Performance of machine learning methods for classification tasks
Journal Title: International Journal on Computer Science and Engineering - Year 2013, Vol 5, Issue 6
Abstract
In this paper, the performance of various machine learning methods on pattern classification and recognition tasks are proposed. The proposed method for evaluating performance will be based on the feature representation, feature selection and setting model parameters. The nature of the data, the methods of feature extraction and feature representation are discussed. The results of the Machine Learning algorithms on the classification task are analysed. The performance of Machine Learning methods on classifying Tamil word patterns, i.e., classification of noun and verbs are analysed. The software WEKA (data mining tool) is used for evaluating the performance. WEKA has several machine learning algorithms like Bayes, Trees, Lazy, Rule based classifiers.
Authors and Affiliations
B. Krithika , Dr. V. Ramalingam , K. Rajan
Keywords
Related Articles
- EP ID EP135818
- DOI -
- Views 92
- Downloads 0
Overview of techniques used for image resolution enhancement
Image resolution enhancement is one of the first steps in image processing. Image resolution enhancement is the process of manipulating an image so that resultant image is more suitable than the original one for specific...
PERFORMANCE EVALUATION OF THREEPHASE INDUCTION MOTOR DRIVE FED FROM Z-SOURCE INVERTER
This paper presents a Z-source inverter which has been proposed as an alternative power conversion concept for adjustable speed AC drives. It is having both voltages buck and boost capabilities as they allow inverters to...
Comparative study of various PKINIT methods used in Advanced Kerberos
Traditional authentication method is password, but it cannot resist dictionary and playback attack. Thus, applications, which send an unencrypted password over the network, are extremely vulnerable. Kerberos can be used...
A Survey on Security Issues in Wireless Ad hoc Network Routing Protocols
Abstract— An ad hoc wireless network is a collection of wireless mobile nodes that self-configure to construct a network without the need for any established infrastructure or backbone. Ad hoc networks use mobile nodes...
PRIORITY BASED UPLINK SCHEDULER FOR IEEE 802.16 NETWORKS
IEEE 802.16, the standard for fixed, portable and mobile Broadband Wireless Access (BWA) systems, is promising to support different classes of traffic with Quality of Service (QoS). The Medium Access Control (MAC) protoc...