Comparison of Anomaly Detection Using Statistical Method and Deep Learning Method in Jakarta Air Quality Index Data
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
Anomaly in the air quality index (AQI) is essential to detect as an early warning of air pollution disasters that may occur in the future.Therefore, recognizing the characteristics of anomaly detection methods in AQI data is crucial.This research aims to compare the statistical and deep learning methods in detecting anomalies in the Jakarta AQI data.The data used is Jakarta AQI and calendar variation from January 1, 2019, to February 29, 2024.The method used in this study is a statistical method, namely distributed lag, and a deep learning method, namely autoencoder and LSTM autoencoder, where this method detects anomalies based on the four-sigma rule.The characteristics of anomaly detection using the distributed lag method tend to be more sensitive, with low false negative values and high false positive values.Meanwhile, anomaly detection using the autoencoder method tends to have a high false negative value with a low false positive value.On the other hand, anomaly detection using the LSTM autoencoder method tends to have a low false negative value with a false positive value that is not too high.Considering the characteristics of the methods, the distributed lag method is more recommended.
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.
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 | 0.003 | 0.001 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.002 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 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 it