Research on Efficient Gait Authentication Techniques Based on Transformer and XGBoost Hybrid Models
Bibliographic record
Abstract
This paper addresses the challenges of traditional identity authentication methods by proposing a novel gait-based authentication technology. This paper introduces a lightweight model based on the Transformer architecture, which utilizes the self-attention mechanism to effectively capture global correlations in gait sequences while enabling efficient parallel computation. Our experimental framework employs the HTC Nexus One dataset from McGill University, incorporating innovative data preprocessing techniques such as multi-gait combination sampling and threshold-based gait segmentation to significantly enhance feature representation and recognition reliability. The experimental results demonstrate that our model achieves a remarkable accuracy of 93.82% on the test set, surpassing existing gait recognition methods. To further enhance classification performance, this paper integrates XGBoost as the final classifier, developing a hybrid model that combines Transformer and XGBoost. This hybrid approach achieves an impressive accuracy of 96.17% on the test set, representing a substantial improvement over the standalone Transformer model. Our research not only reduces computational complexity but also offers an innovative solution for identity authentication in high-security scenarios. The proposed methodology shows promising application potential in various fields, including intelligent security systems and smart home technologies, paving the way for more robust and efficient authentication 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 | 0.001 | 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 | 0.001 |
| Scholarly communication | 0.001 | 0.002 |
| Open science | 0.002 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 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".