Free classifier software for linux

morigin email classifier is a filter that classifies and tags email messages based on the DNS information of the system submitting the mail to your organization.

morigin email classifier can then be used to improve upon existing spam filters such as SpamAssassin.

Layer-7 Packet Classifier for Linux is a packet classifier for Netfilter that identifies packets based on application layer (OSI layer 7) data. This means that it is able to classify packets as HTTP, FTP, Gnucleus, Kazaa, etc., regardless of ports.
It complements existing matches that classify based on port numbers, packet length, TOS bits, and so on. Combined with Linux QoS, it allows for full layer 7 packet shaping.
Main features:
- Patches for Linux 2.4 and 2.6
- Support for TCP, UDP and ICMP over IPv4
- Uses Netfilters connection tracking of FTP, IRC, etc
- Examines data across multiple packets
- Number of packets examined tunable on the fly through /proc
- Number of bytes examined tunable at module load time
- Distinguishes between new connections (those still being tested) and old unidentified connections
- Gives access to both Netfilter and QoS (rate limiting) features
- With the Netfilter "helper" match, you can distinguish between parent and child connections (e.g. ftp command/data)

Pattern Classification Program is an open-source machine learning program for supervised and unsupervised classification of patterns (vectors of measurements). Pattern Classification Program implements the following algorithms and methods:
- k-means clustering
- Fishers linear discriminant
- dimension reduction using Singular Value Decomposition
- Principal Component Analysis
- feature subset selection
- Bayes error estimation
- parametric classifiers (linear and quadratic)
- least-squares (pseudo-inverse) linear discriminant
- k-Nearest Neighbor
- neural networks (Multi-Layer Perceptron)
- Support Vector Machine algorithm
- cross-validation
- bagging (committee) classification
The program supports interactive and batch processing. Commands are issued through a keyboard-driven menu system in the interactive mode, or in a batch file in the batch mode. It is a binary executable and does not need any special run-time environment. PCP uses tab-delimited text files for input data. The results are displayed on the screen and saved in text files.
PCP runs under Linux and Windows operating systems (under Cygwin environment), on i386 architecture CPUs such as Intel Pentium or AMD Athlon. PCP has been developed and tested on RedHat Linux 9.0 distribution. It has also been tested on SUSE Linux 9.1 and Fedora Core 2 and verified to run on Knoppix 3.7 and Windows XP.
Enhancements:
- This release supports model selection for the linear SVM kernel and an option to build SVD transforms using training and test datasets (as opposed to just training data).
- P-errors are now reported in SVM model selection.
- The build process was simplified.

Gamera project is a framework for the creation of structured document analysis applications by domain experts. Domain experts are individuals who have a strong knowledge of the documents in a collection, but may not have a formal technical background.

The goal is to create a tool that leverages their knowledge of the target documents to create custom applications rather than attempting to meet diverse requirements with a monolithic application.

This paper gives an overview of the architecture and design principles of Gamera.

Developing recognition systems for difficult historical documents requires experimentation since the solution is often non-obvious. Therefore, Gameras primary goal is to support an efficient test-and-refine development cycle.

Virtually every implementation detail is driven by this goal. For instance, Python [Rossum2002] was chosen as the core language because of its introspection capabilities, dynamic typing and ease of use. It has been used as a first programming language with considerable success [Berehzny2001].

C++ is used to write plugins where runtime performance is a priority, but even in that case, the Gamera plugin system is designed to make writing extensions as easy as possible. Gamera includes a full-fledged graphical user interface that provides a number of shortcuts for training, as well as inspection of the results of algorithms at every step.

By improving the ease of experimentation, we hope to put the power to develop recognition systems with those who understand the documents best. We expect at least two kinds of developers to work with the system: those with a technical background adding algorithms to the system, and those working on the higher-level aggregation of those pieces. It is important to note this distinction, since those groups represent different skill sets and requirements.

In addition to its support of test-and-refine development, Gamera also has several other advantages that are important to large-scale digitization projects in general. These are:

* Open source code and standards-compliance so that the software can interact well with other parts of a digitization framework
* Platform independence, running on a variety of operating systems including Linux, Microsoft Windows and Mac OS-X
* A workflow system to combine high-level tasks
* Batch processing
* A unit-testing framework to ensure correctness and avoid regression
* User interface components for development and classifier training
* Recognition confidence output so that collection managers can easily target documents that need correction or different recognition strategies.

