Tuning approach to improve multilayer perceptron for breast cancer prediction

Other Title(s)

أسلوب ضبط لتحسين التنبؤ بسرطان الثدي باستخدام قاعدة الإدراك متعددة الطبقات

Dissertant

al-Shami, Fida Musa Ahmad

Thesis advisor

al-Sharjabi, Bassam

University

Middle East University

Faculty

Faculty of Information Technology

Department

Computer Science Department

University Country

Jordan

Degree Date

2019

English Abstract

Breast Cancer has turned into a typical disease around the globe in young women and the main source of cancer death and caused 22.9% of a wide range of cancers in women.

The development of massive breast cancer screening has led to earlier diagnosis and rapid management with a significant improvement in survival rate.

The problem of automatically searching for information contained in medical images is extremely needed.

There is difficulty in interpretation these images as well as their large numbergenerates tedious work for those who must interpret them.

In order to process this large volume of information, doctors are currently turning to the use of systems to assist in the analysis and interpretation of these images.

This could be achieved by Machine Learning (ML) techniques.

The proposed approach in this thesis compares the ML algorithms (KNN, RF and MLP) of the classification on the breast cancer WDBC dataset to obtain the best algorithms in the results.

Then it identifies the most specific and relevant attributes of the malignant tumour classification through more than one feature selection algorithms.

Next, it determines which activation function for MLP that produces a more accurate result.

Finally, tuned MLP and comparing evaluation metrics in machine learning for original MLP and tuned MLP.

The experimental results over WDBC dataset showed that the accuracy enhancement of proposed Tuned MLP compared to the original MLP is around 1.07%

Main Topic

Diseases
Information Technology and Computer Science

Topics

No. of Pages

68

Table of Contents

Table of contents.

Abstract.

Abstract in Arabic.

Chapter One : Introduction.

Chapter Two : Background and literature review.

Chapter Three : Methodology and the proposed work.

Chapter Four : Implementation and results.

Chapter Five : Conclusion and future work.

References.

American Psychological Association (APA)

al-Shami, Fida Musa Ahmad. (2019). Tuning approach to improve multilayer perceptron for breast cancer prediction. Middle East University, Jordan
https://search.emarefa.net/detail/BIM-899293

Modern Language Association (MLA)

al-Shami, Fida Musa Ahmad. Tuning approach to improve multilayer perceptron for breast cancer prediction. Middle East University. (2019).
https://search.emarefa.net/detail/BIM-899293

American Medical Association (AMA)

al-Shami, Fida Musa Ahmad. (2019). Tuning approach to improve multilayer perceptron for breast cancer prediction. Middle East University, Jordan
https://search.emarefa.net/detail/BIM-899293

Language

English

Data Type

Arab Theses

Record ID

BIM-899293