DT-GAIN: a Novel Framework for Multivariate Time-Series Data Imputation in Industrial Iot
Bibliographic record
Abstract
In Industrial Internet of Things (IIoT) applications, data from a variety of sensors is collected continuously to monitor and manage industrial processes. However, missing data caused by network disruptions, sensor malfunctions, or hardware failures seriously affects the performance of datadriven models, leading to unreliable predictions and increased maintenance costs. To address this challenge, we propose Decayaware Transformer-enhanced GAIN (DT-GAIN), a novel imputation framework for multivariate time-series data in IIoT applications. DT-GAIN extends and enhances the Generative Adversarial Imputation Nets (GAIN) framework by integrating the Transformer architecture, which captures long-range dependencies essential for accurate imputation of multivariate timeseries industrial data. In addition, DT-GAIN incorporates a timedecay mechanism that accounts for temporal irregularities by weighing observations based on their recency, thereby improving the ability of the proposed method to handle varying intervals between observations and missing values. In our research, we thoroughly compare DT-GAIN with state-of-the-art imputation methods, including LSTM-based GAIN (L-GAIN), Transformerbased GAIN (T-GAIN), the original GAIN, and SAITS. Our experimental results indicate that DT-GAIN outperforms the methods under investigation in terms of Root Mean Squared Error (RMSE) across various missing rates, particularly excelling in high-missing-data scenarios.
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 | 0.003 | 0.009 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| 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 | 0.003 | 0.002 |
| Research integrity | 0.001 | 0.003 |
| 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".