As the world is advancing technologically, the word “smart” has been used everywhere, from smartphones to smart homes. Everything, including cities, is “smart” now. A smart city utilizes various Internet of Things (IoT) sensors to gather data around the city, which is analyzed to manage the city’s resources and services better. Some applications are applied for traffic congestion, noise, and pollution control.
These applications require data, and more importantly, authentic learning requires useful data. This also leads to one of the major problems with developing smart cities: these cities are large. Beijing is 1,600 square miles, with a population of more than 20 million, and New York City is 302 square miles with more than eight million. To gather accurate data, sensors need to be planted all over the city. Still, it is impossible to deploy them everywhere due to cost, labor, and limited reach in certain areas.
Pei Zhang, an associate research professor of electrical and computer engineering at Carnegie Mellon University, explained that using taxis as sensors is a great approach. A fleet of taxis has a long operational time, sizeable spatial coverage, and a high potential to collect data. Placing sensors all over the city with high density would be expensive and difficult to maintain, but these controlled fleet-like taxis are everywhere, and they have a great reach as well.
Despite the potential of the taxi fleet, it also brings new challenges. If these sensors are deployed on taxis without any regulations, the data will probably have errors and incomplete results because the taxis don’t naturally travel to every part of the city. Instead, they are situated densely around popular areas.
To understand the theory better, the team developed an algorithm to create the best plan to motivate taxi drivers to drive to less populated areas to actuate them to collect data through monetary incentives. The team emphasized two main goals: a larger area covered and a more evenly distributed coverage. To determine which taxis to deploy for the best data, the algorithm considered numerous factors, including the location of a given tax, the possible routes, potential customers, and the need to reduce costs.
The system for city-wide crowdsourcing of data showed positive results. The team saw a 40% improvement in sensing coverage quality and a 30% increase in ride request matching rates, with only 10% of the baseline budget needed. They also collaborated with Chinese company Environmental Thinking and currently have 146 deployments in Shenzhen and 19 taxis in Tianjin.
As a part of this collaboration, the team developed a pollution mapping tool called Atmospheric Monitoring System that tracks a good amount of information about air pollution in a given place. The tool compiles information from weather to 24-hour graphs of particulate matter, nitrogen dioxide, and ozone pollution into a single platform. As the cities become smarter, these systems will provide high resolution and accuracy, sensing information to city managers or occupants. With better situational awareness, a smart city will be better able to respond to its occupants.