Community Research and Development Information Service - CORDIS

Periodic Report Summary 1 - GRAISEARCH (Use of Graphics Rendering and Artificial Intelligence for Improved Mobile Search Capabilities)

The principal aim of this project is to develop and apply revolutionary graphics rendering and artificial intelligence (AI) methods to an existing social media search engine platform (known as Tapastreet) thereby creating ground breaking mobile search capabilities with significant online commercial potential.

Data streams harvested from social networks include geo-located and time stamped images, videos and text data generated by users reflecting their motion patterns and opinion about their environment. Understanding of such patterns are relevant for city planning and transportation, product and event marketing, amongst others. The project tackles extracting the relevant information of value from noisy social media data, as well as its rendering for providing visual data analytics tools to Tapastreet. For instance, this includes static representation of information (e.g., tweet sentiment, tweet activity) overlaid on a 2D map (e.g. Google map), dynamic and interactive representation of an event on a 2D map overtime, and representation of photographic and motion activities in a virtual 3D representation of cities. Game engine technologies are then used to create 3D rendering of events and social media user’s activities as a powerful alternative to 2D map renderings.
Specifically, these goals are achieved by meeting the following Scientific & Technological Objectives:

(a) the creation of dynamic graphics rendering algorithms,
(b) the development of powerful location based AI machine learning algorithms and
(c) integration of both these technologies into a live geo-located social media search engine.
The goals are achieved through knowledge transfer from academic partners (INSA Lyon and Trinity College Dublin) to the industry partner (Tapastreet) by training Marie Curie fellows in image processing, game engine, web technologies, and data analytics relevant to social media data. Several networking activities have taken place between the partners (workshops & meetings).
Research output also includes presentations at conferences and workshops as well as dissemination at national and international events. The highlight of this was the presentation of some of the prototype work to a global meeting of ICANN in Dublin October 2015. The meeting of 3000 of the leading players in the domain name, hosting and web platform sectors enabled Tapastreet to present and solicit feedback from the industry most likely to adopt the FP7 output. The feedback was extremely positive.
The project has already generated 12 peer review publications for the two year period 01/2014-12/15, and this research is currently deployed as part of the Dublin based start-up company Tapastreet’ s products. In term of training, one recruited Marie Curie Fellow on the GRAISearch project at INSA Lyon has already successfully transitioned to a permanent academic position as assistant professor in university of Caen (France).


Deirdre Savage, (Research Accounting Manager)
Tel.: +35318961942
Fax: +35317071633


Life Sciences
Record Number: 193181 / Last updated on: 2017-01-16
Follow us on: RSS Facebook Twitter YouTube Managed by the EU Publications Office Top