Noor Fitria Azzahra
Unknown Affiliation

Published : 2 Documents
Articles

Found 2 Documents
Search

PROMOTER ACCOUNT DETECTION IN TWITTER Syidada, Shofiya; Azzahra, Noor Fitria; Puspaningrum, Eva Yulia
JUTI: Jurnal Ilmiah Teknologi Informasi Vol 12, No 1, Januari 2014
Publisher : Teknik Informatika, ITS

Show Abstract | Original Source | Check in Google Scholar | Full PDF (396.427 KB)

Abstract

Twitter is an online social network and micro-blog that becomes an alternative media for sharing and getting information. In the political area, Twitter provides various features as a media to promote campaign and get a good imaging for political party or contestant. In order to get a good opinion from other users, the contestant can manipulate their success with a massive promotion. This promotion activity could lead to public opinion that is not consistent with the facts. So that, we need to determine whether this is promoter account or not. In this paper, we propose a new framework for promoter account detection. This framework based on twitter content to detect promoter account according to their existence in topic of promotion. This framework employs k-means approach in order to cluster topic of promotion based on twitter’s content. From each cluster, we evaluate the existence of promoter account. With very simple approach, the results obtained on experiment show that this framework is effective for promoter account detection.
Praproses Data Alir ADS-B dari Multi-Receiver dengan Pengelompokan Agglomerasi Berbasis Konsistensi Jarak Azzahra, Noor Fitria; Ginardi, Hari; Saikhu, Ahmad
Jurnal Nasional Teknik Elektro dan Teknologi Informasi (JNTETI) Vol 4, No 1 (2015)
Publisher : Jurusan Teknik Elektro dan Teknologi Informasi, Fakultas Teknik, Universitas Gadjah Mada

Show Abstract | Original Source | Check in Google Scholar | Full PDF (563.793 KB)

Abstract

Abstract— ADS-B is a surveillance technology fortransportation. For an aircraft, ADS-B broadcasts itsinformation simultaneously such as identity, flight number,position, altitude, velocity, etc. Due to the limited range ofreceiving the data, ADS-B needs multi-receiver to increase thecapability of receiving data. But, the usage of multi-receiverraises new problems in the ADS-B data stream, such asredundant and outliers. These problems can reduce the quality ofdata received because it does not represent its actual flightconditions, in other words the nature of time-series data areblurred. This paper proposed a new method for preprocessingthe data stream of the ADS-B multi-receiver to get good qualityof data. The good quality of data means all unique datasuccessfully restored and redundant data is removed, so its timeseriescharacteristic is regained. This method used coordinateinformation (latitude and longitude) in ADS-B data as areference for preprocessing. Applying agglomeration clusteringtechniques and the rule of distance consistency as mergingstrategy of the cluster, this method is able to generate the dataADS-B that represents the status of the real aircraft, which istime-series data. This simple method can generate good qualityof data from the data ADS-B multi-receiver.Intisari— ADS-B merupakan teknologi pengawasan pesawat.Secara simultan, ADS-B menyebarkan informasi pesawat (ID,nomor penerbangan, posisi, ketinggian, kecepatan, dan lain-lain)melalui gelombang elektromagnetik. Karena terbatasnyawilayah jangkauan receiver dalam menerima data ADS-B, makadiperlukan multi-receiver untuk meningkatkan jangkauanpenangkapan sinyal. Penggunaan multi-receiver inimemunculkan masalah baru dalam data alir ADS-B, antara laindata redundan dan data pencilan sehingga menyebabkan datayang diterima memiliki kualitas yang rendah karena tidakmerepresentasikan kondisi sebuah penerbangan yangsebenarnya, dengan kata lain sifat timeseries pada data yangditerima menjadi kabur. Dalam makalah ini, metode barudiajukan dengan tujuan untuk praproses data alir ADS-B darimulti-receiver sehingga dihasilkan data dengan kualitas yangbaik, di mana semua data unik berhasil dikembalikan sifattimeseries-nya dan data redundan berhasil dihilangkan. Metodeini memanfaatkan informasi posisi (lintang dan bujur) pesawatpada data ADS-B sebagai acuan untuk praprosesnya. Denganteknik pengelompokan aglomerasi dan dengan aturankonsistensi jarak antar data sebagai strategi penggabungankelompok, metode ini mampu menghasilkan data ADS-B yangmerepresentasikan keadaan pesawat sebenarnya, yaitu datayang bersifat timeseries. Dengan metode yang sederhana inidapat dihasilkan data ADS-B dari multi-receiver dengan kualitasyang baik.