Advancing Energy Monitoring: Deep Learning for Automated Non-Smart Gas Meter Readings
Bibliographic record
Abstract
Despite the effectiveness of smart gas meters, many older, non-smart meters are still in use, creating significant challenges and costs associated with upgrading to advanced systems. To address this, developing artificial intelligence-powered frameworks to monitor natural gas consumption accurately from these non-smart meters is essential. This study introduces a deep learning (DL)-based framework designed to automate gas consumption readings from traditional, non-smart meters. Utilizing real-time image processing and innovative data augmentation techniques, the proposed system significantly improves measurement precision from 1 cubic meter to 0.001 cubic meters. This approach provides an efficient bridge between traditional and modern energy monitoring systems without necessitating the costly replacement of existing meters. The framework's development and evaluation leverage the NRC-GAMMA dataset, a meticulously gathered and labelled collection of gas meter images. An extensive quality control process was conducted on the dataset, which included several rounds of annotation and verification, to guarantee high accuracy and reliability. The proposed DL model's robust performance across various environmental conditions is enabled by advanced data augmentation strategies and DL algorithms, making it a versatile solution for a broader range of automated energy meter readings, contributing significantly to the efficiency and accuracy of energy management 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 | 0.002 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| 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".