Implementation Learning Vector Quantization (LVQ) Algorithm to Classify Book Categories Based on Book’s Description

Ismardiani, Amalia (2020) Implementation Learning Vector Quantization (LVQ) Algorithm to Classify Book Categories Based on Book’s Description. Other thesis, Universitas Katolik Soegijapranata Semarang.

[img] Text (Amalia Ismardiani- COVER)
14.K1.0081 - AMALIA ISMARDIANI - COVER.pdf
Download (1MB)
[img] Text (Amalia Ismardiani- BAB 1)
14.K1.0081 - AMALIA ISMARDIANI -BAB I.pdf
Download (89kB)
[img] Text (Amalia Ismardiani- BAB II)
14.K1.0081 - AMALIA ISMARDIANI - BAB II.pdf
Restricted to Registered users only
Download (115kB)
[img] Text (Amalia Ismardiani- BAB III)
14.K1.0081 - AMALIA ISMARDIANI - BAB III.pdf
Download (116kB)
[img] Text (Amalia Ismardiani- BAB IV)
14.K1.0081 - AMALIA ISMARDIANI - BAB IV.pdf
Download (429kB)
[img] Text (Amalia Ismardiani- BAB V)
14.K1.0081 - AMALIA ISMARDIANI - BAB V.pdf
Download (142kB)
[img] Text (Amalia Ismardiani- BAB VI)
14.K1.0081 - AMALIA ISMARDIANI - BAB VI.pdf
Download (87kB)
[img] Text (Amalia Ismardiani- DAFTAR PUSTAKA)
14.K1.0081 - AMALIA ISMARDIANI - DAFTAR PUSTAKA.pdf
Download (66kB)
[img] Text (Amalia Ismardiani- LAMPIRAN)
14.K1.0081 - AMALIA ISMARDIANI - LAMPIRAN.pdf
Download (520kB)

Abstract

In this era many bookstores use the internet to sell their books. But many bookstore websites show books that are not categorized hence the search is ineffective. To solve this problem by creating a program that can classify books based on book descriptions. Book categories can be determined based on book descriptions because books in a category can have the same description patterns In this final project used implementation Learning Vector Quantization (LVQ) algorithm to the classification of book categories. The first step is to collect training and testing data using Web Scraper Google Chrome Extension. And then do text preprocessing methods to process the data and TF-IDF methods to extract data features. The accuracy of the LVQ algorithm is obtained by testing the learning rate and maxEpoch. The testing shows that learning rate are important parameter to determine significant performance. The smaller the learning rate will resulting higher accuracy. The highest accuracy obtained at the end of the testing process ont the training data is 91.22%.

Item Type: Thesis (Other)
Subjects: 000 Computer Science, Information and General Works
Divisions: Faculty of Computer Science > Department of Informatics Engineering
Depositing User: ms F. Dewi Retnowati
Date Deposited: 28 May 2021 02:39
Last Modified: 28 May 2021 02:39
URI: http://repository.unika.ac.id/id/eprint/25274

Actions (login required)

View Item View Item
Unika Repository is powered by EPrints 3 which is developed by the School of Electronics and Computer Science at the University of Southampton. More information and software credits.