Smart Traffic: Traffic Congestion Reduction by Shortest Route * Search Algorithm

Lakshna A; Gokila S; Ramesh K; Surendiran R · 2022 · Crossref

DOI: 10.14445/22315381/ijett-v71i3p244

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 problem of urban traffic congestion, which negatively impacts travel time, public health, and the environment. The authors propose a novel heuristic method called the "Shortest Route * Search Algorithm" to identify the simplest and fastest route from an origin to a destination. Unlike traditional algorithms that search all possible paths, this approach focuses on the nearest shortest nodes to optimize time complexity. The motivation stems from the limitations of existing navigation systems, which often fail to account for dynamic factors such as road blockages, driver behavior, and weather conditions, leading to inefficient routing and increased travel stress. The methodology involves creating a weighted graph representation of the road network using pre-processed historical records and real-time traffic data. The algorithm incorporates five specific parameters to refine pathfinding: road type ($r$), vehicle characteristics ($v$), driver behavior ($d$), time ($s$), and weather ($w$). These inputs are gathered via roadside sensors, GPS data, and user feedback regarding incidents like construction or accidents. The system was implemented in Python using Jupyter Notebook. The experimental design compared the proposed algorithm against three existing methods: the heap-based/enhanced Bellman-Ford algorithm, the enhanced Dijkstra algorithm, and the time-dependent A* potentials algorithm. The dataset underwent cleaning and reduction, resulting in a processed dataset of 42,54,811 records derived from an initial set of 2,56,61,847 entries. The results demonstrate that the Shortest Route * Search Algorithm achieved a prediction accuracy of 97%. In terms of efficiency, the algorithm significantly reduced computational time, lowering the processing duration from 30 minutes to 9 minutes and 30 seconds. The study found that the proposed method outperformed the comparative algorithms in both accuracy and latency. By integrating the five additional parameters, the algorithm effectively identified major causes of congestion and redirected travelers to alternate paths with minimal traffic. The heuristic function prioritized nodes based on estimated cost and traffic conditions, avoiding the inefficiency of searching irrelevant nodes. The significance of this research lies in its potential to improve transportation efficiency and reduce environmental impact through optimized routing. The authors conclude that by providing accurate, real-time shortest path predictions, the algorithm helps travelers avoid congestion and plan trips more effectively. The integration of diverse data sources, including driver behavior and weather, allows for a more robust prediction model than traditional graph theory approaches. This approach offers a practical solution for smart city infrastructure, enabling smoother vehicle flow and reducing the time travelers spend stuck in traffic.

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.

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.

• traffic density