Dynamic Travel Information Personalized and Delivered to Your Cell Phone [Summary]

Barbeau, Sean J.; Georggi, Nevine; Winters, Philip · 2011 · ROSA P / National Center for Transit Research (U.S.)

archive: archived pipeline: cataloged verified

Get this paper ↗ (full text — opens at the source; we link to it, we don't host it)

Summary

This research addresses the limitations of Florida’s primary public travel information system, FL511, which currently offers limited alert coverage and lacks personalized, multimodal data integration. The study was motivated by the need to provide travelers with pertinent, timely, and customized information that reduces the hazard of accessing messages while driving. Researchers from the University of South Florida aimed to enhance the existing TRAC-IT software system, which collects user travel behavior data via GPS-enabled mobile phones, by incorporating path prediction technology and multimodal transit data. The methodology involved developing and refining several algorithms to process large volumes of GPS data efficiently. A Fast GPS Clustering algorithm was designed to identify frequent points-of-interest, offering superior efficiency compared to traditional hierarchical clustering methods. A Trip Segmentation algorithm divided GPS data into trips between these points to generate origin/destination models. Additionally, a Naïve Bayes classifier was employed to predict probable traveler destinations and departure times based on typical daily movement profiles. The researchers also integrated data from the Hillsborough Area Regional Transit’s automatic vehicle location (AVL) system to combine traffic congestion alerts with public transit information. To ensure safe interaction for drivers, the team developed a mobile application called Traffic Text-to-Speech (TTS) using the Android operating system’s text-to-speech converter. This application tracks user speed and delivers audio alerts only when the vehicle is completely stopped, allowing drivers to receive information without manual interaction. The findings demonstrate that TRAC-IT can successfully anticipate traveler routes, such as the commute home after work, and provide advance travel advisories for those specific paths. This proactive approach allows users to consider re-routing options before encountering congestion. The integration of AVL data with FL511 successfully created a multimodal traveler information system, providing users with simultaneous updates on traffic conditions and public transportation options. The Traffic TTS application effectively delivered these alerts audibly, maintaining safety by preventing driver distraction during motion. The significance of this work lies in its demonstration that traveler information systems can be extended to include diverse data sources, such as public transportation, to offer personalized and timely guidance. By providing comprehensive multimodal information, the system may encourage travelers to utilize transportation alternatives. The study concludes that future efforts should focus on expanding FL511 coverage to more roads, integrating additional real-time transit information, and deploying these technologies to the general public to improve overall travel efficiency and safety.

Methodology

modeling

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. Discovered via bulk_ingest_rosap on 2026-05-23 (9 acquisition events logged).

Summary generated by qwen3.6-27b-prismaquant on 2026-06-10; verification: verified.

Topics

Ranked by relevance to this paper. Hover a topic for its definition.

• in vehicle coaching