What is mdx?

Collaboration between multiple fields and sectors is required to be able to utilize data and apply it to benefit society at large. There is a need to bring together, both more broadly and more closely, organizations that possess and provide data, particularly corporations and research institutions in specific fields; experts in various fields needed to resolve issues; and specialists in information and data sciences, including in programming, algorithms and machine learning. As a major step toward that end, the mission of mdx is to enable academia (universities and national research institutions), industry, and government to collaborate rapidly, closely and efficiently by sharing knowledge of data and information sciences, knowledge and culture in specific fields, data and software, and a computational infrastructure that runs the necessary software

The overview of the mdx platform is described in our latest paper available here. For more information on mdx and related research papers, please click here.

The features of mdx

mdx: Platform for the Data-Driven Future

mdx aims to be a platform that provides the functionality to collect, store and analyze data that can then be rapidly created, extended and integrated on demand for specific uses.

1. mdx makes the most of a Japanese academic backbone network called SINET (Science Information NETwork) , in that a data collection, storage and analysis environment that is unique to each application is readily created upon request. It generates output from input in real time by connecting remote sensors and storage devices with the computational resources and data stored on the data platform.

2. Data and computer science techniques can be integrated by providing a high-performance computing environment, and highly accurate predictions can be made using the most advanced computing environment in Japan.

3. A community of data owners, analysts and users in a variety of fields who collaborate across the boundaries of academia and industry is formed to create new values. Consultations and development support are provided to those who wish to use this data.


Configuration of mdx

Using virtualization technology, mdx provides private environments (virtual platforms) that are unique to each project. A private virtual environment can be created and configured individually for each project in a flexible manner, making it possible to install the necessary software stack for the project.

Services that require continuous operation, such as field-data platform services, can also be managed on mdx. By making open data and paid data (with appropriate contract) available on mdx, we will continuously maintain an environment that allows machine learning and data mining to be readily performed.

SINET6 and mobile SINET

Without the use of a public network, mdx can be connected to remote computers in coordination with SINET6 L2VPN/VPLS. Without using the Internet, it can be connected to remote monitoring instruments and mobile devices in coordination with mobile SINET (the Science Information Network).

mdx’s high-performance computing environment

mdx allows for large-scale computation in data processing, machine learning and simulation. It also provides access to Japan’s advanced high-performance computing environment in coordination with super high-performance computers, including ABCI. It provides multiple layers of protection to systems and projects by combining virtualization, traffic separation by network switching.

Potential uses

For use as a data repository
  • ● Used as a field data platform and to view, search for and download shared data without the need for a high-performance computing environment
For use as a high-performance computer and/or large-scale data processor
  • ● To process data provided by the field data platform, shared data and user-supplied data, using a high-performance computing environment, and to perform data mining, machine learning and simulation. To facilitate machine learning using a large-scale dataset and data processing by linking to a large number of datasets
For use as a platform hosting environment
  • ● To collect field data and create a data platform on mdx for field data collection; and to facilitate processing by linking to multiple datasets to ensure continuity and scalability of field data platforms