Title :
Data analysis and visualization using spectral decomposition and feature selection
Author :
Kamran, Arezoo ; Shamail, Shafay ; Awais, Mian M.
Author_Institution :
Dept. of Comput. Sci., Lahore Univ. of Manage. Sci. (LUMS), Lahore, Pakistan
Abstract :
The aim of this study is to develop a technique to mine time series data and extract patterns from it which help it to be visualized easily. These visualizations can be static or dynamic while showing the long term dominant trends in data and subduing the short term recurring features. The focus is on time series data from economics and business.
Keywords :
business data processing; data analysis; data mining; data visualisation; economics; time series; business data; data analysis; data visualization; dominant data trends; economics data; feature selection; pattern extraction; short term recurring features; spectral decomposition; time series data mining; Data mining; Data visualization; Discrete cosine transforms; Feature extraction; Market research; Time series analysis; Visualization; Data Mining; Data Visualization; Feature selection; Spectral Decomposition; Time Series Analysis; Trend Highlighting;
Conference_Titel :
Emerging Technologies (ICET), 2013 IEEE 9th International Conference on
Conference_Location :
Islamabad
Print_ISBN :
978-1-4799-3456-0
DOI :
10.1109/ICET.2013.6743528
