Training Set Compression by Incremental Clustering

 
Thread Tools Search this Thread
Special Forums News, Links, Events and Announcements UNIX and Linux RSS News Training Set Compression by Incremental Clustering
# 1  
Old 02-23-2011
Training Set Compression by Incremental Clustering

HPL-2011-25 Training Set Compression by Incremental Clustering - Li, Dalong; Simske, Steven
Keyword(s): Clustering, Support vector machine, KNN, Pattern recognition, CONDENSE.
Abstract: Compression of training sets is a technique for reducing training set size without degrading classification accuracy. By reducing the size of a training set, training will be more efficient in addition to saving storage space. In this paper, an incremental clustering algorithm, the Leader algorithm, ...
Full Report

More...
Login or Register to Ask a Question

Previous Thread | Next Thread

9 More Discussions You Might Find Interesting

1. UNIX for Beginners Questions & Answers

Clustering for beginners. Few questions.

Hello! I need some advices from You. How many days i need to setup cluster using virtual box for mid exp user? Do you have any ideas related to master thesis related to clustering? I need to include some search aspect within that topic.Can You recommend some books/docs about that case? Thank... (4 Replies)
Discussion started by: protos27
4 Replies

2. Ubuntu

Newbie With Linux Clustering, Need Help!!

Hi All, I am new user here and a new one to try clustering with Ubuntu nodes, and need help. If I should be in another place please mention. I have a two nodes with Ubuntu 14.04 installed on them. I need to make a cluster consisting of these two nodes with purpose of experimentation with... (3 Replies)
Discussion started by: IncognitoExpert
3 Replies

3. HP-UX

HP-UX Clustering

Hello guys, I would like to ask for your assistance, since i am new to HP-UX. Please give me some documentation about clustering in HP-UX. More precisely design,architecture, configuring etc. I am working on my master thesis right now and would like to include some guidance about that.... (1 Reply)
Discussion started by: bazillion
1 Replies

4. Red Hat

Clustering Technology Documentation

Hello, I'm new in this forum. I'll have a new project to change architecture for our servers. From one server where we found database oracle 9i and Oracle application ebs 11 installed in HPux to cluster that contain nodes in redhat. Can you give me a detailed documentation that... (1 Reply)
Discussion started by: Safi1982
1 Replies

5. Linux

Linux os clustering

Hi, I have done the OS clustering in linux redhat 5.6, my one node is down and when i am trying to reboot the other node it is not coming up. any pointer to this would be helpful. the SAN storage luns are not coming as mounted (2 Replies)
Discussion started by: mohitj.engg
2 Replies

6. UNIX for Dummies Questions & Answers

Linux Clustering

hi guys Some time ago I used Linux HA(Heartbeat) to setup like 3 cluster. Now I have to install another 2 cluster and was checking more info to be sure HA was still used but I found some other stuff like OpenAIS - Corosync - Pacemaker to tell you the truth I am kinda confused here I get... (0 Replies)
Discussion started by: karlochacon
0 Replies

7. Solaris

Clustering filesystems

SunOS 5.10 Generic_142900-15 sun4u sparc SUNW,SPARC-Enterprise How can I tell if "clustering" is being used in my shop? I have to file systems that are identical. These filesystems are nfs mounted. But how can I tell if they are being kept in sync as a result of clustering or some other... (2 Replies)
Discussion started by: Harleyrci
2 Replies

8. UNIX for Dummies Questions & Answers

training unix set up for a p.c.

I'm looking for a free unix download(for a p.c. which I think is running xp) to simulate or mirror a unix operating system to teach a friend basic unix skills for an interview. I saw the solaris link, but couldn't really tell if it would work on a p.c. And I don't want to mess with his operating... (9 Replies)
Discussion started by: mmtemp
9 Replies

9. UNIX for Dummies Questions & Answers

Clustering or not

I woulld like to use the JDE newest version, but I am considering whether using 2 X Wintel server with clustering or 1 Unix server without clustering. Is Unix stable enough to except the clustering? (0 Replies)
Discussion started by: superlouis
0 Replies
Login or Register to Ask a Question
Dpkg::Compression::FileHandle(3)				   libdpkg-perl 				  Dpkg::Compression::FileHandle(3)

