliability for neurodegenerative disorder screening
Innovation
Methods, ideas, or system contributions that make the work stand out.
Self-Attention-based deep learning for imputation
Custom autoencoder refining smooth pursuit sequences
Robust handling of large missing data intervals
🔎 Similar Papers
No similar papers found.
