High Frequency EEG Artifact Detection with Uncertainty via Early Exit Paradigm
arXiv:2107.10746
Abstract
Electroencephalography (EEG) is crucial for the monitoring and diagnosis of brain disorders. However, EEG signals suffer from perturbations caused by non-cerebral artifacts limiting their efficacy. Current artifact detection pipelines are resource-hungry and rely heavily on hand-crafted features. Moreover, these pipelines are deterministic in nature, making them unable to capture predictive uncertainty. We propose E4G, a deep learning framework for high frequency EEG artifact detection. Our framework exploits the early exit paradigm, building an implicit ensemble of models capable of capturing uncertainty. We evaluate our approach on the Temple University Hospital EEG Artifact Corpus (v2.0) achieving state-of-the-art classification results. In addition, E4G provides well-calibrated uncertainty metrics comparable to sampling techniques like Monte Carlo dropout in just a single forward pass. E4G opens the door to uncertainty-aware artifact detection supporting clinicians-in-the-loop frameworks.
arXiv commentICML 2021 Workshop on Human In the Loop Learning
References in corpus (8)
- Adam: A Method for Stochastic Optimization
- PyTorch: An Imperative Style, High-Performance Deep Learning Library
- Bayesian Convolutional Neural Networks with Bernoulli Approximate Variational Inference
- Adaptive Neural Networks for Efficient Inference
- Subject-Aware Contrastive Learning for Biosignals
- The Benefit of the Doubt: Uncertainty Aware Sensing for Edge Computing Platforms
- Uncertainty-Aware COVID-19 Detection from Imbalanced Sound Data
- Stochastic-Shield: A Probabilistic Approach Towards Training-Free Adversarial Defense in Quantized CNNs