College of Computer Science and Mathematics

Discussion of the master’s thesis in the College of Computer Science and Mathematics -Department of Statistics and Informatics Department entitled:

” Improving Support vector machine for Imbalance big data classification ”

In continuation of the scientific research movement and with the follow-up and presence of the Dean of the College of Computer Science and Mathematics

Respected Professor Dr. Duha Bashir Abdullah

Master’s thesis by  Alaa Abdulazeez Qanbar

supervised by  Prof.  Dr.  Zakariya Yahya Algamal

This thesis includes Using the Monte-Carlo simulation method to generate data that follows a classification model and contains stray values. The simulation results, based on classification accuracy criteria and diagnostic accuracy criteria, have shown the superiority of the proposed method compared to other methods. In addition, the proposed method was applied to real global data in the field of genetics. The results showed that the proposed method is superior to other traditional methods as it gives it high classification accuracy.

The study addressed Diagnosing stray observations and deleting them using machine learning methods, including the vector machine method, which supports the analysis of huge, unbalanced data, thus obtaining high classification accuracy compared to other methods. By relying on the classification accuracy criteria CA and G-mean and relying on the criteria for diagnosing the efficiency of the methods in diagnosing stray observations, CIP and ICIP, which gave the highest value for the CIP criterion and the lowest value for the ICIP criterion.

The study aims to Improving classification of unbalanced huge data using the support vector machine to analyze big data. To achieve the goal, one of the nature-inspired algorithms, namely the pigeon algorithm, was employed to identify outlier values ​​and delete them, thus obtaining the highest classification accuracy using the support vector machine.

The discussion committee consists of

1. M.D. Osama Bashir Shukr (Chairman)
2. M.D. Naam Abdel Moneim Abdel Majeed (member)
3. M. Beida Suleiman Behnam (Member)
4. D. Zakaria Yahya Nouri (member and supervisor)