Analysis Of Weka Tools And Its Classification Algorithms Essay

976 Words Mar 12th, 2015 4 Pages
In section II, WEKA tools and its classification algorithms have been discussed in detail. The performance metrics have been analyzed in section III. Dataset description has been explained in section IV while results along with further analysis has been presented in section V followed by conclusion in section VI.
WEKA is a tool for Data mining and Machine Learning. The University of Waikato, New Zealand first implemented it in 1997 [4]. It is a collection of an enormous number of Machine Learning and Data Mining algorithms. One drawback of this software is that it supports data files only written in ARFF (attribute relation file format) and CSV (comma separated values) format. Initially it was written in C but later on it was rewritten in JAVA language. It comprises of a GUI interface for interaction with the data files. It possesses 49 data pre-processing tools, 15 attribute evaluators, 76 classification algorithms and 10 search algorithms for the purpose of feature selection. It comprises of three graphical user interfaces:- “The Explorer”, “The Experimenter”, and “The Knowledge Flow”. WEKA provides the opportunity for the development of any new Machine Learning algorithm. It contains visualization tools and a set to panels to execute the desired tasks.
Classification algorithms or classifiers are used to basically sort out the network traffic into normal and anomaly categories. The objective of classification is to construct a…

Related Documents