Open Access Open Access  Restricted Access Subscription Access
Open Access Open Access Open Access  Restricted Access Restricted Access Subscription Access

Efficient Email Classification Approach Based on Semantic Methods


Affiliations
1 Department of Computer Science, GATE College, Tirupati, Andhra Pradesh, India
     

   Subscribe/Renew Journal


Considering the manner that of its ease, efficiency and ampleness, guileless Bayes (NB) has continued being likely the most notable 10 estimations inside the mastery mining and AI person’s crew. Of unique techniques to a good deal helpfully its unexpected possibility doubt, the characteristic weighting has put extra emphasis on essentially insightful functions than those that are extensively much less perceptive. Right currently, combat that for NB drastically perceptive capabilities have to be definitely related with the type (most outrageous simple noteworthiness), however uncorrelated with first-rate features (least regular redundancy). In angle on this reason, we propose an association hooked up perspective weighting (CFW) channel for NB [1, 2, 3].

Keywords

Correlation, Feature weighting, Mutual Information, Mutual Redundancy, Mutual Relevance, Naive Bayes.
Subscription Login to verify subscription
User
Notifications
Font Size



  • Efficient Email Classification Approach Based on Semantic Methods

Abstract Views: 430  |  PDF Views: 0

Authors

Alisha Afreen Shaik
Department of Computer Science, GATE College, Tirupati, Andhra Pradesh, India

Abstract


Considering the manner that of its ease, efficiency and ampleness, guileless Bayes (NB) has continued being likely the most notable 10 estimations inside the mastery mining and AI person’s crew. Of unique techniques to a good deal helpfully its unexpected possibility doubt, the characteristic weighting has put extra emphasis on essentially insightful functions than those that are extensively much less perceptive. Right currently, combat that for NB drastically perceptive capabilities have to be definitely related with the type (most outrageous simple noteworthiness), however uncorrelated with first-rate features (least regular redundancy). In angle on this reason, we propose an association hooked up perspective weighting (CFW) channel for NB [1, 2, 3].

Keywords


Correlation, Feature weighting, Mutual Information, Mutual Redundancy, Mutual Relevance, Naive Bayes.

References