Smart City Search Engine Uses Sensors


University of Glasgow search engine project will use social media and sensors to take the pulse of a city

Researchers at the University of Glasgow are helping build a search engine that will combine data from social networks with real-time sensor information such as recognition of faces in crowds to help users locate individual people or events.

The European-funded project, called Search engine for MultimediA Environment geneRated contenT (SMART), takes advantage of the already widespread presence of sensors such as CCTV cameras and microphone arrays, according to Dr. Iadh Ounis of the University of Glasgow’s School of Computing Science.

Finding events

“The main point is that users will be able to find interesting events in the city and find out what people are saying about the events in social networks such as Twitter,” Ounis said in an interview with BBC Radio Scotland on Monday.

The research follows on from other projects that have demonstrated the potential of combining sensor information with data from social networks. In 2011, for instance, researchers at Carnegie Mellon University demonstrated the ability to identify strangers and gain personal information including social security numbers using a combination of facial recognition software and social media profiles.

Researchers have noted how facial recognition features in social networks such as Facebook can be used to accurately identify users from photographs.

The University of Glasgow’s project is being built using open-source search engine technology called Terrier that the university has been developing since 2004, Ounis said. The university’s research builds on the existing concept of “smart cities”, spaces covered with intelligent sensors that provide searchable information.

“Current research shows that it is possible to, for instance, detect crowds, noise or music in the city,” Ounis told BBC Radio Scotland. “The main challenge we have now is to detect those of most interest to users.”

He said intelligent sensors would already have been capable of detecting the recent Olympic torch event in Glasgow, identifying that an unusual event was occurring and that it was related to the torch.

Real-world testing

Ounis said other possible queries could include: “Where is there something interesting happening nearby right now?” or “Where are my friends hanging out in the city right now?”

He said the project could be ready for testing in a real city by 2014.

The project is aiming to develop a scalable search and retrieval architecture for multimedia data, along with real-time processing, search and retrieval techniques, the university said.

The sensor data to be used will include location information as well as the results of processing algorithms such as face detectors, person trackers, classifiers of acoustic events and crowd analyses, the university said.

Partners on the project include Atos, Athens Information Technology, IBM’s Haifa Research Lab, Imperial College London, City of Santander, PRISA Digital, Telesto and Consorzio S3 Log.

How well do you know the cloud? Take our quiz.