Application and comparison of different classification methods based on symptom analysis with traditional classification technique for breast cancer diagnosis

Standard

Application and comparison of different classification methods based on symptom analysis with traditional classification technique for breast cancer diagnosis. / Al-Juboori, F. S. ; Alexeyeva, N. P. .

In: Periodicals of Engineering and Natural Sciences, Vol. 8, No. 4, 2020, p. 2146-2159.

Research output: Contribution to journal › Article › peer-review

BibTeX

@article{9eec744600fb45c597612f95679fedfa,

title = "Application and comparison of different classification methods based on symptom analysis with traditional classification technique for breast cancer diagnosis",

abstract = "Novel approach for classification technique such as Artificial Neural Network (ANN), Linear Discriminant Analysis (LDA) and Random Forest (RF) using factor or dichotomic variables has been introduced. This study searches for the highly informative finitely linear combinations (symptoms) of variables in the finite field on the based of the Fisher{\textquoteright}s exact test and accurately predict the target class for each case in the data. There are several super symptoms have comparable p-values. In this case, it becomes possible to choose as a nominative representative the factor which is more accessible for interpretation. The super symptom means a linear combination of various multiplications of k dichotomous variables over a field of characteristic 2 without repeating. In algebra, such functions are called Zhegalkin polynomials or algebraic normal forms.",

keywords = "symptom analysis, artificial neural network, linear discriminant analysis, random forest, breast cancer, accuracy",

author = "Al-Juboori, {F. S.} and Alexeyeva, {N. P.}",

year = "2020",

language = "English",

volume = "8",

pages = "2146--2159",

journal = "Periodicals of Engineering and Natural Sciences",

issn = "2303-4521",

publisher = "International University of Sarajevo",

number = "4",

}

RIS

TY - JOUR

T1 - Application and comparison of different classification methods based on symptom analysis with traditional classification technique for breast cancer diagnosis

AU - Al-Juboori, F. S.

AU - Alexeyeva, N. P.

PY - 2020

Y1 - 2020

N2 - Novel approach for classification technique such as Artificial Neural Network (ANN), Linear Discriminant Analysis (LDA) and Random Forest (RF) using factor or dichotomic variables has been introduced. This study searches for the highly informative finitely linear combinations (symptoms) of variables in the finite field on the based of the Fisher’s exact test and accurately predict the target class for each case in the data. There are several super symptoms have comparable p-values. In this case, it becomes possible to choose as a nominative representative the factor which is more accessible for interpretation. The super symptom means a linear combination of various multiplications of k dichotomous variables over a field of characteristic 2 without repeating. In algebra, such functions are called Zhegalkin polynomials or algebraic normal forms.

AB - Novel approach for classification technique such as Artificial Neural Network (ANN), Linear Discriminant Analysis (LDA) and Random Forest (RF) using factor or dichotomic variables has been introduced. This study searches for the highly informative finitely linear combinations (symptoms) of variables in the finite field on the based of the Fisher’s exact test and accurately predict the target class for each case in the data. There are several super symptoms have comparable p-values. In this case, it becomes possible to choose as a nominative representative the factor which is more accessible for interpretation. The super symptom means a linear combination of various multiplications of k dichotomous variables over a field of characteristic 2 without repeating. In algebra, such functions are called Zhegalkin polynomials or algebraic normal forms.

KW - symptom analysis

KW - artificial neural network

KW - linear discriminant analysis

KW - random forest

KW - breast cancer

KW - accuracy

UR - http://pen.ius.edu.ba/index.php/pen

UR - http://pen.ius.edu.ba/index.php/pen/article/view/1720

M3 - Article

VL - 8

SP - 2146

EP - 2159

JO - Periodicals of Engineering and Natural Sciences

JF - Periodicals of Engineering and Natural Sciences

SN - 2303-4521

IS - 4

ER -

ID: 71607997