Japanese
research
We propose a visualization technique which support the analysis of multi variate time series data through overview and compression.
Colorscore: Visualization of musical structure of classical music
Demonstration movie (.avi)
The objective of the music information visualization includes visualizing internal constitution of one piece of music, in addition to listing many pieces of music.
This visualization method is valuable for assistance of composition and arrengement of music, practicing musical instruments and conducting, and education for beginners.
We have proposed the system called 'Colorscore' that can visualize and summarize the full score.
Colorscore extracts some compositional patterns of the score and shows in different colors so that it can visualize the internal constitution of the music.
Colorscore is also capable of summurizing and displaying the music by the compressed representation of the visualized result in both cross and longitudinal directions.
Above figure shows the visualization result of "Waltz des fleurs" composed by Tchaikovsky. Colorscore assigns parts(instruments) to vertical axis and time(bars) to horizontal axis.
Each color shows the role (for example main melody or accompaniment of each phrase.
Visualization of tendencies of system logs
Demonstration movie (.avi)
System logs such as transactions of credit cards and access logs of web cites can be treated as multi variate time series.
Through the analysis of these system logs, we can discover the tendency of overall logs, especially fraudulent or error logs,
and determine the preferable timing of campaign or renewal.
We propose Visual Analytics Tool which support effective analysis of such multi variate and large scale time series.
Proposed method shows overview of tendency of time series by heatmap, and the user can apply two kinds of compression,
compression by sort and compresion by clustering.
The tool also realize attribute recommendation which recommends attribute which brings the interesting result by the colors of buttons.
Above figure shows user interface and an example of visualization result.
For visualization, we assign time to X-axis, and the value of attributes to Y-axis, and colors to total occurences (warmer color means large amount of occurences) to visualize the tendency of time series.