User Tools

Site Tools

You are here: start » rvkde » readme
Trace:
rvkde:readme

Differences

This shows you the differences between two versions of the page.

Link to this comparison view

Both sides previous revisionPrevious revision
rvkde:readme [2008/08/07 01:17] – dirtyrvkde:readme [2008/08/19 01:11] (current) – external edit 127.0.0.1
Line 1: Line 1:
 ====== Abstract ====== ====== Abstract ======
 RVKDE, standing for Relaxed Variable Kernel Density Estimation, is an RVKDE, standing for Relaxed Variable Kernel Density Estimation, is an
-integrated software of classification, regression and density estimation. This+integrated software of classification, regression and density estimation.  This
 document explains the use of RVKDE. document explains the use of RVKDE.
  
-RVKDE is available at 'http://mbi.ee.ncku.edu.tw/rvkde/'. Please read the+RVKDE is available at 'http://mbi.ee.ncku.edu.tw/rvkde/'.  Please read the
 COPYRIGHT file before using RVKDE. COPYRIGHT file before using RVKDE.
  
Line 10: Line 10:
   - Quick start   - Quick start
   - Installation and data format   - Installation and data format
-  - //kde-train.pl// usage +  - __kde-train.pl__ usage 
-  - //kde-predict.pl// usage+  - __kde-predict.pl__ usage
   - Additional tools   - Additional tools
   - Additional information   - Additional information
  
 ====== Quick start ====== ====== Quick start ======
-If you are new to RVKDE and if the data is not large, please go to //tool// +If you are new to RVKDE and if the data is not large, please go to __tool__ 
-directory and use //kde-easy.pl// after installation. It does everything, from+directory and use __kde-easy.pl__ after installation.  It does everything, from
 data scaling to parameter selection, automatic. data scaling to parameter selection, automatic.
  
Line 24: Line 24:
 </code> </code>
  
-More information about parameter selection can be found in //tool/README//.+More information about parameter selection can be found in __tool/README__
  
 ====== Installation and data format ====== ====== Installation and data format ======
Line 53: Line 53:
 </code> </code>
   - Execute them without arguments to show the usages.   - Execute them without arguments to show the usages.
-  - Using //cd// to the directory of your extracted RVKDE.+  - Using __cd__ to the directory of your extracted RVKDE.
   - Execute them without arguments to show the usages.<code>   - Execute them without arguments to show the usages.<code>
 kde-train.pl kde-train.pl
Line 70: Line 70:
 Each line contains an instance and is ended by a '\n' character.  For Each line contains an instance and is ended by a '\n' character.  For
 classification, <value> is an integer indicating the class label (multi-class classification, <value> is an integer indicating the class label (multi-class
-is supported). For regression, <value> is the target value which can be any +is supported).  For regression, <value> is the target value which can be any 
-real number. <index>:<feature> gives a feature (attribute) value. <index> is an +real number.  <index>:<feature> gives a feature (attribute) value.  <index> is 
-integer starting from 1 and <feature> is a real number. Labels in the testing +an integer starting from 1 and <feature> is a real number.  Labels in the 
-file are only used to calculate accuracy or errors. If they are unknown, just +testing file are only used to calculate accuracy or errors.  If they are 
-fill the first column with any numbers.+unknown, just fill the first column with any numbers.
  
-A sample classification data included in this package is **heart.scale**. +A sample classification data included in this package is __satimage__.  Type 
-Type //kde-train.pl heart.scale//, and the program will read the training +__kde-train.pl satimage.scale__, and the program will read the training data 
-data and output the model file //heart.scale.model//. If you have a test set +and output the model file __satimage.scale.model__.  If you have a test set 
-called //heart.scale.t//, then type //kde-predict.pl heart.scale.t +called __satimage.scale.t__, then type __kde-predict.pl satimage.scale.t 
-heart.scale.model output// to see the prediction accuracy. The //output// file +satimage.scale.model output__ to see the prediction accuracy.  The __output__ 
-contains the predicted class labels.<code> +file contains the predicted class labels.<code> 
-kde-train.pl heart.scale # train +kde-train.pl satimage.scale # train 
-kde-predict.pl heart.scale.t heart.scale.model output # predict+kde-predict.pl satimage.scale.t satimage.scale.model output # predict
 vi output # predicted results vi output # predicted results
 </code> </code>
Line 91: Line 91:
 Usage: kde-train.pl [OPTION]... TRAINING_FILE [MODEL_FILE] Usage: kde-train.pl [OPTION]... TRAINING_FILE [MODEL_FILE]
 kde-train.pl is a Perl wrapper for RVKDE to make the using of RVKDE like kde-train.pl is a Perl wrapper for RVKDE to make the using of RVKDE like
-LIBSVM. Make sure the rvkde binary executable file is in the same directory+LIBSVM.  Make sure the rvkde binary executable file is in the same directory
 of this script. of this script.
  
