KLASIFIKASI MULTI LABEL PADA GENRE NOVEL BERDASARKAN COVER MENGGUNAKAN METODE CONVOLUTIONAL NEURAL NETWORK

LUBIS, YASMIN AZZAHRAH and Supardi, Julian (2022) KLASIFIKASI MULTI LABEL PADA GENRE NOVEL BERDASARKAN COVER MENGGUNAKAN METODE CONVOLUTIONAL NEURAL NETWORK. Undergraduate thesis, Sriwijaya University.

[thumbnail of RAMA_55201_09021181722017.pdf] Text
RAMA_55201_09021181722017.pdf - Accepted Version
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (4MB) | Request a copy
[thumbnail of RAMA_55201_09021181722017_TURNITIN.pdf] Text
RAMA_55201_09021181722017_TURNITIN.pdf - Accepted Version
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (9MB) | Request a copy
[thumbnail of RAMA_55201_09021181722017_0010077210_01_front_ref.pdf]
Preview
Text
RAMA_55201_09021181722017_0010077210_01_front_ref.pdf - Accepted Version
Available under License Creative Commons Public Domain Dedication.

Download (1MB) | Preview
[thumbnail of RAMA_55201_09021181722017_0010077210_02.pdf] Text
RAMA_55201_09021181722017_0010077210_02.pdf - Accepted Version
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (520kB) | Request a copy
[thumbnail of RAMA_55201_09021181722017_0010077210_03.pdf] Text
RAMA_55201_09021181722017_0010077210_03.pdf - Accepted Version
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (384kB) | Request a copy
[thumbnail of RAMA_55201_09021181722017_0010077210_04.pdf] Text
RAMA_55201_09021181722017_0010077210_04.pdf - Accepted Version
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (1MB) | Request a copy
[thumbnail of RAMA_55201_09021181722017_0010077210_05.pdf] Text
RAMA_55201_09021181722017_0010077210_05.pdf - Accepted Version
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (502kB) | Request a copy
[thumbnail of RAMA_55201_09021181722017_0010077210_06.pdf] Text
RAMA_55201_09021181722017_0010077210_06.pdf - Accepted Version
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (11kB) | Request a copy
[thumbnail of RAMA_55201_09021181722017_0010077210_06_ref.pdf] Text
RAMA_55201_09021181722017_0010077210_06_ref.pdf - Bibliography
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (277kB) | Request a copy
[thumbnail of RAMA_55201_09021181722017_0010077210_07_lamp.pdf] Text
RAMA_55201_09021181722017_0010077210_07_lamp.pdf - Accepted Version
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (126kB) | Request a copy

Abstract

Fiction book classification based on its cover become a particularly exciting research topic in recent years. There exists a wide variety of book genres, and the design on its cover as a graphic designs vary in many different ways such as colors, styles, textual information, even for books of the same genre, make it an challenging task to do fiction book genre classification based on its cover. In some related work before, classification system for define genre of fiction book practice still limited with traditional classification, where a fiction book will only be classified into one genre, whereas in real situations a novel can be classified into more than one genre. In addition, another problem lies in the data redundancy in several categories of the dataset. Therefore, in this study will try to solved the two problems, the first by applying multi-label classification practice with a Convolutional Neural Network model in order to classify the fiction book genre information based on the cover and provide the correct genre classification results, then the second we will collect fiction book’s cover image as new dataset using web scraping technique, so the data can be used for multi label classification purpose. The Convolutional Neural Network model used in this study is the VGG16 architecture. The results of experiments conducted in this study indicate that the VGG16 model that has been trained using the dataset that has been collected by the author can perform a multi label classification to determine the novel genre in the testing process properly and obtain a fairly good F1 Score.

Item Type: Thesis (Undergraduate)
Uncontrolled Keywords: Klasifikasi Multi Label, Convolutional Neural Network, VGG16, Genre Novel, Deep Learning
Subjects: Q Science > Q Science (General) > Q300-390 Cybernetics > Q325.5 Machine learning
Q Science > Q Science (General) > Q334-342 Computer science. Artificial intelligence. Algorithms. Robotics. Automation.
Divisions: 09-Faculty of Computer Science > 55201-Informatics (S1)
Depositing User: Ms. Yasmin Azzahrah Lubis
Date Deposited: 26 Jan 2022 01:59
Last Modified: 26 Jan 2022 01:59
URI: http://repository.unsri.ac.id/id/eprint/62726

Actions (login required)

View Item View Item