Global Sources
EE Times-Asia
Stay in touch with EE Times Asia
EE Times-Asia > Sensors/MEMS

Search engine aims to utilize "Smart City" concept

Posted: 10 Jul 2012 ?? ?Print Version ?Bookmark and Share

Keywords:Smart cities? SMART? search engine? information technology?

A search engine that can interrogate networks of sensors to give real time answers to questions about the physical world has been developed. Known as SMART ('Search engine for MultimediA Environment geneRated content'), the engine aims to develop and implement an open source system which allows internet users to search and analyze data from any network of sensors.

The engine responds to questions by matching search queries with information from sensors and cross-referencing data from social networks such as Twitter. With this new search engine, users will be able to receive responses to queries such as "what part of the city holds live music events which my friends have been to recently?" or "How busy is the city center?" Currently, standard search engines such as Google are not able to provide answers to these types of queries.

The SMART project is a joint research initiative of nine partners including the University of Glasgow, Atos, Athens Information Technology, IBM's Haifa Research Lab, Imperial College London, City of Santander, PRISA Digital, Telesto and Consorzio S3 Log. Dr Iadh Ounis from the University of Glasgow stated that the SMART project will be built upon an open-source search engine technology known as Terrier, which has been in development at the university since 2004.

Dr Ounis further explained that the SMART engine will be able to answer high-level queries by automatically identifying cameras, microphones and other sensors that can contribute to the query. The information gathered will then be synthesized in an intelligent manner. SMART builds upon the existing concept of 'smart cities', physical spaces which are covered in an array of intelligent sensors which communicate with each other and can be searched for information. The search results sourced from these smart cities can be reused across multiple applications, making the system more effective. SMART is expected to be tested in a real city by 2014.

SMART will to develop a scalable search and retrieval architecture for multimedia data. Intelligent techniques for real-time processing as well as search and retrieval of physical world multimedia will be included in the development of this engine. The SMART framework hopes to boost scalability in both functional and business terms, while being extensible in terms of sensors and multimedia data processing algorithms.

The matching will be based on the sensors' context and metadata (e.g., location, state, capabilities). The dynamic context of the physical world will also be a factor, as the metadata is perceived by processing algorithms (such as face detectors, person trackers, classifiers of acoustic events and components for crowd analysis). At the same time, SMART will be able to leverage Web2.0 social networks information in order to facilitate social queries on physical world multimedia.

The SMART project is part of the University of Glasgow's growing theme of research on sensor systems. The University aims to ensure that its research portfolio can provide entire sensor solutions, from novel physical sensors, to intelligent applications and visualizations of sensor inputs. The University is also part of the Scottish Sensor Systems Centre, which is funded by the Scottish Funding Council and collaboration between eight of Scotland's leading universities and industry to undertake joint industrial/academic projects into sensor systems.

- ?? EETimes Europe

Article Comments - Search engine aims to utilize "Smart...
*? You can enter [0] more charecters.
*Verify code:


Visit Asia Webinars to learn about the latest in technology and get practical design tips.

Back to Top