Mostafa Abdulghafoor Mohammed
University Polytechnic of Bucharest

Published : 2 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 2 Documents
Search

A new model for large dataset dimensionality reduction based on teaching learning-based optimization and logistic regression Hind Raad Ibraheem; Zahraa Faiz Hussain; Sura Mazin Ali; Mohammad Aljanabi; Mostafa Abdulghafoor Mohammed; Tole Sutikno
TELKOMNIKA (Telecommunication Computing Electronics and Control) Vol 18, No 3: June 2020
Publisher : Universitas Ahmad Dahlan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.12928/telkomnika.v18i3.13764

Abstract

One of the human diseases with a high rate of mortality each year is breast cancer (BC). Among all the forms of cancer, BC is the commonest cause of death among women globally. Some of the effective ways of data classification are data mining and classification methods. These methods are particularly efficient in the medical field due to the presence of irrelevant and redundant attributes in medical datasets. Such redundant attributes are not needed to obtain an accurate estimation of disease diagnosis. Teaching learning-based optimization (TLBO) is a new metaheuristic that has been successfully applied to several intractable optimization problems in recent years. This paper presents the use of a multi-objective TLBO algorithm for the selection of feature subsets in automatic BC diagnosis. For the classification task in this work, the logistic regression (LR) method was deployed. From the results, the projected method produced better BC dataset classification accuracy (classified into malignant and benign). This result showed that the projected TLBO is an efficient features optimization technique for sustaining data-based decision-making systems.
A real-time big data sentiment analysis for iraqi tweets using spark streaming Nashwan Dheyaa Zaki; Nada Yousif Hashim; Yasmin Makki Mohialden; Mostafa Abdulghafoor Mohammed; Tole Sutikno; Ahmed Hussein Ali
Bulletin of Electrical Engineering and Informatics Vol 9, No 4: August 2020
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (692.543 KB) | DOI: 10.11591/eei.v9i4.1897

Abstract

The scale of data streaming in social networks, such as Twitter, is increasing exponentially. Twitter is one of the most important and suitable big data sources for machine learning research in terms of analysis, prediction, extract knowledge, and opinions. People use Twitter platform daily to express their opinion which is a fundamental fact that influence their behaviors. In recent years, the flow of Iraqi dialect has been increased, especially on the Twitter platform. Sentiment analysis for different dialects and opinion mining has become a hot topic in data science researches. In this paper, we will attempt to develop a real-time analytic model for sentiment analysis and opinion mining to Iraqi tweets using spark streaming, also create a dataset for researcher in this field. The Twitter handle Bassam AlRawi is the case study here. The new method is more suitable in the current day machine learning applications and fast online prediction.