Public Transport Capacity Prediction Using Real-Time Boarding Data
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for predicting the capacity of public transport vehicles to accommodate boarding passengers are inadequate, particularly in real-time scenarios, and do not effectively incorporate real-time data with historical data to improve forecasting accuracy.
Innovation Solution
A method and system that combines real-time data with pre-recorded datasets to predict the capacity of public transport vehicles for boarding passengers, using automatic processes to update and display this information on stationary devices and transmit it to remote computers, incorporating sensors and cameras to measure passenger and luggage presence, and adjusting for external factors like weather and events.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If real-time data and historical data are combined to predict capacity, then prediction accuracy is improved, but system complexity increases
Solution Approach 1:
The system segments data into historical data (stored in database) and real-time data (collected by sensors), processing them through separate but coordinated modules. The prediction unit combines these segmented data sources to achieve accurate capacity forecasting while maintaining manageable system complexity through modular architecture.
Solution Approach 2:
The control unit acts as an intermediary that coordinates between the database, sensor units, prediction unit, and display units. This intermediary component integrates real-time sensor data with historical data from the database, enabling accurate predictions while managing system complexity through centralized coordination.
2Measurement precision
If multiple sensors and cameras are used to detect passengers and luggage, then measurement precision is improved, but device complexity increases
Solution Approach 1:
The system merges multiple detection technologies (sensors and cameras) into an integrated monitoring system. The control unit consolidates data from various sensor units and camera systems, combining their detection capabilities to achieve high measurement precision while managing complexity through unified data processing.
Solution Approach 2:
The sensor units and camera systems serve multiple functions: detecting passengers, detecting luggage, and providing real-time data for capacity prediction. This multi-functionality reduces the need for separate dedicated systems, achieving high measurement precision without proportionally increasing device complexity.
3Loss of information
If real-time capacity information is displayed on multiple devices, then information availability is improved, but system complexity increases
Solution Approach 1:
The system distributes capacity information across multiple display dimensions: stationary display devices at stops and remote computer devices accessible via network. This multi-dimensional information distribution ensures high information availability while managing complexity through standardized communication protocols and centralized data management by the control unit.
Data Source
Figure 1~2
Figure 3~4
Figure 5
AI summary
A method and a computerized system programmed to carry out the method of predicting the capacity of a public-transport vehicle for passengers to board at the stop and for displaying this predicted capacity on remote computer devices or service screens is provided. The method comprises a prediction process and a data procurement process. The capacity of the public-transport vehicle for passengers to board at the stop is predicted in the prediction process by using previously measured and learned values of capacities of public-transport vehicles for passengers to board and/or previously measured and learned numbers of passengers that have alighted from public-transport vehicles at the stop. The capacity of the public-transport vehicle for passengers to board at the stop and/or the number of passengers that have alighted the public-transport vehicle at the stop are measured in the data procurement process. Thereafter, updated indications are determined out of this measured values, for example, by averaging the newly acquired numbers with a dataset of previously stored numbers and taking non-periodic traffic-relevant events into account by modifying the expectation values accordingly.