EMAIL: PASSWORD:
Front Office
UPT. PERPUSTAKAAN
Institut Teknologi Sepuluh Nopember Surabaya


Kampus ITS Sukolilo - Surabaya 60111

Phone : 031-5921733 , 5923623
Fax : 031-5937774
E-mail : libits@its.ac.id
Website : http://library.its.ac.id

Support (Customer Service) :
timit_perpus@its.ac.id




Welcome..guys!

Have a problem with your access?
Please, contact our technical support below:
LIVE SUPPORT


Moh. Fandika Aqsa


Davi Wahyuni


Tondo Indra Nyata


Anis Wulandari


Ansi Aflacha




ITS » Master Theses » 51200-Teknik Informatika S2
Posted by tondoindra@gmail.com at 09/06/2015 22:44:45  •  1538 Views


HIERARCHICAL MULTI-VIEWPOINT SELF ORGANIZING MAP PADA PENGELOMPOKAN PENGGUNA UNTUK MENGETAHUI PROFIL UNDUH DI LINGKUNGAN KAMPUS

HIERARCHICAL MULTI-VIEWPOINT SELF ORGANIZING MAP ON USER GROUPING TO DISCOVER DOWNLOAD PROFILE IN CAMPUS AREA

Author :
PUTRI, TESA ERANTI ( 5112201038 )




ABSTRAK

Fasilitas internet di kampus terkadang disalahgunakan untuk mengunduh berkas data berukuran besar yang tidak berhubungan dengan akademis. Penyalahgunaan itu berpotensi untuk mengganggu pengguna lain yang memerlukan fasilitas internet untuk kepentingan akademis. Oleh karena itu diperlukan informasi profil unduh pengguna di lingkungan kampus yang dapat dimanfaatkan untuk memonitor transaksi unduhan pengguna dan mengetahui pengguna yang memiliki kecenderungan penyalahgunaan fasilitas internet kampus. Fokus pada penelitian ini adalah mengetahui profil unduh pengguna. Profil unduh dibentuk dari pengelompokan pengguna berdasarkan preferensinya dalam mengunduh. Pengelompokan diaplikasikan dengan teknik web usage mining pada dokumen web access log menggunakan pemodelan Self Organizing Map SOM dengan konsep hierarchical multi-viewpoint. Pada pemodelan ini jumlah transaksi unduh pengguna akan dianalisis dari sudut pandang viewpoint tipe data yang diunduh lokasi pengunduhan dan domain email pengunduh. Setiap viewpoint dianalisis dalam peta SOM sendiri. Ketiga peta SOM viewpoint disusun secara hierarchical berjenjang kemudian dilatih dari lapisan terbawah ke atas menggunakan vektor fitur hasil penggabungan fitur pada viewpoint tersebut dengan viewpoint di bawahnya. Setiap kelompok hasil pemetaan mencerminkan profil unduh dari ketiga viewpoint. Indikator keberhasilan pengelompokan dilihat dari goodness measure yang mengukur homogenitas pengelompokan dan analisis manual hasil pengelompokan SOM. Dari pengujian diperoleh bahwa pelatihan SOM Hierarchical Multiviewpoint yang menghasilkan pengelompokan yang memiliki homogenitas tinggi dengan cost minimal dijalankan pada parameter 945 05 dan T 40 kali. Susunan viewpoint dari bawah ke atas yang menghasilkan pengelompokan dengan homogenitas tinggi adalah domain email-lokasi-tipe data. Sedangkan susunan viewpoint dari bawah ke atas yang memberikan gambaran profil unduh paling jelas dan lengkap adalah lokasi-domain email-tipe data.


ABSTRACT

Internet facility in the campus is sometimes misused to download large data files that are not related to academic. This misuse has the potential to interfere with other users who need the facility for academic interests. Therefore it is necessary to acquire information of users download profile in the campus area that can be used to monitor user download transactions and find out users who have tendency to abuse the campus internet facility. The focus of this research is to discover users download profile. This profile is formed through grouping of users by their download preferences. The grouping is applied with web usage mining techniques on web access log document using modelling of Self Organizing Map SOM with hierarchical multi-viewpoint concept. In this model the number of user download transactions will be analyzed from the viewpoints of the type of data downloaded download location and users email domain and every viewpoint has its own SOM map for analysis. All three viewpoint SOM maps are arranged hierarchically then each are trained starting from the bottom layer upwards using feature vectors produced from incorporation of the feature on current layer with the feature from the layer underneath. Each group mapping result reflects the users download profile from the three viewpoints. The indicator for the success of the grouping is seen from goodness measure that measures homogeneity of grouping and manual analysis of SOM grouping results. From the experiments it is concluded that Hierarchical Multiviewpoint SOM produced grouping result that has high homogeneity withminimum cost when trained on 94505 and T40. The arrangement of viewpoints from bottom to top that yields grouping with high homogeneity is email domainlocation- data type. Whereas the arrangement of viewpoints that gives a clear and complete picture of download profile from bottom to top is location-email domain-data type.



Keywordsprofil unduh, pengelompokan pengguna, web usage mining, Self Organizing Map Hierarchical Multi-viewpoint
 
Subject:  Web Server
Contributor
  1. Dr. Eng. Chastine Fatichah, S.Kom., M.Kom
  2. Diana Purwitasari, S.Kom., M.Sc.
Date Create: 18/07/2014
Type: Text
Format: PDF
Language: Indonesian
Identifier: ITS-Master-51103150001248
Collection ID: 51103150001248
Call Number: RTIf 006.33 Put h


Source
Master Theses of informatics Engineering RTIf 006.33 Put h, 2015

Coverage
ITS Community

Rights
Copyright @2015 by ITS Library. This publication is protected by copyright and per obtained from the ITS Library prior to any prohibited reproduction, storage in a re transmission in any form or by any means, electronic, mechanical, photocopying, reco For information regarding permission(s), write to ITS Library




[ Download - Open Access ]

  1.  ITS-Master-37829-5112201038-abstract_id.pdf - 215 KB
  2.  ITS-Master-37829-5112201038-abstract_en.pdf - 218 KB
  3.  ITS-Master-37829-5112201038-conclusion.pdf - 451 KB




 Similar Document...




! ATTENTION !

To facilitate the activation process, please fill out the member application form correctly and completely

Registration activation of our members will process up to max 24 hours (confirm by email). Please wait patiently

POLLING

Bagaimana pendapat Anda tentang layanan repository kami ?

Bagus Sekali
Baik
Biasa
Jelek
Mengecewakan





You are connected from 18.232.55.175
using CCBot/2.0 (https://commoncrawl.org/faq/)



Copyright © ITS Library 2006 - 2020 - All rights reserved.
Dublin Core Metadata Initiative and OpenArchives Compatible
Developed by Hassan