Project Title: Digging into Data – DIDC Project 2013
Project Funder: Social Sciences and Humanities Research Council of Canada (SSHRC), Natural Sciences and Engineering Research (NSERC) and Canadian Foundation for Innovation (CFI)
What problem are we solving?
The International, multi-disciplinary project is based on the Indian Ocean World (IOW) project with cross-cultural study of literary networks in a global context by integrating new image processing techniques with social network analysis.
In the project, four teams are divided between humanities and engineering, from the U.S., Canada, and Netherlands which they undertake the cross-cultural study of literary networks and the onset of various global modernisms across China, the Middle East, and Europe. This project seeks to combine image processing network science and test analysis to study cultures of literary communication within a global context.
- Synchromedia experience in document and map image analysis will play a central role in researching all new questions posed by the project under the Direction of Professor Cheriet. Synchromediateam will concentrate their research on a new forms of text analysis, new methods for interpreting quantitative network measures in the context of cultural history.
- Synchromedia will employ Visual Language Processing (VLP), new image recognition techniques in a way to generate statistical relationships between elements in collections which will open access to a much broader spectrum of the world’s textual cultures for large scale text analysis.
- Synchromedia will equip with a Culture Box Storage Cluster and at the same time will be the use of the central processing compute Cluster named “Guillimin” which already exists. This infrastructure will significantly contribute to knowledge, understanding in the fields of computational literature, studies visual language processing, document image analysis, and relation discovery. With the Culture Box storage cluster, three other components are included in the infrastructure; this project requires a dedicated storage cluster. Is planned in order a) to preserve the results including the generated representation and relation data to be accessible by the public and research communities and b) to ensure protection by avoiding faults in non-dedicated infrastructure, at technical or administrative level.
This project is being funded by Social Sciences and Humanities Research Council of Canada (SSHRC), by Natural Sciences and Engineering Research (NSERC) and by Canadian Foundation for Innovation (CFI) for a period of 2 years starting in 2013.