Combining Image Transformations to Solve Unseen Time Series Classification Problems
Bibliographic record
Abstract
Time Series Classification (TSC) is a key problem in several domains. One of the most popular approaches for TSC is to encode time series as images and use Computer Vision (CV) models for classification. The success of this approach has led to the emergence of several image transformation functions, each offering distinct insights valuable for different classification tasks. However, the significant difference between pre-existing image transformation functions makes it challenging to determine the most suitable transformation for a given TSC task. This work combines insights from various image transformations by concatenating DL-extracted black-box features obtained from several image representations of a given time series. These features are obtained from DL models that are trained on a large family of TSC datasets that have been transformed into one of several image transformations. As a result, each model is specialized in extracting insights from image representations of a specific type. To evaluate the generalizability of these insights, unseen TSC datasets are transformed into feature vector datasets by concatenating the features extracted from several specialized models, transforming a given TSC dataset into a dataset of feature vectors. This feature vector dataset is then learned using an ensemble model, whose initial results are improved using a Genetic Algorithm (GA). The approach is evaluated on the UCR archive and compared to several existing methods. The results show that the insights gained from image representations of time series are both useful and generalizable.
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.003 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.002 | 0.003 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.001 | 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 teacher head, 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".