Line 103: Line 103:
  
 Examples: Examples:
-  kde-train.pl heart.scale # generate heart.scale.model +  kde-train.pl satimage.scale # generate satimage.scale.model 
-  kde-train.pl heart.scale heart.scale.kde-model # different model name +  kde-train.pl satimage.scale satimage.scale.kde-model # different model name 
-  kde-train.pl -v 5 heart.scale # five-fold cross validation +  kde-train.pl -v 5 satimage.scale # five-fold cross validation 
-  kde-train.pl -s 30 heart.scale # using different parameters+  kde-train.pl -s 30 satimage.scale # using different parameters
  
 Option -v splits the data into n parts by modulo arithmetic and calculates Option -v splits the data into n parts by modulo arithmetic and calculates
Line 118: Line 118:
 Usage: kde-predict.pl [OPTION]... TESTING_FILE MODEL_FILE OUTPUT_FILE Usage: kde-predict.pl [OPTION]... TESTING_FILE MODEL_FILE OUTPUT_FILE
 kde-predict.pl is a Perl wrapper for RVKDE to make the using of RVKDE like kde-predict.pl is a Perl wrapper for RVKDE to make the using of RVKDE like
-LIBSVM. Make sure the rvkde binary executable file is in the same directory+LIBSVM.  Make sure the rvkde binary executable file is in the same directory
 of this script. of this script.
  
Line 133: Line 133:
  
 Examples: Examples:
-  kde-predict.pl heart.scale.t heart.scale.model output +  kde-predict.pl satimage.scale.t satimage.scale.model output 
-  kde-predict.pl -s 30 -t 30 heart.scale.t heart.scale.model output+  kde-predict.pl -s 30 -t 30 satimage.scale.t satimage.scale.model output
  
-Unlike LIBSVM, RVKDE is a lazy-learning tool. The model file contains only+Unlike LIBSVM, RVKDE is a lazy-learning tool.  The model file contains only
 basic information and the real prediction model is constructed right before the basic information and the real prediction model is constructed right before the
-prediction operation. It means you can specify different parameters (alpha, +prediction operation.  It means you can specify different parameters (alpha, 
-beta, ks and kt) for kde-predict.pl as those specified for kde-train.pl. Only+beta, ks and kt) for kde-predict.pl as those specified for kde-train.pl.  Only
 one condition must be hold: the ks for kde-predict.pl is less than or equal to one condition must be hold: the ks for kde-predict.pl is less than or equal to
 the ks for kde-train.pl. the ks for kde-train.pl.
Line 154: Line 154:
 Yen-Jen Oyang, Shien-Ching Hwang, Yu-Yen Ou, Chien-Yu Chen, and Zhi-Wei Chen. Yen-Jen Oyang, Shien-Ching Hwang, Yu-Yen Ou, Chien-Yu Chen, and Zhi-Wei Chen.
 Data Classification with the Radial Basis Function Network Based on a Novel Data Classification with the Radial Basis Function Network Based on a Novel
-Kernel Density Estimation Algorithm. //IEEE Transactions on Neural Networks//,+Kernel Density Estimation Algorithm.  //IEEE Transactions on Neural Networks//,
 **16**, 225-236, 2005. **16**, 225-236, 2005.
  
Line 163: Line 163:
 Acknowledgments: Acknowledgments:
 This work was supported in part by the National Science Council of Taiwan via This work was supported in part by the National Science Council of Taiwan via
-the grant NSC 92-2213-E-002-095. The authors thank their group members and+the grant NSC 92-2213-E-002-095.  The authors thank their group members and
 users for many helpful discussions and comments. users for many helpful discussions and comments.
 +
rvkde/readme.1218071864.txt.gz · Last modified: by dirty

Page Tools

Except where otherwise noted, content on this wiki is licensed under the following license: CC Attribution-Noncommercial-Share Alike 4.0 International
CC Attribution-Noncommercial-Share Alike 4.0 International Donate Powered by PHP Valid HTML5 Valid CSS Driven by DokuWiki

Copyright © 2006-2014 MBI Lab. All rights reserved.

  • Service
  • DBD2BS: connecting a DNA-binding protein with its binding sites
  • E1DS: predicting catalytic sites based on 1-dimensional signatures
  • PRASA: an integrated web server that analyzes protein interaction types
  • Prote2s: predicting protein secondary structures
  • seeMotif: exploring and visualizing sequence motifs in 3D structures
  • MEDock: a docking web server for efficient prediction of protein-ligand binding sites
  • Protemot: predicting protein binding sites with automatically extracted geometrical templates
  • YGA: identifying distinct biological features between yeast gene sets
  • Database
  • AH-DB: collecting protein structure pairs before and after bindingan hot
  • YPA: collecting promoter features in Saccharomyces cerevisiae
  • Collaborative
  • iPDA: a integrated protein disorder analyzer
  • ProteDNA: Predictor of sequence-specific DNA-binding residues in transcription factors
  • MAGIIC-PRO: discovering functional long motifs that are interleaved by several large irregular gaps