Improved Diverse Gaussian HMM and SVM ML Technique for Sensor Fault Detection and Classification in Air Quality Monitoring System
Bibliographic record
Abstract
Internet of Things (IoT) based real-time applications are highly prone to sensor faults because of their deployment in a risky environment.One of the important applications of IoT that is in great demand in this modern era is the air quality monitoring system because of the increase in air pollution over the years around the globe.Hence handling the reliability issue of air quality sensors is of great concern.In this article, a data based diverse fault detection and classification technique is implemented to overcome the sensor fault issue involved in air quality monitoring systems.The proposed work is a two-phase process; first, a Gaussian Hidden Markov Model (GHMM) is used to perform sensor fault detection on real-time air quality sensor data to detect the presence of fault in sensors followed by performing sensor fault classification using a Support Vector Machine (SVM) on the faulty sensor data obtained from fault detection to identify the most difficult to find sensor fault types like 'Out of bounds' and 'Spike fault'.The proposed technique efficiently carries out sensor fault detection and classification with an overall accuracy of 99.48%.Compared to Machine Learning (ML) algorithms like Logistic Regression (LR), Naive Bayes (NB), and Multi-Layer Perceptron (MLP) the diverse proposed technique works well with a precision of 99.50%, recall of 99.08%, and an F1-score of 99.53%.
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 | 0.001 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| 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 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".