Everyone knows that trips to Disneyland, Six Flags, or Sentosa are filled with laughs, rides, sugary food, and, of course, long lines. In hopes of reducing the frustration of lines, ADSC researchers are partnering with Sentosa, an amusement resort off Singapore’s southern coast, to dramatically decrease the time guests spend waiting for shuttle busses.

The researchers have developed an app that predicts the wait times for each shuttle based on data across the island. Using data from the island, such as WiFi signals and video analysis outputs at bus stops, tram ticket sales, car parking entrance records and weather, the researchers can estimate shuttle bus wait times and the number of waiting passengers.

“The guests will be able to look at the app and see the status of each bus station and the trends in wait times and the number of passengers,” ADSC Senior Research Scientist Zhenjie Zhang said.

The app is based on previous work that examined traffic patterns in Singapore and Shanghai.

In 2014, Zhang and ADSC Research Scientist Tom Fu, partnered with a Singapore startup company to create an app to predict, with 90 percent accuracy, how many people are likely to enter a Singapore metro station within the next hour. The results were based on call detail records from mobile phone users for one month. Using information from those calls, such as which cell towers were nearby, the researchers analyzed the rough trajectories of mobile phone users and the train schedules to create a prediction model.

That project gave the researchers background information on public transportation and helped them compete in the Shanghai Open Data Competition. In this competition, the Shanghai government provided all data from their transportation systems for one month, including the statuses of taxis, metros, buses, how many passengers were riding at a certain time, accident information and weather.

Former ADSC senior research engineer Victor Chen Liang and ADSC postdoctoral researcher Wang Li built the system, Mercury, to digest large amounts of data from these transportations systems and then created a demo app that allows users to get time predictions for various public transportation options.

“If you want to take the metro at 5 p.m., you can put that information in and you’ll get updates if the time prediction changes,” Zhang said. “For taxi availability prediction and bus traveling time predictions, you can know how many available taxis there are in the area in the next hour.”

In the most recent project with Sentosa, the researchers have modified the app to add Sentosa’s attraction spots and make it real-time.

“The scale is very different, as Shanghai is a very big and national city, while Sentosa is a very small island with only a few thousand guests every day,” Zheng said. “The first two projects were more like experiments, so this is the first time we’ve been able to test the system and the models in a real-world application. Data from Sentosa is a little sparse. We are still trying to improve the accuracy of the model because of the sparseness.”

The researchers also imagine connecting the app with local food and beverage services, so if the wait time is long, the app may encourage tourists to walk to their location in exchange for a discount to a local restaurant or simply suggest nearby, less-crowded transportation or restaurant options.

The project is funded by the Government Technology of Singapore (formerly the Infocomm Development Authority of Singapore) and the researchers hope Sentosa will be able to implement their research into their everyday operations soon.

“We believe this is just the beginning,” Zhang said. “Singapore is expected to become a smart nation and traffic is one of the most important aspects of a smart nation, so we foresee more projects coming from other public transportation players.”