Dr. Stratos Stylianidis

GeoImaging Ltd 6 Georgios Seferis Street 1075 Nicosia Cyprus Tel. +357-22447770 | Fax. +357-22374988 www.geoimaging.com.cy

-] What application will you create (or enhance) as part of the project (what does it do)

We have in mind some applications which we would like to improve using parallel processing; indicatively we mention:

  • 1) Satellite image processing in order to update –for instance- the road network on the maps, in two or more different time points
  • 2) X-ray image processing in order to –for instance- locate the spine for the purpose of scoliosis monitoring

-] Who will use the application (will it be used by end users in the community, or people inside a company using it as a tool, or for advancing science..)

  • 1) For advancing science, engineers, people involve in satellite and remote sensing technology, etc.
  • 2) Trained people inside hospitals, clinics, private doctors, etc.

-] What are the application's computation needs that will benefit from parallel computation

  • 3) Images of 20000x20000 pixels (per image)
  • 4) Hundreds of 1000x3000 pixels images (per image)

-] What has blocked you from using parallel computation up to this point

Difficult programming, not familiar with special parallel programming rules

-] How will your application provide higher benefit as a result of the parallel computation (what currently can't be done that will be enabled, or what aspect will be improved. For example, will weeks of waiting for simulation results drop to hours? Will a researcher be able to interactively search, rather than doing a scatter shot of simulations and hoping one of them was the right one? Will a product be producible with less material or less design effort? Will the graphics be richer, or render faster, or use less battery?)

Much faster run time. How much, depends on the quality of the final parallelism and the number of the available cores/CPUs to which the problem will be distributed

-] Who will receive this benefit and how (for example, will the application help cure cancer for millions of EU citizens by enabling doctors to use personalized genetics?)

  • 1) Companies providing digital maps, remote sensing services, local & regional authorities, public services, etc.
  • 2) Doctors and physicians who will be able to automatically diagnose and monitor scoliosis, a task currently done manually.

-] What market(s) will be affected by this benefit, and will this benefit be passed on, to yet further markets

  • 1) Companies providing digital maps services, remote sensing services, local & regional authorities, public services, etc. to whom we can sell or use our product
  • 2) Medical sector (hospitals, clinics, private doctors etc) to whom we will sell our product and services

-] Separately, for logistics of the project, we would like to start by coding in C/C++, but are open to integrating into other languages, such as Python, Java, or even Javascript. Could you say a bit about your development process:

-] What language(s) do you plan to use for the application

MATLAB and C++

-] Is the application.. desktop based, Cloud (SAAS) based, browser based, or mobile

Desktop

-] A little bit about the architecture (do you have a server with database, or a large data set that is churned through such as

Big Data style, what parts of the computation are performed on the end-user device versus in a server, and so on) There is a big database with images, which would be great to be dealt in partitions in parallel

Geoimaging Ltd (link) is a SME based in Cyprus, established in 2002 at Nicosia. The company offers scientific and professional solutions in IT and Geo-informatics. It is also active in R&D programmes, in EU & national funded projects and provides consultations services as well. GeoImaging goal is to support its clients and partners in the responsible and successful completion of projects.

Currently, Geoimaging Ltd is running: (a) 3 FP7 projects (SMEs, SiS, ENV) such as SCOLIO-SEE, RESPONSIBILITY, IASON; (b) 2 AAL projects, SOPHIA (as project coordinator) and ELDERSUP; (c) 1 LLP project, ATMAPS. GEO is negotiating with the funding authorities: (a) 1 H2020 project, LARA (as project coordinator), (b) 1 EUROSTARS project (CASPAR); (c) 1 JPI Cultural Heritage project (TANGIBLE –as project coordinator-). The company has successfully finished: (a) 7 FP7 projects (ICT, SiS, TPT, ENV, SMEs): RADICAL, ETHICAL, REACT, OBSERVE, CHAMPI-ON, NUTRISTAT, DE-MONTES; (b) 1 EUROSTARS project: FORSAT (as project coordinator); (c) 1 AAL project: TTNET. I reckon that we could contribute in your project. If you are interested in our profile we could further discuss to see the details and if there is an opportunity for cooperation.

One of our main activity lines involves image processing, a field that traditionally depletes the CPU’s resources and gets optimized through parallel processing. Dealing with high resolution images such as X-rays, Intravascular Ultrasound (IVUS) images, satellite images etc., has led us to parallel programming, a challenging task considering the fact that the programmer needs to re-learn to implement even the basic code. The most frequently used image processing tools are MATLAB and C++.

We are working in the field of data mining and graph mining as well. Both fields are challenging regarding the complexity of the algorithms which will be used to solve relative problems such as community detection, dense sub-graphs or frequent sub-graphs discovery, similarities between graph nodes definition etc. The challenge becomes larger when the graph is a streaming form or the size of the graph is more than 10GB. In these cases, the 'problem' will be addressed either by CPU acceleration or by developing algorithms adapted to parallel and distributed systems. In the second case of the parallel solution will be promising if a suitable framework will be chosen, since most of the existing ones are not suitable for graphs. The main programming languages which are used are JAVA and C/C++.