Non-Invasive Tongue-Based HCI System Using Deep Learning for Microgesture Detection
Bibliographic record
Abstract
Tongue-based Human-Computer Interaction (HCI) systems have surfaced as alternative input devices offering significant benefits to individuals with severe disabilities.However, these systems often employ invasive methods such as dental retainers, tongue piercings, and multiple mouth electrodes.These methods, due to hygiene issues and obtrusiveness, are deemed impractical for daily use.This paper presents a novel non-invasive tonguebased HCI system that utilizes deep learning for microgesture detection.The proposed system overcomes the limitations of previous methods by non-invasively detecting gestures.This is accomplished by measuring tongue vibrations via an accelerometer positioned on the Genioglossus muscle, thereby eliminating the need for in-mouth installations.The system's performance was evaluated by comparing the classification results of deep learning with four widely-used supervised machine learning algorithms, namely K-Nearest Neighbors (KNN), Support Vector Machines (SVM), Decision Trees, and Random Forests.Raw data were preprocessed in both time and frequency domains to extract relevant patterns before classification.In addition, a deep learning Convolutional Neural Network (CNN) model was trained on the raw data, leveraging its proficiency in processing time series data and capturing intricate patterns automatically using convolutional and pooling layers.The CNN model demonstrated a 97% success rate in tongue gesture detection, indicating its high accuracy.The proposed system is also lowprofile, lightweight, and cost-effective, making it suitable for daily use in various contexts.This study thus introduces a non-invasive, efficient, and practical approach to tongue-based HCI systems.
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 | 0.000 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.000 |
| Insufficient payload (model declined to judge) | 0.003 | 0.001 |
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".