A Novel Deep Learning Model for Subway PM <sub>2.5</sub> Prediction Using Neighborhood Component Analysis and Convolutional Latent Variables
Bibliographic record
Abstract
The accurate prediction of PM2.5concentrations in indoor environments is vital for public health and environmental protection, given the significant risks posed by poor indoor air quality. This study proposes a novel approach using the benefits of deep learning and metric learning for forecasting PM2.5concentrations. Our method integrates a 2-dimensional convolutional neural network, a latent variables model, and neighborhood component analysis, collectively forming the convolution latent variable-neighborhood component analysis (CLV-NCA) model. The 2-dimensional convolutional neural network extracts spatiotemporal features from the data, while the latent variables model reduces the model’s computational complexity by compressing these features. The neighborhood component analysis further enhances the model’s robustness, allowing it to adapt to the characteristics of various indoor environments and the complex nature of PM2.5data. The effectiveness of the CLV-NCA model is validated using indoor air quality data, demonstrating significant improvements over conventional models. Compared with the traditional linear partial least squares model, the proposed CLV-NCA model demonstrates approximately twice the accuracy, resulting in a 51.50% reduction in prediction error. This research contributes to the advancement of soft measurement modeling in indoor air quality monitoring, providing a robust and efficient tool for PM2.5prediction.
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 | 0.001 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| 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".