Vehicle arrival prediction using multiple data sources including passenger bus arrival prediction

A system for determining a vehicle arrival time at a stop location along a vehicle route having multiple stop locations, the system comprising:

• a memory device;
• and
• a processor being connected to the memory device,
• wherein the processor performs steps of:
• receiving information representing prior travel times of vehicles between vehicle stops along a vehicle route, each of said prior travel times occurring on a different travel date;
• receiving real-time data representing a current journey, the current journey referring to a movement of a vehicle currently traveling along the route and the current journey comprising one or more subsequent vehicle stops of varying lengths, the current journey having a current date;
• weighting the received information for each prior travel time based on a function of the travel time from a prior travel date and the current date to obtain a weight of prior travel time;
• calculating a regular trend representing the current journey based on the received prior travel times information and the received real-time data, said calculating performed by summing, for each of the prior travel times, a product of the weight of the prior travel time and a slope representing an average vehicle travel speed for the corresponding prior travel time;
• computing a deviation from the regular trend in the current journey, said computing performed by summing, for the prior travel times, a product of the weight of the prior travel time and a deviation of the corresponding prior travel time;
• determining a future traffic status in the one or more subsequent vehicle stops in the current journey;
• and
• estimating, for the vehicle, each arrival time at each subsequent vehicle stop weighted based on the varying length and further based on the calculated regular trend, the computed deviation and the determined future traffic status, and determining a whole estimated arrival time in the current journey based on the estimated arrival times at each subsequent vehicle stop;
• computing a deviation from the whole estimated arrival time in the current journey;
• computing a deviation from the determined future traffic status in the current journey;
• correlating the deviation from the whole estimated arrival time with the deviation from the future traffic status;
• updating the whole estimated arrival time based on the deviation from the whole estimated arrival time, the deviation from the future traffic status, and the correlation.

A computer program product for determining a vehicle arrival time at a stop location along a vehicle route having multiple stop locations, the computer program product comprising a storage medium readable by a processing circuit and storing instructions run by the processing circuit for performing a method, the method comprising:

• receiving information representing prior travel times of vehicles between vehicle stops along a vehicle route, each of said prior travel times occurring on a different travel date;
• receiving real-time data representing a current journey, the current journey referring to a movement of a vehicle currently traveling along the route and the current journey comprising one or more subsequent vehicle stops of varying lengths, the current journey having a current date;
• weighting the received information for each prior travel time based on a function of the travel time from a prior travel date and the current date to obtain a weight of prior travel time;
• calculating a regular trend representing the current journey based on the received prior travel times information and the received real-time data, said calculating performed by summing, for each of the prior travel times, a product of the weight of the prior travel time and a slope representing an average vehicle travel speed for the corresponding prior travel time;
• computing a deviation from the regular trend in the current journey, said computing performed by summing, for the prior travel times, a product of the weight of the prior travel time and a deviation of the corresponding prior travel time;
• determining a future traffic status in the one or more subsequent vehicle stops in the current journey;
• and
• estimating, for the vehicle, each arrival time at each subsequent vehicle stop weighted based on the varying length and further based on the calculated regular trend, the computed deviation and the determined future traffic status, and determining a whole estimated arrival time in the current journey based on the estimated arrival times at each subsequent vehicle stop;
• computing a deviation from the estimated arrival time in the current journey;
• computing a deviation from the determined future traffic status in the current journey;
• correlating the deviation from the whole estimated arrival time with the deviation from the future traffic status;
• updating the whole estimated arrival time based on the deviation from the whole estimated arrival time, the deviation from the future traffic status, and the correlation.