Citation

Agarwal S, Gupta S, Kachroo P, Dhingra N. Transp. Dev. Econ. 2024; 10(1): e15.

Copyright

(Copyright © 2024, Holtzbrinck Springer Nature Publishing Group)

DOI

10.1007/s40890-024-00199-w

PMID

unavailable

Abstract

This paper presents a streamlined machine learning-assisted integrated approach for smart surveys and data collection with applications to multiple domains such as transportation, aviation, healthcare, and education. We exploit several machine learning methods to enhance the survey's effectiveness and increase the trustworthiness of the collected data in real time. The methodology is demonstrated in a case study involving the daytime seat belt surveys mandated by the U.S. National Highway Traffic Safety Administration (NHTSA). To implement and test the approach, we also built an integrated tool. This cloud-based software tool is designed to aid in intelligent data collection, quality control, survey management, data analysis, insight extraction, and a feedback structure. This tool automates and standardizes the complete process of transportation-related data collection, quality control, and better decision-making. The framework presented is adaptable, underscoring its potential for widespread application and utility in other domains as well.

Language: en

Keywords

Anomaly Detection; Automated Quality Control; Data Collection