|
| This Article | ||
| ||
| Share | ||
| Bibliographic References | ||
| Add to: | ||
 Digg  Furl  Spurl  Blink  Simpy  Google  Del.icio.us  Y!MyWeb | ||
| Search | ||
| ||
| ASCII Text | x | ||
| Kentaro Onizuka, Tamotsu Noguchi, Yutaka Akiyama, Hideo Matsuda, "Using Data Compression for Multidimensional Distribution Analysis," IEEE Intelligent Systems, vol. 17, no. 3, pp. 48-54, May/June, 2002. | |||
| BibTex | x | ||
| @article{ 10.1109/MIS.2002.1005631, author = {Kentaro Onizuka and Tamotsu Noguchi and Yutaka Akiyama and Hideo Matsuda}, title = {Using Data Compression for Multidimensional Distribution Analysis}, journal ={IEEE Intelligent Systems}, volume = {17}, number = {3}, issn = {1541-1672}, year = {2002}, pages = {48-54}, doi = {http://doi.ieeecomputersociety.org/10.1109/MIS.2002.1005631}, publisher = {IEEE Computer Society}, address = {Los Alamitos, CA, USA}, } | |||
| RefWorks Procite/RefMan/Endnote | x | ||
| TY - MGZN JO - IEEE Intelligent Systems TI - Using Data Compression for Multidimensional Distribution Analysis IS - 3 SN - 1541-1672 SP48 EP54 EPD - 48-54 A1 - Kentaro Onizuka, A1 - Tamotsu Noguchi, A1 - Yutaka Akiyama, A1 - Hideo Matsuda, PY - 2002 KW - linear compression KW - mean-force potentials KW - multidimensional distribution KW - spherical Bessel KW - spherical harmonics VL - 17 JA - IEEE Intelligent Systems ER - | |||
The authors propose a method for multidimensional distribution analysis using a data compression technique. The method avoids the explosion in number of parameters (or coefficients) representing a multidimensional distribution even when the distribution has many dimensions (up to six dimensions or more). In the method, a multidimensional distribution is linearly expanded into a set of expansion coefficients. The expansion procedure neglects high-order cross-terms and reduces the total number of coefficients representing the distribution. This compression technique resemble DCT-based image data compression for computer vision.The authors applied the method to the knowledge-based mean-force potentials between residues for the analysis of protein sequence structure compatibility. They obtain the mean-force potentials by the multidimensional distribution of relative configurations (essentially 6D) between residues. The performance of the multidimensional mean-force potentials measured by native-structure-recognition tests was proved much higher than the performance of conventional 1D distance-based potentials derived from binned distributions.