An ensemble deep learning approach to evaluate haptic delay from a single trial EEG data
Bibliographic record
Abstract
Haptic technologies are becoming increasingly valuable in Human-Computer interaction systems as they provide means of physical interaction with a remote or virtual environment. One of the persistent challenges in tele-haptic systems, communicating haptic information over a computer network, is the synchrony of the delivered haptic information with the rest of the sensory modalities. Delayed haptic feedback can have serious implications on the user performance and overall experience. Limited research efforts have been devoted to studying the implication of haptic delay on the human neural response and relating it to the overall haptic experience. Deep learning could offer autonomous brain activity interpretation in response to a haptic experience such as haptic delay. In this work, we propose an ensemble of 2D CNN and transformer models that is capable of detecting the presence and redseverity of haptic delay from a single-trial Electroencephalography data. Two EEG-based experiments involving visuo-haptic interaction tasks are proposed. The first experiment aims to collect data for detecting the presence of haptic delay during discrete force feedback using a bouncing ball on a racket simulation, while the second aims to collect data for detecting the severity level (none, mild, moderate, severe) of the haptic delay during continuous force feedback via grasping/releasing of an object in a bucket. The ensemble model showed a promising performance with an accuracy of 0.9142 ± 0.0157 for detecting haptic delay during discrete force feedback and 0.6625 ± 0.0067 for classifying the severity of haptic delay during continuous force feedback (4 levels). These results were obtained based on training the model with raw EEG data as well as their wavelet transform using several wavelet kernels. This study is a step forward towards developing cognitive evaluation of the user experience while interaction with haptic interfaces.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.002 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".