A novel method of using sound waves and artificial intelligence for the detection of vehicle's proximity from cyclists and E-scooters
Bibliographic record
Abstract
Outdoor air pollution has been found to have a significant adverse effect on health. When the authors attempted to monitor air quality that cyclists or e-scooter users' breath during commuting in different locations for health and safety analysis, it was found that the existence of internal combustion engine (ICE) cars has a significant effect on the pollution levels and the monitoring process. To comprehensively study the effect of cars and traffic on air quality that cyclists and e-scooters users experience, a low-cost and reliable system was needed to detect the proximity of cars that have diesel or petrol engines. Video cameras can be used to visually detect vehicles, but in the modern age with the existence of many electric and hybrid vehicles and the need to reduce the cost of instrumentation, there was a need to determine the passing of vehicles near e-scooter and bike users from the combined engine and tires sounds. To address this issue, this study suggests a novel approach of using sound waves of internal combustion engines and tire sounds during the passing of cars, combined with AI techniques (neural networks), to detect the proximity of cars from cyclists and e-scooter users. Audio-visual data was collected using Go-Pro cameras in order to combine the data with GPS location and pollution levels. Geographical data maps were produced to demonstrate the density of cars that cyclists encounter when on or near the road. This method will enable air quality monitoring research to detect the existence of ICE cars for future correlation with measured pollution levels. The proposed method allows for:•The automated selection of sensitive features from sound waves to detect vehicles.•Low-cost hardware which is independent of orientation that can be integrated with other air quality and GPS sensors.•The successful application of sensor fusion and neural networks.
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 | 0.000 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.000 |
| 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".