ON ONE APPROACH FOR FEATURE SELECTION BASED ON THE APPLICATION OF THE METHOD OF LOGICAL ANALYSIS OF DATA

2021 ◽  
pp. 37-41
Author(s):  
Р.И. Кузьмич ◽  
А.А. Ступина ◽  
М.И. Цепкова ◽  
С.Н. Ежеманская
Keyword(s):  
Feature Selection ◽  
Logical Analysis ◽  
Classification Task ◽  
Logical Analysis Of Data ◽  
Selection Of

Предлагается подход для отбора важных признаков при классификации наблюдений. Реализация подхода основана на построении логических правил на базе метода логического анализа данных и учете частоты использования признаков при их формировании для конкретной задачи классификации. An approach is proposed for the selection of important features in the classification of observations. The implementation of the approach is based on the construction of patterns based on the method of logical analysis of data and taking into account the frequency of using features when forming them for a specific classification task.

scholarly journals An iterative feature selection procedure for a classification problem based on the method of logical analysis of data

2021 ◽  
Vol 2094 (3) ◽  
pp. 032054
Author(s):  
R I Kuzmich ◽  
A A Stupina ◽  
I S Zhirnova ◽  
O V Slinitsyna ◽  
I I Boubriak
Keyword(s):  
Feature Selection ◽  
Iterative Procedure ◽  
Selection Procedure ◽  
Classification Problem ◽  
Ranking And Selection ◽  
Logical Analysis ◽  
Logical Analysis Of Data ◽  
Selection Of

Abstract An iterative procedure for selecting features for classifying observations is proposed. The main principles of the proposed iterative procedure are ranking and selection of features according to the frequency of their use when constructing logical patterns based on the method of logical analysis of data. The empirical confirmation of the expediency of this procedure is given.

REDUCTION OF THE CLASSIFIER IN THE METHOD OF LOGICAL ANALYSIS OF DATA BASED ON THE Ε-, Δ-CRITERION FOR SELECTING PATTERN

2021 ◽  
pp. 4-8
Author(s):  
Р.И. Кузьмич ◽  
А.А. Ступина ◽  
В.А. Соколов ◽  
И.С. Поважнюк
Keyword(s):  
Training Sample ◽  
Logical Analysis ◽  
Logical Analysis Of Data ◽  
Sample Application ◽  
Subsequent Selection ◽  
Selection Of ◽  
Algorithmic Procedure

Предлагается алгоритмическая процедура редукции классификатора в методе логического анализа данных, основанная на отборе закономерностей с помощью ε-, δ-критерия. Реализация подхода заключается в формировании исходного классификатора как набора закономерностей на базе наблюдений обучающей выборки, применения к полученным правилам процедуры наращивания и последующего их отбора в новый классификатор на базе ε-, δ-критерия. Приводится эмпирическое подтверждение целесообразности данной алгоритмической процедуры. An algorithmic procedure for the reduction of the classifier in the method of logical analysis of data, based on the selection of patterns using the ε-, δ-criterion is proposed. The implementation of the approach consists in the formation of the initial classifier as a set of patterns based on observations of the training sample, application of the increasing procedure to the obtained patterns and their subsequent selection into a new classifier based on the ε-, δ-criterion. An empirical confirmation of the expediency of this algorithmic procedure is given.

scholarly journals A Feature Selection Approach in the Study of Azorean Proverbs

2014 ◽  
pp. 38-58 ◽  
Author(s):  
Luís Cavique ◽  
Armando B. Mendes ◽  
Matthias Funk ◽  
Jorge M. A. Santos
Keyword(s):  
Feature Selection ◽  
Real World ◽  
Rough Sets ◽  
Noisy Data ◽  
Logical Analysis ◽  
Logical Analysis Of Data ◽  
Selection Algorithm ◽  
Feature Selection Algorithm ◽  
Selection Approach ◽  
Feature Selection Approach

A paremiologic (study of proverbs) case is presented as part of a wider project based on data collected among the Azorean population. Given the considerable distance between the Azores islands, the authors present the hypothesis that there are significant differences in the proverbs from each island, thus permitting the identification of the native island of the interviewee based on his or her knowledge of proverbs. In this chapter, a feature selection algorithm that combines Rough Sets and the Logical Analysis of Data (LAD) is presented. The algorithm named LAID (Logical Analysis of Inconsistent Data) deals with noisy data, and the authors believe that an important link was established between the two different schools with similar approaches. The algorithm was applied to a real world dataset based on data collected using thousands of interviews of Azoreans, involving an initial set of twenty-two thousand Portuguese proverbs.

