Application of AI and IoT technologies to control air pollution in smart cities
Bibliographic record
Abstract
As smart cities are developing worldwide, so is the concern of air pollution there. It is increasingly becoming a hot topic of concern worldwide. According to the 2023 World Air Quality Report published by IQAir, a Swiss-based air quality technology company, Bangladesh was on the top of the list of PM2.5 concentration (μg/m³) for countries, regions, and territories in descending order followed by Pakistan and India. Not only in smart cities but also in many metro cities, the air quality index (AQI) is reducing every day. Major contributors to this declining AQI include vehicle fuel emissions, fuel oil, fumes from process industries, chemical products, and many others. Today’s AI and IoT technologies however have the potential to provide solutions to many real-life problems including the problem of monitoring and controlling air pollution. AI and IOT help to control air pollution by monitoring AQI, sensors, and remote sensing. It can collect real-time data from multiple locations, which is then analyzed to identify the sources of air pollution. IOT makes monitoring easier and access to that information should be affordable to all. IoT and AI also help to detect toxic substances and fumes that may contain carbon monoxide, ozone, nitrogen dioxide, sulphur dioxide, and other toxic gases. This paper underlines the burning issue of air pollution worldwide with a focus on the smart cities of the future. Citing a few recent developments in AI and IOT technologies, it advocates that monitoring AQI, application sensors, and remote sensing can effectively contribute to ensuring quality air in future smart cities. Examples of application of these technologies in a few metro cities have also been quoted along with the scope of future research in these areas.
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) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.002 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 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".