CNN-CCA: A deep learning approach for anomaly detection in metro rail sensor time-series data
Bibliographic record
Abstract
The Internet of Things (IoT) offers new challenges in estimating correlations among data from multiple connected devices to understand their behaviors. Canonical Correlation Analysis (CCA) can be used to measure correlations among several observed variables. Different CCA methods have been proposed in the literature including probabilistic, sparse, kernel, discriminative, and deep learning-based CCAs. However, existing CCA approaches are limited by assumptions of linearity, reliance on predefined kernels, or difficulty in modeling localized patterns in high-frequency IoT sensor data. In this research, we explore two methods, linear CCA and non-linear deep learning-based CCA. Experiments demonstrate the effectiveness of CCA in detecting correlation in synthetic and metro rail time series sensor data collected from Autonomous Train (AT) signaling systems. Also, we propose a novel Convolutional Neural Network (CNN) based CCA method to detect correlation-based mappings and combine it with statistical anomaly detection methods in collective anomaly detection. The results indicate strong performance with an F1-score of 89.0% and a sensitivity of 94.1%, which can pave the way for the application of the proposed models to real-time collective anomaly detection and CCA in IoT systems.
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 | 0.003 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.002 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 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".