scholarly journals The Effect of Best First and Spreadsubsample on Selection of a Feature Wrapper With Na�ve Bayes Classifier for The Classification of the Ratio of Inpatients

2016 ◽  
Vol 3 (2) ◽  
pp. 139-148
Author(s):  
M Rizky Wijaya ◽  
Ristu Saptono ◽  
Afrizal Doewes
Keyword(s):  
Feature Selection ◽  
Training Dataset ◽  
Data Sampling ◽  
Bayes Classifier ◽  
American Hospital ◽  
Ve Bayes ◽  
Data Problem ◽  
Best First Search ◽  
Selection Of

Diabetes can lead to mortality and disability, so patients should be inpatient again to undergo treatment again to be saved. On previous research about feature selection with greedy stepwise forward fail to predict classification ratio inpatient of patient with the result of recall and precision 0 on data training 60%, 75%, 80%, and 90% and there is suggestion to handle unbalanced class data problem by comparison of data readmitted 6293 and the otherwise 64141. The research purposed to know the effect of choosing the best model using best first instead of greedy stepwise forward and data sampling with spreadsubsample to resolve unbalanced class data problem. The data used was patient data from 130 American Hospital in 1999 until 2008 with 70434 data. The method that used was best first search and spreadsubsample. The result of this research are precision found 0.4 and 0.333 on training dataset 75% and 90% with best first method, while spreadsubsample method found that value of precision and recall is more significantly increased. Spreadsubsample has more effect with the result of precision and recall rather than using best first method.

An Improved Naive Bayesian Classification Algorithm for Sentiment Classification of Microblogs

2014 ◽  
Vol 543-547 ◽  
pp. 3614-3620
Author(s):  
Zhi Qiang Li ◽  
De Quan Yang ◽  
Yuan Tan ◽  
Yuan Ping Zou
Keyword(s):  
Feature Selection ◽  
Bayesian Classification ◽  
Sentiment Classification ◽  
Experimental Result ◽  
Naive Bayesian ◽  
Naïve Bayesian ◽  
Correlation Degree ◽  
Weight Calculation ◽  
Selection Of

For the attribute-weighted based naive Bayesian classification algorithms, the selection of the weight directly affects the classification results. Based on this, the drawbacks of the TFIDF feature selection approaches in sentiment classification for the microblogs are analyzed, and an improved algorithm named TF-D(t)-CHI is proposed, which applies statistical calculation to obtain the correlation degree between the feature words and the classes. It presents the distribution of the feature items by variance in classes, which solves the problem that the short-texts contain few feature words while the high frequency feature words have too high weight. Experimental result indicate that TF-D(T)-CHI based naive Bayesian classification for feature selection and weight calculation has better classification results in sentiment classification for microblogs.

Reputation Scoring Fake News Using Text Mining

2017 ◽  
Vol 4 (1) ◽  
pp. 12-17
Author(s):  
Ahmad Firdaus
Keyword(s):  
Feature Selection ◽  
Decision Tree ◽  
Text Categorization ◽  
Information Gain ◽  
Feature Selection Method ◽  
Support Vector ◽  
Stable Level ◽  
Vector Machines ◽  
Selection Of

The classification of hoax news or news with incorrect information is one of the text categorization applications.Like text-based categorization of machine applications in general, this system consists of pre-processing andexecution of classification models. In this study, experiments were conducted to select the best technique in each sub-process by using 1200 articles hoax and 600 articles no hoax collected manually. This research Triedexperimenting to determine the best preprocessing stages between stop removals and stemming and showing the results of the deception Tree algorithm achieving an accuracy of 100% concluded above naive byes more stable level of accuracy in the number of datasets used in all candidates. Information gain, TFIDF and GGA based on using Naive Byes algorithm, supporting Vector Machine and Decision Tree no significant percentage change occurred on all candidates. But after using GGA (Optimize Generation) feature selection there is an increase of accuracy level The results of a comparison of classification algorithms between Naive Byes, decision trees and Support Vector machines combined with the GGA feature selection method for classifying the best result is generated by the selection of GGA + Decision Tree feature on candidate 2 (Paslon2) 100% and in the selection of the Information Gain + Decision Tree Feature selection with the lowest accuracy Candidate 3 at 36.67%, but overall improvement of accuracy Occurred on all algorithm after using feature selection and Naive byes more stable level of accuracy in the number of datasets used in all candidates.

Sign in / Sign up

Export Citation Format

Share Document