KLASIFIKASI AUTHOR MATCHING PADA DATA BIBLIOGRAFI MENGGUNAKAN METODE COST-SENSITIVE DEEP NEURAL NETWORK (CSDNN)

LESTARI, SUCI DWI and Firdaus, Firdaus (2021) KLASIFIKASI AUTHOR MATCHING PADA DATA BIBLIOGRAFI MENGGUNAKAN METODE COST-SENSITIVE DEEP NEURAL NETWORK (CSDNN). Undergraduate thesis, Sriwijaya University.

	Text RAMA_56201_09011181722021.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (2MB) | Request a copy
	Text RAMA_56201_09011181722021_TURNITIN.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (6MB) | Request a copy
Preview	Text RAMA_56201_09011181722021_ 0221017801_01_front_ref.pdf - Accepted Version Available under License Creative Commons Public Domain Dedication. Download (1MB) | Preview
	Text RAMA_56201_09011181722021_ 0221017801_02.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (431kB) | Request a copy
	Text RAMA_56201_09011181722021_ 0221017801_03.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (487kB) | Request a copy
	Text RAMA_56201_09011181722021_ 0221017801_04.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (437kB) | Request a copy
	Text RAMA_56201_09011181722021_ 0221017801_05.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (63kB) | Request a copy
	Text RAMA_56201_09011181722021_ 0221017801_06_ref.pdf - Bibliography Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (206kB) | Request a copy
	Text RAMA_56201_09011181722021_ 0221017801_07_lamp.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (790kB) | Request a copy

Abstract

Author Name Ambiguity is an issue that occurs when publication records contain ambiguous or ambiguous author names, i.e. the same author may appear under different names, or different authors may have similar names. The method proposed in this research is Cost-Sensitive Deep Neural Network (CSDNN). The bibliographic dataset used is the DBLP Dataset by Jinseok Kim, et al. This research focuses on the use of classification methods, namely CSDNN and DNN. The main parameters of the research carried out are accuracy, precision, specificity, recall, and error rate, which are important parameters to determine the success rate of the method used in overcoming problems AND in particular finding the similarities of the authors. The CSDNN classification resulted achieves accuracy, precision, specificity, recall, and error rate which is 99.94%, 96.60%, 99.97%, 96.90%, and 0.000515. DNN classification resulted achieves accuracy, precision, specificity, recall, and error rate which is 99.94%, 99.97%, 96.90%, 96.78%, and 0.000501.

Item Type:	Thesis (Undergraduate)
Uncontrolled Keywords:	Author Matching, Digital Library, Bibliographic Data, Author Name Disambiguation, Cost-Sensitive Deep Neural Network, Deep Neural Network.
Subjects:	Q Science > Q Science (General) > Q334-342 Computer science. Artificial intelligence. Algorithms. Robotics. Automation.
Divisions:	09-Faculty of Computer Science > 56201-Computer Systems (S1)
Depositing User:	Suci Dwi Lestari
Date Deposited:	09 Jul 2021 04:40
Last Modified:	09 Jul 2021 04:40
URI:	http://repository.unsri.ac.id/id/eprint/49524

Actions (login required)

View Item