PROVIDING A WEB-BASED PLATFORM BASED ON PREDICTED WEIGHTS FROM EXISTING CONDITIONS
DOI: 10.5194/isprs-archives-xlii-4-w18-1169-2020
archive: archived pipeline: cataloged verified
Get this paper ↗ (DOI — opens at the source; we link to it, we don't host it)
Summary
This paper addresses the growing challenge of urban traffic congestion, which negatively impacts environmental quality, public health, and citizen well-being. Motivated by the need for effective traffic management solutions beyond infrastructure reinforcement, the authors propose a web-based platform that utilizes artificial intelligence to predict future traffic conditions. The primary goal is to provide users with real-time and predictive traffic information to facilitate route finding that is closer to reality, thereby reducing travel time and congestion. The study focuses on the 7th and 8th districts of Tehran, Iran. The methodology involves collecting online traffic data from MapQuest every five minutes. This data, represented by color codes indicating traffic intensity (green for low, yellow for moderate, and red for high traffic), is stored in a database structured by individual streets. To enable prediction, the researchers employed an artificial neural network algorithm. The neural network takes the street location and time as inputs to model traffic patterns and generate predicted traffic conditions as outputs. The system was designed to visualize this information on a web interface, allowing users to view both current and forecasted traffic states. The proposed model was tested on more than 100 cases within the specified study area. The results were compared against existing traffic management algorithms. The findings indicate that the proposed platform offers higher precision in traffic prediction. Furthermore, the system demonstrated a performance advantage in speed, being on average 10 minutes faster than similar existing programs. The successful implementation of the neural network allowed for accurate approximation of traffic conditions based on historical and real-time data inputs. The significance of this work lies in its application of artificial intelligence to enhance urban traffic management. By providing accurate, predictive traffic data through a web-based interface, the platform helps users save time and avoid congested routes. The authors conclude that such scientific approaches to analyzing and predicting traffic information are essential for reducing the negative effects of traffic, including health risks and environmental pollution. This study contributes to the field of smart city development by demonstrating the efficacy of neural networks in processing complex urban data for practical traffic reduction solutions.
Provenance
The full processing record for this entry. Every stage of this paper's journey through the pipeline is logged — what ran, with which tool and model, how many attempts it took, and when it last completed.
| Stage | Outcome | Tool | Model | Prompt | Attempts | Completed |
|---|---|---|---|---|---|---|
| discover | success | Crossref | — | — | 1 | 2026-06-25 |
| archive | success | canonical_url | — | — | 1 | 2026-06-26 |
| extract | success | cached | — | — | 5 | 2026-06-26 |
| clean | success | clean | — | — | 1 | 2026-06-25 |
| chunk | success | chunk | — | — | 1 | 2026-06-25 |
| embed | success | embed | Qwen/Qwen3-Embedding-8B | — | 1 | 2026-06-25 |
| promote | success | — | — | — | 1 | 2026-06-25 |
| summarize | success | llm | qwen3.6-27b-prismaquant | summ-v5 | 4 | 2026-06-26 |
| tag | success | vector_similarity | — | — | 6 | 2026-06-25 |
| verify | success | — | — | — | 1 | 2026-06-26 |
Summary generated by qwen3.6-27b-prismaquant on 2026-06-26; verification: verified.
Topics
Ranked by relevance to this paper. Hover a topic for its definition.