A hybrid BiLSTM–transformer–GCN architecture with API fusion for adaptive transportation resource analytics
Mohammed Saad Javeed, Arindam Kishor Biswas, Md Nahid Hasan, Jannatul Maua, Rahomotul Islam · 2026
Read A hybrid BiLSTM–transformer–GCN architecture with API fusion for adaptive transportation resource analytics by Mohammed Saad Javeed, Arindam Kishor Biswas, Md Nahid Hasan, Jannatul Maua, Rahomotul Islam (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/plos-pone-0349787.txt.
Description
Mohammed Saad Javeed and co-authors combined three kinds of deep learning into one system for understanding city transport data. Traffic networks pour out mixed streams of sensor readings, accident reports, and outside context, and sorting useful resources in real time is hard. Their 2026 design reads sequences forward and backward, weighs long-range patterns with attention, and maps road connections as a graph, all enriched with live data pulled from outside services.
Tested on a Barcelona accident dataset and a highway traffic volume dataset, the combined system classified transport resources more accurately than standard rivals and also spotted anomalies well. Removing either the outside data feeds or the graph component hurt performance, confirming both earn their place. The authors report fast enough responses for real deployment.
Catalog record
| CREATOR | Mohammed Saad Javeed, Arindam Kishor Biswas, Md Nahid Hasan, Jannatul Maua, Rahomotul Islam |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 63860 |
| LICENSE | CC_BY |
| RIGHTS | CC BY |
| SOURCE | PLOS |