Enhancing vehicular emissions monitoring: A raw data processing and imputation model for heavy-duty diesel vehicles using remote OBD systems
Bibliographic record
Abstract
Currently, the raw data exported from the remote on-board diagnostics (OBD) monitoring systems of heavy-duty diesel vehicles exhibit significant issues with missing values in key items such as NOx concentration, posing challenges to effective emission regulation. This study proposes a systematic approach to raw data processing, provides a detailed analysis of NOx data missing patterns, and develops a weighted prediction model based on the AutoRegressive Moving Average with eXogenous variables- Long Short-Term Memory (ARMAX-LSTM) for missing data imputation. The ARMAX-LSTM model combines the capability of LSTM to capture nonlinear patterns with ARMAX’s ability to describe linear data, enhanced by dynamic weighting coefficients to improve prediction accuracy. Using Spearman rank correlation analysis, nine key parameters and the NOx downstream concentration itself were selected as input features for predicting and imputing missing values. Experimental results demonstrate that the proposed model reduces the mean squared error by 26.99% compared to the ARMAX baseline model and by 14.08% compared to the LSTM baseline model for randomly missing data. For naturally missing data segments, the model produced imputed curves with good continuity and stability, meeting engineering application requirements. This study provides technical support for improving OBD data quality and identifying high-emission vehicles, while also highlighting the model’s limitations in handling scenarios with all data items missing over continuous time periods. These findings offer directions for future model optimization.
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 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| 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 | 0.001 |
| 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".