Improved Neural Signal Classification in a Rapid Serial Visual Presentation Task Using Active Learning

Abstract

The application space for brain-computer interface (BCI) technologies is rapidly expanding with improvements in technology. However, most real-time BCIs require extensive individualized calibration prior to use, and systems often have to be recalibrated to account for changes in the neural signals due to a variety of factors including changes in human state, the surrounding environment, and task conditions. Novel approaches to reduce calibration time or effort will dramatically improve the usability of BCI systems. Active Learning (AL) is an iterative semi-supervised learning technique for learning in situations in which data may be abundant, but labels for the data are difficult or expensive to obtain. In this paper, we apply AL to a simulated BCI system for target identification using data from a rapid serial visual presentation (RSVP) paradigm to minimize the amount of training samples needed to initially calibrate a neural classifier. Our results show AL can produce similar overall classification accuracy with significantly less labeled data (in some cases less than 20%) when compared to alternative calibration approaches. In fact, AL classification performance matches performance of 10-fold cross-validation (CV) in over 70% of subjects when training with less than 50% of the data. To our knowledge, this is the first work to demonstrate the use of AL for offline electroencephalography (EEG) calibration in a simulated BCI paradigm. While AL itself is not often amenable for use in real-time systems, this work opens the door to alternative AL-like systems that are more amenable for BCI applications and thus enables future efforts for developing highly adaptive BCI systems.

Online and Offline Domain Adaptation for Reducing BCI Calibration Effort

“…As in [51], [53], we also performed comprehensive statistical tests to check if the performance differences among the six algorithms (BL1 was not included because it is not iterative) were statistically significant. We used the area-underperformance-curve (AUPC) [31], [51], [53] to assess overall performance differences among these algorithms. The AUPC is the area under the curve of the BCAs obtained at each of the 30 runs, and is normalized to [0, 1].…”

“…The newly labeled test data are then integrated with the groundtruth training data to retrain the model, and hence to improve it iteratively. 4) Active learning, which optimally selects the most informative unlabeled samples to label [22], [31], [48], [50]. There are many criteria to determine which unlabeled samples are the most informative [42].…”

Improving EEG-Based Driver Fatigue Classification Using Sparse-Deep Belief Networks

“…The potential future direction of this research includes: (i) real-time driver fatigue with the active transfer learning approach for new user adaptation (Wu et al, 2014; Marathe et al, 2016; Wu, 2016), (ii) improvement of the classification result through an intelligent fusion algorithm, and (iii) testing the efficacy of hybrid driver fatigue detection systems using a combination of physiological measurement strategies known to be related to fatigue status, such as brain signal measurement using electroencephalography (EEG), eye movement and facial tracking systems using camera and electrooculography (EOG), and heart rate variability measurement using electrocardiography (ECG).…”

Towards the automated localisation of targets in rapid image-sifting by collaborative brain-computer interfaces

“…One of the new systems for human augmentation focuses on cortically-coupled vision: the use of a BCI for triaging imagery in order to speed up the detection of images of interest amongst a series of distractors [7, 13–15]. If the ratio of targets vs non-targets is sufficiently low (i.e., around 10%), a P300 Event-Related Potential (ERP) is elicited in response to targets [16], and its detection allows for the classification of images into one of these two categories.…”