Main Page
Deanship
The Dean
Dean's Word
Curriculum Vitae
Contact the Dean
Vision and Mission
Organizational Structure
Vice- Deanship
Vice- Dean
KAU Graduate Studies
Research Services & Courses
Research Services Unit
Important Research for Society
Deanship's Services
FAQs
Research
Staff Directory
Files
Favorite Websites
Deanship Access Map
Graduate Studies Awards
Deanship's Staff
Staff Directory
Files
Researches
Contact us
عربي
English
About
Admission
Academic
Research and Innovations
University Life
E-Services
Search
Deanship of Graduate Studies
Document Details
Document Type
:
Thesis
Document Title
:
Multilabel Classification Model for Streaming Data Adaptive Model Rule for Multilabel Streaming Data (AMLSD(
نموذج التصنيف متعدد التسميه للبيانات المتدفقة
Subject
:
Faculty of Computing and Information Technology
Document Language
:
Arabic
Abstract
:
challenge with processing multilabel streaming data (MLSD) is implementing a stable and adaptive model; a model could deal with all the challenges, issues and unique features such model may have. An adaptive model rule was implemented in this study to process the multilabel streaming data (MLSD), the model integrated of multi-phases work together to process the MLSD with stability and adaptive manner. Adaptive Model Rule model is implemented in this study to process the MLSD. The main component of AMLSD is the aggregator. The aggregator would hold the main functionalities of the AMLSD model such as the testing and learning processes. AMRule is one of used functions which aim to minimize the training time by collected the predicted rules over the training instances in the rule set (RS). Another important part is the page-Hinkely (PH) test which work after the AMRule to detect the outliers of statistics and heuristically values of the current sketch of instances, a decision of expanding the RS or not would be execute according to the PH test. The AMLSD performance behaviour is evaluate and test over various setting and parameters in term of comparative statements with other scenarios. These comparative statements are illustrated though a multi-comparative statement using different performance metrics to determine the benefits of using the AMLSD with the multilabel streaming data (MLSD).
Supervisor
:
Prof. Wadee Alhlabi
Thesis Type
:
Master Thesis
Publishing Year
:
1441 AH
2020 AD
Added Date
:
Tuesday, June 2, 2020
Researchers
Researcher Name (Arabic)
Researcher Name (English)
Researcher Type
Dr Grade
Email
أماني العطاس
alattas, Amani
Researcher
Master
Files
File Name
Type
Description
46263.pdf
pdf
Back To Researches Page