ISTC for Big Data Researchers Present at NEDB Day 2016

ISTC for Big Data principal investigators and researchers presented a broad base of research at North East Database Day 2016, which was sponsored by Microsoft and held at MIT’s Stata Center in Cambridge, Mass., January 28, 2016.

The 8th Annual North East Database Day showcased work by some of the top university research programs and corporate research labs in the Northeast. The fast-paced program demonstrated just how rapidly discoveries are happening in innovative software and architecture to solve Big Data challenges in health care, industry, science and other areas.

ISTC PIs and researchers presenting talks included:

Tim Kraska (Brown University), who presented “Making Distributed Transactions Scale.” Database applications have long been designed based on the conventional wisdom that distributed transactions don’t scale because the network is the major bottleneck. However, this wisdom no longer holds true as network transfer rates approach those of main memory bandwidth, thanks to new next-generation, high-performance RDMA-capable networks. Yet, simply upgrading an existing database cluster with InfiniBand without redesigning the system doesn’t necessarily improve its performance – in fact, performance can degrade. The talk presented a new system optimized for transaction processing over high-speed RDMA-capable networks and early results from the team’s experiments. For all the details, read the team’s blog post: “The End of Slow Networks: It’s Time for a Redesign.

Vijay Gadepally  (MIT CSAIL / MIT Lincoln Laboratory), who presented an update on the BigDAWG polystore system,  a new big data federation architecture being developed by a multi-institution team of more than a dozen ISTC researchers. BigDAWG is designed to work on complex problems that naturally span different processing or storage engines. BigDAWG provides an architecture that supports diverse database systems working with different data models, addresses the competing notions of location transparency and semantic completeness via “islands of information,” and uses middleware to provide a uniform multi-island interface. Download the latest presentation slides here and read a recent blog post on the project from Jennie Duggan (Northwestern University).

ISTC for Big Data Blog_Big DAWG Islands_020216

Siddharth Samsi (MIT Lincoln Laboratory), who presented “D4M and Large Array Databases for Management and Analysis of Large Biomedical Imaging Data.”  He presented a new set of tools that leverage the D4M (Dynamic Distributed Dimensional Data Model) toolbox for analyzing giga-voxel biomedical datasets. By combining SciDB (a computational array database) and the D4M toolbox, researchers demonstrated that they could access large volumetric data and perform large-scale bioinformatics analytics efficiently and interactively. D4M and SciDB play a role in the BigDAWG polystore system and how it handles analysis of high-volume, multi-dimensional data like those in scientific applications.

At the post-program reception, ISTC for Big Data researchers and teams displayed posters describing their current research projects:

      * presenter

For short abstracts on these and other posters, go here.

NEDB 2016 keynote talks included D. Richard Hipp on “SQLite, The Database at the Edge of the Network” and Le Cong (MIT) on “Novel Genome Engineering Tools Based on CRISPR-Cas System and Their Application and Intersection with Genomics Analysis.”

Slides from NEDB 2016 keynotes and talks are available for download here.

This entry was posted in Analytics, Big Data Applications, Big Data Architecture, DBMS, ISTC for Big Data Blog, Polystores, Query Engines, Streaming Big Data, Tools for Big Data, Visualizing Big Data and tagged , , , , , , , , , . Bookmark the permalink.

Leave A Reply

Your email address will not be published. Required fields are marked *

× six = 24