InterIMAGE Cloud Platform (ICP)

InterIMAGE Cloud Platform (ICP) is an open-source, distributed framework for automatic interpretation of remote sensing and medical image data built on top of Hadoop. This new system can be understood as a functional and architectural redesign of the first version of InterIMAGE. ICP delivers some important features for automatically interpreting big data using expert knowledge. It:

  1. Enables the user to embed expert knowledge into the system intuitively through the definition of semantic networks and rule sets defined in a high-level programming language; 
  2. Allows programmers to extend the system by adding their own algorithms straight forwardly;
  3. Delivers the robustness of MapReduce for cluster computing without the complexity of handling the Hadoop programming language.

One of the tools within the scope of ICP is the Data Mining Package; which is an open source software tool implemented in Java, able to perform supervised classification procedures on huge amounts of data, usually referred as big data, on a distributed infrastructure using Hadoop MapReduce. The tool has four classification algorithms implemented, taken from WEKA’s machine learning library, namely: Decision Trees, Naïve Bayes, Random Forest and Support Vector Machines (SVM).

Packages

ICP: Data Mining Package (last update: December 1th, 2014)

Documentation

(in construction)

License Terms

ICP and its package tools are noncommercial. You may not use this work for commercial purposes. For any reuse or distribution, you must make clear to others the license terms of this work. Any of these conditions can be waived if you get written permission from LVC/PUC-Rio.

If you use the Interimage Cloud Platform in any of your experiments or researches that lead to a scientific publication, please cite the following paper:

R. Ferreira, D. Oliveira, P. Happ, G. Costa, R. Feitosa, C. Bentes; InterIMAGE 2: The Architecture of an Open Source, High Performance Framework for Automatic, Knowledge-Based Image Interpretation. International Geographic Object-Based Image Analysis Conference. Thessaloniki, 2014.

If you use the ICP: Data Mining Package tool in any of your experiments or researches that lead to a scientific publication, please cite the following paper:

V. A. Ayma, R. S. Ferreira, P. Happ, D. Oliveira, R. Feitosa, G. Costa, A. Plaza, P. Gamba; Classification Algorithms for Big Data Analysis, a Map Reduce Approach. International Society for Photogrammetry and Remote Sensing, 2015.