Incrementally Exploring Large-scale Multidimensional Data
Jaemin Jo, Wonjae Kim, Seunghoon Yoo, Bohyoung Kim, and Jinwook Seo / 2017
PARTICIPANTS
- Jaemin Jo, Seoul National University, Seoul, Republic of Korea
- Wonjae Kim, Seoul National University, Seoul, Republic of Korea
- Seunghoon Yoo, Seoul National University, Seoul, Republic of Korea
- Bohyoung Kim, Hankuk University of Foreign Studies, Yongin-si, Republic of Korea
- Jinwook Seo, Seoul National University, Seoul, Republic of Korea
ABSTRACT
The advance in distributed computing technologies opens up new possibilities of data exploration even for datasets with a few billion entries. In this paper, we present SwiftTuna, an interactive system that brings in modern cluster computing technologies (i.e., in-memory computing) to InfoVis, allowing rapid and incremental exploration of large-scale multidimensional data without building precomputed data structures (e.g., data cubes). Our performance evaluation demonstrates that SwiftTuna enables data exploration of a real-world dataset with four billion records while preserving the latency between incremental responses within a few seconds.
VIDEO
SUPPORT
This work was supported by the National Research Foundation of Korea (NRF) grants funded by the Korea government (MSIP) (No. NRF-2014R1A2A2A03006998 and NRF-2016R1A2B2007153) and by the Hankuk University of Foreign Studies Research Fund of 2016. Bohyoung Kim and Jinwook Seo are the corresponding authors.
Publications
- Jaemin Jo, Wonjae Kim, Seunghoon Yoo, Bohyoung Kim, and Jinwook Seo, "SwiftTuna: Incrementally Exploring Large-scale Multidimensional Data", [PDF], IEEE VIS 2016
- Jaemin Jo, Wonjae Kim, Seunghoon Yoo, Bohyoung Kim, and Jinwook Seo, SwiftTuna: Responsive and Incremental Visual Exploration of Large-scale Multidimensional Data, [PDF], 10th IEEE Pacific Visualization Symposium (PacificVis '17)