Meta: Defining the Disaggregated Component Assignation Error Metric for Complex Time-Series Signal Data
Bibliographic record
Abstract
Researchers designing disaggregation algorithms have constant debates as to what accuracy and error metrics to use to evaluate/measure performance. What is the best measure of the classification accuracy of the disaggregated components? What is the best way to measure the error in the magnitude of each signal component? In some cases, metrics that measure regression (for example, power consumption estimation) tend to report better than actual performance. We propose a novel metric based on quadratic programming that we coined the disaggregated component assignation error (DCAE). DCAE (pronounced like the worddecay) is suitable for blind source separation problems such as unsupervised disaggregation because it is robust under a set of fundamental test cases for disaggregation. The main motivation for this metric is to detect poor unsupervised disaggregation performance in cases where traditional classification or estimation metrics cannot. DCAE is tested using time-series power data with the classical disaggregation problem of nonintrusive load monitoring (NILM). DCAE demonstrates automatically matching unsupervised disaggregated appliance power readings to their corresponding ground-truth components.IEEE SOCIETY/COUNCILPower and Energy Society (PES), Signal Processing Society (SPS)DATA TYPE/LOCATIONTime-Series, Signals; n/aDATA DOI/PIDn/a
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 | 0.009 | 0.033 |
| Meta-epidemiology (narrow) | 0.002 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.004 | 0.005 |
| Science and technology studies | 0.001 | 0.002 |
| Scholarly communication | 0.004 | 0.005 |
| Open science | 0.002 | 0.003 |
| Research integrity | 0.002 | 0.002 |
| Insufficient payload (model declined to judge) | 0.003 | 0.002 |
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".