NAME
Dpkg::Compression::FileHandle - object dealing transparently with file compression SYNOPSIS
use Dpkg::Compression::FileHandle; $fh = Dpkg::Compression::FileHandle->new(filename=>"sample.gz"); print $fh "Something "; close $fh; $fh = Dpkg::Compression::FileHandle->new(); open($fh, ">", "sample.bz2"); print $fh "Something "; close $fh; $fh = Dpkg::Compression::FileHandle->new(); $fh->open("sample.xz", "w"); $fh->print("Something "); $fh->close(); $fh = Dpkg::Compression::FileHandle->new(filename=>"sample.gz"); my @lines = <$fh>; close $fh; $fh = Dpkg::Compression::FileHandle->new(); open($fh, "<", "sample.bz2"); my @lines = <$fh>; close $fh; $fh = Dpkg::Compression::FileHandle->new(); $fh->open("sample.xz", "r"); my @lines = $fh->getlines(); $fh->close(); DESCRIPTION
Dpkg::Compression::FileHandle is an object that can be used like any filehandle and that deals transparently with compressed files. By default, the compression scheme is guessed from the filename but you can override this behaviour with the method "set_compression". If you don't open the file explicitly, it will be auto-opened on the first read or write operation based on the filename set at creation time (or later with the "set_filename" method). Once a file has been opened, the filehandle must be closed before being able to open another file. STANDARD FUNCTIONS
The standard functions acting on filehandles should accept a Dpkg::Compression::FileHandle object transparently including "open" (only when using the variant with 3 parameters), "close", "binmode", "eof", "fileno", "getc", "print", "printf", "read", "sysread", "say", "write", "syswrite", "seek", "sysseek", "tell". Note however that "seek" and "sysseek" will only work on uncompressed files as compressed files are really pipes to the compressor programs and you can't seek on a pipe. FileHandle METHODS The object inherits from FileHandle so all methods that work on this object should work for Dpkg::Compression::FileHandle too. There may be exceptions though. PUBLIC METHODS
my $fh = Dpkg::Compression::FileHandle->new(%opts) Creates a new filehandle supporting on-the-fly compression/decompression. Supported options are "filename", "compression", "compression_level" (see respective set_* functions) and "add_comp_ext". If "add_comp_ext" evaluates to true, then the extension corresponding to the selected compression scheme is automatically added to the recorded filename. It's obviously incompatible with automatic detection of the compression method. $fh->ensure_open($mode) Ensure the file is opened in the requested mode ("r" for read and "w" for write). Opens the file with the recorded filename if needed. If the file is already open but not in the requested mode, then it errors out. $fh->set_compression($comp) Defines the compression method used. $comp should one of the methods supported by Dpkg::Compression or "none" or "auto". "none" indicates that the file is uncompressed and "auto" indicates that the method must be guessed based on the filename extension used. $fh->set_compression_level($level) Indicate the desired compression level. It should be a value accepted by the function "compression_is_valid_level" of Dpkg::Compression. $fh->set_filename($name, [$add_comp_ext]) Use $name as filename when the file must be opened/created. If $add_comp_ext is passed, it indicates whether the default extension of the compression method must be automatically added to the filename (or not). my $file = $fh->get_filename() Returns the filename that would be used when the filehandle must be opened (both in read and write mode). This function errors out if "add_comp_ext" is enableactivated while the compression method is set to "auto". The returned filename includes the extension of the compression method if "add_comp_ext" is enabled. $ret = $fh->use_compression() Returns "0" if no compression is used and the compression method used otherwise. If the compression is set to "auto", the value returned depends on the extension of the filename obtained with the get_filename method. my $real_fh = $fh->get_filehandle() Returns the real underlying filehandle. Useful if you want to pass it along in a derived object. DERIVED OBJECTS
If you want to create an object that inherits from Dpkg::Compression::FileHandle you must be aware that the object is a reference to a GLOB that is returned by Symbol::gensym() and as such it's not a HASH. You can store internal data in a hash but you have to use "*$self-"{...}> to access the associated hash like in the example below: sub set_option { my ($self, $value) = @_; *$self->{"option"} = $value; } AUTHOR
Raphael Hertzog <hertzog@debian.org> 1.16.0.3 2012-04-17 Dpkg::Compression::FileHandle(3)