An LSTM Network With Neural Plasticity for Driver Fatigue Recognition on Real Roads
Bibliographic record
Abstract
Driver fatigue recognition is a highly challenging issue because of the complexity of road conditions, the dynamics of traffic flow, and the differences between drivers. This article proposes a biologically inspired long short-term memory (LSTM) model with neural plasticity (NP-LSTM) to improve the learning and memory ability of the traditional driver fatigue recognition method, thus improving effectiveness and robustness of monitoring and early-warning systems. First, the approximate entropy (ApEn) of the time series of drivers’ operation behaviors and vehicle status is investigated to explore the features of potential irregularity in fatigue-driving behaviors; then, inspired by the plastic learning mechanism of biological neurons, the intrinsic plasticity and synaptic plasticity are embedded into the LSTM neural network to realize the classified storage of complex road patterns, the dynamics of traffic flow, and the memory of drivers’ individual differences; finally, the dropout technology is introduced to further build a “sparse” neural network, which avoids the repeated training of an unchanged neural network under different conditions and enhances the adaptability and generalization of the whole monitoring and early-warning system. Experimental study on real roads is conducted to demonstrate the effectiveness of the proposed method. The results show that the average recognition accuracy is 88.73%, demonstrating a better recognition performance of the proposed method.
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) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.001 | 0.000 |
| 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".