An improved flexible partial histogram bayes learning algorithm

Haider O. Lawend, Anuar Mikdad Muad, Aini Hussain

Research output: Contribution to journalArticle

Abstract

This paper presents a proposed supervised classification technique namely flexible partial histogram Bayes (fPHBayes) learning algorithm. The traditional classification algorithms like neural network, support vector machine, first nearest neighbor, nearest subclass classifier and Gaussian mixture model classifier are accurate but slow when dealing with large number of instances. In additional to that these algorithms might require to be retrain when the classes changes. On the other hand, algorithms like naïve Bayes and nearest class mean are fast but not accurate. It is difficult and challenging to have a classification algorithm that is fast and accurate when dealing with large number of instances. In our previous work, partial histogram Bayes (PHBayes) learning algorithm showed some advantages in the aspects of speed and accuracy in classification tasks. However, its accuracy declines when dealing with small number of instances or when the class feature distributes in wide area. In this work, the proposed fPHBayes solves these limitations. fPHBayes is able to work fast with good accuracy with large and small number of instances. fPHBayes uses a probability distribution derived from smoothing the observed histogram in order to represent the class. Then it performs the classification using the Bayesian rule. fPHBayes was analyzed and compared with PHBayes and other standard learning algorithms like first nearest neighbor, nearest subclass mean, nearest class mean, naive Bayes and Gaussian mixture model classifier. The experiments were performed using both real data and synthetic data considering different number of instances and different variances of Gaussians. The results showed that fPHBayes is more accurate and flexible to deal with different number of instances and different variances of Gaussians as compared to other classifiers.

Original languageEnglish
Pages (from-to)975-986
Number of pages12
JournalIndonesian Journal of Electrical Engineering and Computer Science
Volume11
Issue number3
DOIs
Publication statusPublished - 1 Sep 2018

Fingerprint

Bayes
Learning algorithms
Histogram
Learning Algorithm
Partial
Classifiers
Classifier
Gaussian Mixture Model
Classification Algorithm
Nearest Neighbor
Probability distributions
Support vector machines
Neural networks
Supervised Classification
Naive Bayes
Synthetic Data
Smoothing
Support Vector Machine
Probability Distribution
Class

Keywords

  • Classification
  • Distribution
  • Histogram probability
  • Machine learning
  • Naïve bayes
  • PHBayes

ASJC Scopus subject areas

  • Signal Processing
  • Information Systems
  • Hardware and Architecture
  • Computer Networks and Communications
  • Control and Optimization
  • Electrical and Electronic Engineering

Cite this

An improved flexible partial histogram bayes learning algorithm. / Lawend, Haider O.; Muad, Anuar Mikdad; Hussain, Aini.

In: Indonesian Journal of Electrical Engineering and Computer Science, Vol. 11, No. 3, 01.09.2018, p. 975-986.

Research output: Contribution to journalArticle

@article{5a47da472f884b2caea0199e25a11b9a,
title = "An improved flexible partial histogram bayes learning algorithm",
abstract = "This paper presents a proposed supervised classification technique namely flexible partial histogram Bayes (fPHBayes) learning algorithm. The traditional classification algorithms like neural network, support vector machine, first nearest neighbor, nearest subclass classifier and Gaussian mixture model classifier are accurate but slow when dealing with large number of instances. In additional to that these algorithms might require to be retrain when the classes changes. On the other hand, algorithms like na{\"i}ve Bayes and nearest class mean are fast but not accurate. It is difficult and challenging to have a classification algorithm that is fast and accurate when dealing with large number of instances. In our previous work, partial histogram Bayes (PHBayes) learning algorithm showed some advantages in the aspects of speed and accuracy in classification tasks. However, its accuracy declines when dealing with small number of instances or when the class feature distributes in wide area. In this work, the proposed fPHBayes solves these limitations. fPHBayes is able to work fast with good accuracy with large and small number of instances. fPHBayes uses a probability distribution derived from smoothing the observed histogram in order to represent the class. Then it performs the classification using the Bayesian rule. fPHBayes was analyzed and compared with PHBayes and other standard learning algorithms like first nearest neighbor, nearest subclass mean, nearest class mean, naive Bayes and Gaussian mixture model classifier. The experiments were performed using both real data and synthetic data considering different number of instances and different variances of Gaussians. The results showed that fPHBayes is more accurate and flexible to deal with different number of instances and different variances of Gaussians as compared to other classifiers.",
keywords = "Classification, Distribution, Histogram probability, Machine learning, Na{\"i}ve bayes, PHBayes",
author = "Lawend, {Haider O.} and Muad, {Anuar Mikdad} and Aini Hussain",
year = "2018",
month = "9",
day = "1",
doi = "10.11591/ijeecs.v11.i3.pp975-986",
language = "English",
volume = "11",
pages = "975--986",
journal = "Indonesian Journal of Electrical Engineering and Computer Science",
issn = "2502-4752",
publisher = "Institute of Advanced Engineering and Science (IAES)",
number = "3",

