Skip to Content
You are currently on the new version of our website. Access the old version .
SensorsSensors
  • Article
  • Open Access

16 November 2023

22 Pages

Smart Public Transportation Sensing: Enhancing Perception and Data Management for Efficient and Safety Operations

,
,
,
,
and
1
Shenzhen International Graduate School, Tsinghua University, Shenzhen 518055, China
2
Hangzhou DTWave Technology Co., Ltd., Hangzhou 311100, China
3
College of Mathematics and Informatics, College of Software Engineering, South China Agricultural University, Guangzhou 510642, China
4
Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen 518055, China
This article belongs to the Special Issue New Trends in Artificial Intelligence of Things

Abstract

The use of cloud computing, big data, IoT, and mobile applications in the public transportation industry has resulted in the generation of vast and complex data, of which the large data volume and data variety have posed several obstacles to effective data sensing and processing with high efficiency in a real-time data-driven public transportation management system. To overcome the above-mentioned challenges and to guarantee optimal data availability for data sensing and processing in public transportation perception, a public transportation sensing platform is proposed to collect, integrate, and organize diverse data from different data sources. The proposed data perception platform connects multiple data systems and some edge intelligent perception devices to enable the collection of various types of data, including traveling information of passengers and transaction data of smart cards. To enable the efficient extraction of precise and detailed traveling behavior, an efficient field-level data lineage exploration method is proposed during logical plan generation and is integrated into the FlinkSQL system seamlessly. Furthermore, a row-level fine-grained permission control mechanism is adopted to support flexible data management. With these two techniques, the proposed data management system can support efficient data processing on large amounts of data and conducts comprehensive analysis and application of business data from numerous different sources to realize the value of the data with high data safety. Through operational testing in real environments, the proposed platform has proven highly efficient and effective in managing organizational operations, data assets, data life cycle, offline development, and backend administration over a large amount of various types of public transportation traffic data.

Article Metrics

Citations

Article Access Statistics

Multiple requests from the same IP address are counted as one view.