Unsupervised Multivariate Time Series Anomaly Detection via Transformer-based models and Time Series Encoding
Bibliographic record
Abstract
This thesis has investigated the anomaly detection problem on multivariate time series. In particular, we have studied two different directions: the point-based approach and the range-based approach. For the point-based approach, one novel Transformer-based model: Transformer Conditional Variational Autoencoder (T-CVAE) has been designed and compared with state-of-the-art multivariate time series anomaly detection baselines. Through exhaustive experiments on three open-source datasets, our model T-CVAE has outperformed all baseline models in terms of the F1 score. On the other hand, for the range-based approach, we have developed and implemented two time series encoding techniques: Outer product Matrix (OM) and Gramian Angular Field Matrix (GAFM). We have compared the two methods with the existing Gram Matrix approach in the literature. Based on empirical experiment results, we have found that GAFM time series encoding performs best among the three in terms of the F1 measurement.
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 | 0.004 |
| 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 | 0.000 |
| Scholarly communication | 0.001 | 0.002 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.000 | 0.002 |
| 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".