}

TY - JOUR

T1 - An improved flexible partial histogram bayes learning algorithm

AU - Lawend, Haider O.

AU - Muad, Anuar Mikdad

AU - Hussain, Aini

PY - 2018/9/1

Y1 - 2018/9/1

N2 - This paper presents a proposed supervised classification technique namely flexible partial histogram Bayes (fPHBayes) learning algorithm. The traditional classification algorithms like neural network, support vector machine, first nearest neighbor, nearest subclass classifier and Gaussian mixture model classifier are accurate but slow when dealing with large number of instances. In additional to that these algorithms might require to be retrain when the classes changes. On the other hand, algorithms like naïve Bayes and nearest class mean are fast but not accurate. It is difficult and challenging to have a classification algorithm that is fast and accurate when dealing with large number of instances. In our previous work, partial histogram Bayes (PHBayes) learning algorithm showed some advantages in the aspects of speed and accuracy in classification tasks. However, its accuracy declines when dealing with small number of instances or when the class feature distributes in wide area. In this work, the proposed fPHBayes solves these limitations. fPHBayes is able to work fast with good accuracy with large and small number of instances. fPHBayes uses a probability distribution derived from smoothing the observed histogram in order to represent the class. Then it performs the classification using the Bayesian rule. fPHBayes was analyzed and compared with PHBayes and other standard learning algorithms like first nearest neighbor, nearest subclass mean, nearest class mean, naive Bayes and Gaussian mixture model classifier. The experiments were performed using both real data and synthetic data considering different number of instances and different variances of Gaussians. The results showed that fPHBayes is more accurate and flexible to deal with different number of instances and different variances of Gaussians as compared to other classifiers.

AB - This paper presents a proposed supervised classification technique namely flexible partial histogram Bayes (fPHBayes) learning algorithm. The traditional classification algorithms like neural network, support vector machine, first nearest neighbor, nearest subclass classifier and Gaussian mixture model classifier are accurate but slow when dealing with large number of instances. In additional to that these algorithms might require to be retrain when the classes changes. On the other hand, algorithms like naïve Bayes and nearest class mean are fast but not accurate. It is difficult and challenging to have a classification algorithm that is fast and accurate when dealing with large number of instances. In our previous work, partial histogram Bayes (PHBayes) learning algorithm showed some advantages in the aspects of speed and accuracy in classification tasks. However, its accuracy declines when dealing with small number of instances or when the class feature distributes in wide area. In this work, the proposed fPHBayes solves these limitations. fPHBayes is able to work fast with good accuracy with large and small number of instances. fPHBayes uses a probability distribution derived from smoothing the observed histogram in order to represent the class. Then it performs the classification using the Bayesian rule. fPHBayes was analyzed and compared with PHBayes and other standard learning algorithms like first nearest neighbor, nearest subclass mean, nearest class mean, naive Bayes and Gaussian mixture model classifier. The experiments were performed using both real data and synthetic data considering different number of instances and different variances of Gaussians. The results showed that fPHBayes is more accurate and flexible to deal with different number of instances and different variances of Gaussians as compared to other classifiers.

KW - Classification

KW - Distribution

KW - Histogram probability

KW - Machine learning

KW - Naïve bayes

KW - PHBayes

UR - http://www.scopus.com/inward/record.url?scp=85050344211&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85050344211&partnerID=8YFLogxK

U2 - 10.11591/ijeecs.v11.i3.pp975-986

DO - 10.11591/ijeecs.v11.i3.pp975-986

M3 - Article

VL - 11

SP - 975

EP - 986

JO - Indonesian Journal of Electrical Engineering and Computer Science

JF - Indonesian Journal of Electrical Engineering and Computer Science

SN - 2502-4752

IS - 3

ER -