Gamera has a modular plugin architecture. These modules typically perform one of five document recognition tasks:

1. Pre-processing
2. Document segmentation and analysis
3. Symbol segmentation and classification
4. Syntactical or structural analysis
5. Output

Each of these tasks can be arbitrarily complex, involve multiple strategies or modules, or be removed entirely depending on the specific recognition problem at hand. The actual steps that make up a complete recognition system are completely controlled by the user.

Pre-processing involves standard image-processing operations such as noise removal, blurring, de-skewing, contrast adjustment, sharpening, binarization, and morphology. Close attention to and refinement of these steps is particularly important when working with degraded historical documents.

libbnr is an implementation of the Bayesian Noise Reduction (BNR) algorithm. All samples of text contain some degree of noise (data which is either intentionally or unintentionally irrelevant to accurate statistical analysis of the sample where removal of the data would result in a cleaner analysis).

The Bayesian noise reduction algorithm provides a means of cleaner machine learning by providing more useful data, which ultimately leads to better sample analysis. With the noisy data removed from the sample, what is left is only data relevant to the classification. libbnr can be linked in with your classifier and called using the standard C interface.

The Linux QoS Library (LQL) provides a GPL licensed, GObject based C API to manipulate the network queueing disciplines, classes and classifiers in the Linux kernel.

LQL does not use the TC command as a back-end. Instead, LQL communicates with the Linux kernel via Netlink sockets the same way TC does.
At the present time, LQL implements a subset of the Linux network QoS features exposed by the TC command.

Hopefully, this will change as the library matures.
In an ideal world TC would be implemented with a high(er) level API like LQL so that new kernel network QoS features would be immediately available to third party applications using the high level library.

Who knows what interesting innovations would have been created around the Linux network QoS features over the last few years if there was an easier API to manipulate them. LQL is an attempt to fill this need.

Queueing disciplines currently supported by LQL:

HTB
PFIFO
SFQ
PFIFOFast
Priomap
DSMark
Netem

Classifiers currently supported by LQL:

U32
Fwmark
TCIndex

Traffic Control Super Script implements traffic shaping for IP traffic passing through a NAT/bridge box with a single configuration file with one line per host.
Traffic Control Super Script can manage bandwidth to user-specified speeds based on the u32 classifier, and can identify traffic by source, destination, source and destination port, protocol, and ToS field. It then limits the rate of connection in either a single or a bidirectional fashion.
Enhancements:
- This release adds multiple interface support.
- It adds an option to choose between flat file and MySQL rules databases.
- It fixes bug #1469742 (duplicate group breaking child / parent relationships when direction=bi on group definitions).
- Various minor bugs have been fixed.
- There are major code cleanups, and major documentation updates on the Web site.

MACTS project is a traffic shaper that uses MAC addresses which are associated with users to classify traffic.
This allows fair usage of bandwidth among many machines. Additionally, there is a statistics monitor which displays current statistics on the terminal or stores them in round robin databases.
The stored data may then be used to generate graphs with the included Perl/CGI scripts. The configuration file is straight-forward and requires little knowledge of networking or the underlying traffic control mechanism. Setup should be easy.
Components:
macts - This clears the current traffic classifiers and sets up new ones, as directed by /etc/macts/macts.conf. It also stores some temporary state data in /etc/macts/handles.cache.
macts-stats - With no args, this displays statistics on a terminal, including data rate (kb/s), packet rate (packets/s), and backlog (packets) for each machine. Given the -r flag, it stores the statistics in round robin databases (one for each machine), located in /etc/macts/stats/.
macts-chart - This is a CLI chart generator which reads data from RRDs stored in /etc/macts/stats/.
macts-chart.cgi - This is a CGI wrapper for macts-chart.
Installation:
- mkdir /etc/macts
- mkdir /etc/macts/stats
- create /etc/macts/macts.conf
- add the following lines to /etc/sysctl.conf:
net.ipv4.conf.default.accept_source_route = 1 # is this necessary?
net.bridge.bridge-nf-filter-vlan-tagged = 0
net.bridge.bridge-nf-call-ip6tables = 0
net.bridge.bridge-nf-call-iptables = 0
net.bridge.bridge-nf-call-arptables = 0
- move macts, macts-stats, and macts-chart to /usr/local/bin/.
- (optional) install rrdtools and the perl rrdtool interface
- (optional) add the following line to roots cron:
*/5 * * * * /usr/local/bin/macts-stats -r 2&> /dev/null
- (optional) move macts-chart.cgi to your web servers cgi directory.
Enhancements:
- Installation instructions have been fixed.