Collective thinking approach for improving leak detection systems
Bibliographic record
Abstract
Abstract Water mains, especially old pipelines, are consistently threatened by the formation of leaks. Leaks inherit increased direct and indirect costs and impacts on various levels such as the economic field and the environmental level. Recently, financially capable municipalities are testing acoustic early detection systems that utilize wireless noise loggers. Noise loggers would be distributed throughout the water network to detect any anomalies in the network. Loggers provide early detection via recording and analyzing acoustic signals within the network. The city of Montreal adopted one of the leak detection projects in this domain and had reported that the main issue that hinders the installed system is false alarms. False alarms consume municipality resources and funds inefficiently. Therefore, this paper aims to present a novel approach to utilize more than one data analysis and classification technique to ameliorate the leak identification process. In this research, acoustic leak signals were analyzed using Fourier Transform, and the multiple frequency bandwidths were determined. Three models were developed to identify the state of the leak using Naïve Bayes (NB), Deep Learning (DL), and Decision Tree (DT) Algorithms. Each of the developed models has an accuracy ranging between 84% to 89%. An aggregator approach was developed to cultivate the collective approaches developed into one single answer. Through aggregation, the accuracy of leak detection improved from 89% at its best to 100%. The design, implementation approach and results are displayed in this paper. Using this method helps municipalities minimize and alleviate the costs of uncertain leak verifications and efficiently allocate their resources.
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 | 0.002 | 0.003 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.001 | 0.002 |
| Open science | 0.001 | 0.002 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.003 | 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".