Type of source code : API, Website, Database System

Goals and context : Service disruptions of rail transit systems have become more frequent in the past decade in urban cities, due to various reasons, such as power failures, signal errors, and so on. Smart transit cards provide detailed tapping records of commuters, which enable us to infer their trajectories under both normal and disruptive circumstances. In this article, we study and predict the impact of disruptions on commuters and further evaluate the vulnerability of the rail system. Specifically, we define two metrics, stay ratio and travel delay, to quantify the impact, and we derive the predictor of each metric based on the inferred alternative route choices of commuters under disruptive circumstances. We demonstrate that the alternative route choices contribute to more similar feature distribution among different disruptions, which is crucial to tackling the main challenge of abnormal data scarcity and is beneficial for obtaining more reliable predictors for future disruptions. We evaluate our approach with a real-world transit card dataset. The result demonstrates the effectiveness of our method. Based on the predictors, we further analyse the vulnerability of the rail system. An evaluation with cross validation from taxi GPS trajectory data indicates its efficacy in discovering vulnerable rail stations as well as Origin-Destination pairs.

Usage : Service Optimization: Machine learning models can help predict the impact of disruptions, allowing transit authorities to optimize service in real-time by adjusting schedules, rerouting trains, or providing alternative transportation options. Resource Allocation: By predicting the impact of disruptions, authorities can better allocate resources such as maintenance crews, replacement parts, and emergency personnel to minimize the impact on passengers. Passenger Information: Predictive models can provide accurate and timely information to passengers about disruptions, helping them make alternative travel arrangements or adjust their schedules accordingly. Cost Savings: By minimizing the impact of disruptions and optimizing service, transit authorities can reduce costs associated with delays, maintenance, and customer dissatisfaction. Safety: Predictive models can also help improve safety by identifying potential issues before they cause disruptions or accidents, allowing for proactive maintenance and repairs.

Desired features : User Interface, Administrator website

Features Details : Time and Date: The time and date of the disruption, which can help identify patterns in disruptions based on the day of the week, time of day, and season. Weather Conditions: Weather data such as temperature, precipitation, and wind speed, which can impact the likelihood and severity of disruptions. Location: The location of the disruption within the transit system, which can help identify areas that are more prone to disruptions. Type of Disruption: The type of disruption, such as track maintenance, signal failure, or unplanned incidents like accidents or medical emergencies. Historical Data: Historical data on past disruptions, including their duration and impact, which can help identify trends and patterns. Service Information: Information about the affected rail lines, stations, and services, which can help determine the extent of the disruption. External Factors: Other external factors that could impact the transit system, such as events, holidays, or road closures. Infrastructure Data: Data on the condition of the rail infrastructure, such as track age, maintenance history, and recent repairs. Operational Data: Data on train schedules, capacity, and other operational factors that could affect the transit system's ability to recover from disruptions.