Skip to content
/ NPSC Public

A Matlab software library for online stream classification

Notifications You must be signed in to change notification settings

AHosseini/NPSC

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

3 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

NPSC: The Matlab Online Bayesian Non-Parametric Stream Classification Package

Build Status License

NPSC is a Matlab software library for online stream classification. It aims to provide flexible modeling, learning, and inference of general dependent nonparametric models for classifying stream data with non-stationary generating process to capture the concept drift occur in large volume of various stream data arising from social networks, financial trading, etc.

Prerequisites

Features

  • A coherent generative model for stream classification

  • The model manages its complexity by adapting the size of the latent space and the number of classifiers over time.

  • Handling concept drift by adapting data-concept association without unnecessary i.i.d. assumption among data of a batch

  • An online algorithm for inference on the non-conjugate non-parametric time-dependent models.

Running The Code

  • Unzip the lightspeed library and put it in the root folder of the project

  • Run the install script

  • Set the Dataset in the "Main" Script

  • Run the Main script

The results will be saved under the folder Results

Citation

In case of using the code, please cite the following paper:

Hosseini, S.A., Rabiee, H.R., Hafez, H. and Soltani-Farani, A., 2014, September. Classifying a Stream of Infinite Concepts: A Bayesian Non-parametric Approach. In Joint European Conference on Machine Learning and Knowledge Discovery in Databases (pp. 1-16). Springer Berlin Heidelberg.

About

A Matlab software library for online stream classification

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages