Efficient human-machine control with asymmetric marginal reliability input devices

Abstract

Input devices such as motor-imagery brain-computer interfaces (BCIs) are often unreliable. In theory, channel coding can be used in the human-machine loop to robustly encapsulate intention through noisy input devices but standard feedforward error correction codes cannot be practically applied. We present a practical and general probabilistic user interface for binary input devices with very high noise levels. Our approach allows any level of robustness to be achieved, regardless of noise level, where reliable feedback such as a visual display is available. In particular, we show efficient zooming interfaces based on feedback channel codes for two-class binary problems with noise levels characteristic of modalities such as motor-imagery based BCI, with accuracy <75%. We outline general principles based on separating channel, line and source coding in human-machine loop design. We develop a novel selection mechanism which can achieve arbitrarily reliable selection with a noisy twostate button. We show automatic online adaptation to changing channel statistics, and operation without precise calibration of error rates. A range of visualisations are used to construct user interfaces which implicitly code for these channels in a way that it is transparent to users. We validate our approach with a set of Monte Carlo simulations, and empirical results from a human-in-the-loop experiment showing the approach operates effectively at 50-70% of the theoretical optimum across a range of channel conditions.

High-resolution neural recordings improve the accuracy of speech decoding

“…We quantified this phonological error using Hamming distance (bits) and showed that classifier errors were inversely proportional to phonological distance. Evaluating speech decoding models with phonological distance could lead to error correction that comparatively weighs similar phonemes with a lower cost versus phonemes with dissimilar features 58 . This phonological error metric could be used in addition to classification accuracy to optimize cost-functions for speech decoding algorithms.…”

High-resolution neural recordings improve the accuracy of speech decoding

“…We quantified this phonological error using Hamming distance (bits) and showed that classifier errors were inversely proportional to phonological distance. Evaluating speech decoding models with phonological distance could lead to error correction that comparatively weighs similar phonemes with a lower cost versus phonemes with dissimilar features 50 . This phonological error metric could be used in addition to classification accuracy to optimize cost-functions for speech decoding algorithms.…”

An Introduction to Bayesian Methods for Interaction Design

“…Such an interface represents, manipulates and displays uncertainty as a first-class value [50,51]. This can extend throughout the interaction loop, from low-level inference about user state from sensors [47], interpretation of pointing actions [27], probabilistic GUIs [10], text entry [56], error-tolerant interfaces [58], motion correlation [54] and 2D selection [37].…”