Mixed-reality (MR) P300 interfaces can register selectable destinations, such as wheelchair goals, directly in the user's surroundings. When the cues disappear between flashes, however, the user must retain an intended target that is no longer visible. We tested whether such an interface supports target selection and whether giving each cue a stable colour-shape identity improves it compared with visually uniform spheres. Six healthy adults completed four trials in each cue condition of a 5x5 row/column task on a head-mounted MR display, with EEG from Fz, Cz, and Pz. Shrinkage linear discriminant analysis was evaluated with nested validation in which complete trials were held out from class balancing, hyperparameter selection, and fitting. Both conditions evoked a parietal target-related positivity. The decoded cell was correct in 18 of 48 held-out trials, against 1.9 expected by chance (binomial p < 1e-12), and in three participants individually. Cue format made no detectable difference: complete-target accuracy was 9/24 in both conditions (paired difference 0.0 percentage points, 95% CI [-37, 37]), and held-out AUC was 0.609 for spheres and 0.585 for object cues. Disappearing-stimulus MR P300 selection is therefore feasible under strict trial-level evaluation, but the benefit of object identity, if any, is too small to resolve in a pilot of this size.
Figures & tables
Fig. 1: Cue conditions, trial structure, and analysis. (a) Uniform spheres. (b) Object-distinguishable cues; each cell has a unique colour–shape identity. (c) Top: after a 5-s target preview all cues are hidden and reappear in place only as 200-ms row and column flashes. Bottom: in a conventional display all items stay visible and a flash changes the colour of a row (orange). (d) Identical acquisition, preprocessing, features, and complete-trial-held-out decoding in both conditions.
Outcome
Spheres
Object
Difference [95% CI]
p
Pz diff. ( μ V)
1.44±1.63
1.63±1.33
0.19[−1.09,1.46]
.72
AUC
.609±.134
.585±.092
−.023[−.102,.055]
.47
Row acc. (%)
41.7±40.8
62.5±30.6
20.8[−14.0,55.7]
.25
Column acc. (%)
58.3±37.6
50.0±38.7
−8.3[−29.8,13.1]
.63
Complete target (%)
37.5±44.0
37.5±41.1
0.0[−37.1,37.1]
1.00
TABLE I: Participant-level outcomes ( N=6 , mean ± SD)
Fig. 2: (a) Grand-average Pz target-minus-non-target difference (mean ± SEM, N=6 ); grey marks the 250–600 ms window. (b) Correct cells out of eight held-out trials per participant, split by condition. The dashed line is the chance expectation (0.32); two or more correct is significant for one participant (binomial p<0.05 ). (c) Complete-target accuracy after each completed flash sequence (mean ± SEM across participants), decoded offline by the trial-held-out models; the dashed line is chance (0.04).
Selecting out-of-reach objects is a fundamental task in mixed reality (MR). Existing methods rely on a single cue or deterministically fuse multiple cues, leading to performance degradation when the dominant cue becomes unreliable. In this work, we introduce a probabilistic cue integration framework that enables flexible combination of multiple user-generated cues for intent inference. Inspired by natural grasping behavior, we instantiate the framework with pointing direction and grasp gestures as a new interaction technique, Point&Grasp. To this end, we collect the Out-of-Reach Grasping (ORG) dataset to train a robust likelihood model of the gestural cue, which captures grasping patterns not present in existing in-reach datasets. User studies demonstrate that our selection method with cue integration not only improves accuracy and speed over single-cue baselines, but also remains practically effective compared to state-of-the-art methods across various sources of ambiguity. The dataset and code are available at https://github.com/drlxj/point-and-grasp.
Xuejing Luo, Hee-Seung Moon, Christian Holz +1
Department of Information and Communication Engineering, School of Electrical Engineering Aalto University Helsinki, Finland ELLIS Institute Helsinki, Finland · School of Computer Science and Engineering Chung-Ang University Seoul, Republic of Korea · ETH Zürich Zurich, Switzerland
P300 brain-computer interface (BCI) spellers can provide hands-free communication for people with severe motor impairments. Modern pipelines combine multiple individually promising components, often assuming that 'more-is-better'. We tested this assumption using a four-component full-factorial experiment varying the inclusion of Euclidean Alignment (EA), xDAWN spatial filtering, subject calibration, and language model priors on a public P300 dataset. Performance was evaluated using accuracy, repetitions, and information transfer rate (ITR) with mixed-effects models. Results show that the value of components is conditional rather than additive. Calibration was the strongest singular contributor, while EA compensated for its absence in zero-calibration settings. Adding independently useful components could also reduce performance, revealing component anti-synergy. Contrary to conventional wisdom, LM support was not universally beneficial: its effect depends strongly on the strength of the underlying EEG pipeline, while results from a larger LM showed a similar pattern. Together, these findings challenge maximal 'all-on' pipeline design and highlight the value of selecting spatial and language-support components according to the quality of available EEG evidence.
Lucas Yang, Rui Liu, Fusheng Wang
Parkland High School Allentown, PA, USA · Dept. of Computer Science Stony Brook University Stony Brook, NY, USA · Dept. of Computer Science Dept. of Biomedical Informatics Stony Brook University Stony Brook, NY, USA
P300-based brain-computer interfaces (BCIs) enable communication by decoding stimulus-evoked EEG responses into character selections without requiring voluntary motor output. Reliable P300 detection remains difficult because of low response amplitude and signal-to-noise ratio, while practical spellers require accurate character selection with few stimulus repetitions and low computational cost. We propose a compact deep learning architecture that combines xDAWN spatial filtering for event-related potential enhancement and dimensionality reduction, a fixed frequency-selective filter bank, and convolutional feature learning for spatio-temporal EEG decoding. Depthwise-separable convolutions and progressive average pooling reduce computational complexity while retaining discriminative temporal information. The resulting target/non-target classifier contains only 5,100 trainable parameters. We evaluated the model on two public benchmarks, BCI Competition II Dataset IIb and BCI Competition III Dataset II, and compared it with established P300 decoding methods across different numbers of stimulus repetitions. The model achieved an information transfer rate of 17.8 bits/min with two repetitions on BCI Competition III and 40.5 bits/min on BCI Competition II, demonstrating a favorable accuracy-speed trade-off. These results suggest that combining domain-informed spatial and spectral priors with compact neural networks can support efficient P300 decoding for EEG-based BCI communication.
Mohammad Mahdi Habibi Bina, Mohammad Reza Daliri
Neuroscience & Neuroengineering Research Laboratory, Biomedical Engineering Department, School of Electrical Engineering, Iran University of Science and Technology (IUST), Tehran, Iran