Claim Missing Document
Check
Articles

Found 21 Documents
Search

Algoritma LSTM-CNN untuk Binary Klasifikasi dengan Word2vec pada Media Online Dedi Tri Hermanto; Arief Setyanto; Emha Taufiq Luthfi
Creative Information Technology Journal Vol 8, No 1 (2021): Januari - Juni
Publisher : UNIVERSITAS AMIKOM YOGYAKARTA

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24076/citec.2021v8i1.264

Abstract

Media online banyak menghasilkan berbagai macam berita, baik ekonomi, politik, kesehatan, olahraga atau ilmu pengetahuan. Di antara itu semua, ekonomi adalah salah satu topik menarik untuk dibahas. Ekonomi memiliki dampak langsung kepada warga negara, perusahaan, bahkan pasar tradisional tergantung pada kondisi ekonomi di suatu negara. Sentimen yang terkandung dalam berita dapat mempengaruhi pandangan masyarakat terhadap suatu hal atau kebijakan pemerintah. Topik ekonomi adalah bahasan yang menarik untuk dilakukan penelitian karena memiliki dampak langsung kepada masyarakat Indonesia. Namun, masih sedikit penelitian yang menerapkan metode deep learning yaitu Long Short-Term Memory dan CNN untuk analisis sentimen pada artikel finance di Indonesia. Penelitian ini bertujuan untuk melakukan pengklasifikasian judul berita berbahasa Indonesia berdasarkan sentimen positif, negatif dengan menggunakan metode LSTM, LSTM-CNN, CNN-LSTM. Dataset yang digunakan adalah data judul artikel berbahasa Indonesia yang diambil dari situs Detik Finance. Berdasarkan hasil pengujian memperlihatkan bahwa metode LSTM, LSTM-CNN, CNN-LSTM memiliki hasil akurasi sebesar, 62%, 65% dan 74%.Kata Kunci — LSTM, sentiment analysis, CNNOnline media produce a lot of various kinds of news, be it economics, politics, health, sports or science. Among them, economics is one interesting topic to discuss. The economy has a direct impact on citizens, companies, and even traditional markets depending on the economic conditions in a country. The sentiment contained in the news can influence people's views on a matter or government policy. The topic of economics is an interesting topic for research because it has a direct impact on Indonesian society. However, there are still few studies that apply deep learning methods, namely Long Short-Term Memory and CNN for sentiment analysis on finance articles in Indonesia. This study aims to classify Indonesian news headlines based on positive and negative sentiments using the LSTM, LSTM-CNN, CNN-LSTM methods. The dataset used is data on Indonesian language article titles taken from the Detik Finance website. Based on the test results, it shows that the LSTM, LSTM-CNN, CNN-LSTM methods have an accuracy of, 62%, 65% and 74%.Keywords — LSTM, sentiment analysis, CNN
Analisis Aplikasi Marbel Huruf Versi Mobile Terhadap Pembelajaran Membaca di Desa Semanding Ponorogo Jamilah Karaman; Arief Setyanto; Amir Fatah Sofyan
INTENSIF: Jurnal Ilmiah Penelitian dan Penerapan Teknologi Sistem Informasi Vol 2 No 2 (2018): Vol. 2 No. 2 Agustus 2018
Publisher : Universitas Nusantara PGRI Kediri

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (176.797 KB) | DOI: 10.29407/intensif.v2i2.11878

Abstract

The development of technology, especially information and communication technology offers many ease-ease in learning, which allows the shift of learning orientation from the process of presenting various knowledge into the process of guidance in individual exploration of science. Interactive learning media for children who rampant today is a game-based learning pedia is "MARBEL". Marbel is an abbreviation of "Let's Learn", marbel application is an educational application (mobile learning) for children aged 2 to 8 years so that made mobile-based applications aims to facilitate children in the learning process.
Analisis Permodelan Periodic VRP with Driver-Consistency dan Consistency-VRP with Time-Windows Muhammad Reza Riansyah; Arief Setyanto; Eko Pramono
Progresif: Jurnal Ilmiah Komputer Vol 18, No 1: Februari 2022
Publisher : STMIK Banjarbaru

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (387.398 KB) | DOI: 10.35889/progresif.v18i1.768

Abstract

Abstrak. Sistem distribusi merupakan bagian penting dalam aktivitas pemasaran untuk mempermudah penyampaian barang dan jasa kepada konsumen. Dalam sistem distribusi terdapat komponen-komponen berupa Pelanggan, Kendaraan, Pengemudi, Rute dan Depot yang menjadi tujuan pendistribusian. Dalam menentukan rute terdapat berbagai masalah yang dapat ditemukan yaitu dengan Vehicle Routing Problem (VRP). VRP digunakan untuk menentukan beberapa rute dimana dalam setiap rute dilalui oleh suatu kendaraan yang memulai perjalanan dari depot awal sampai depot akhir dengan permintaan pasti maupun tidak pasti. Penelitian ini di buat untuk membanding model Periodic VRP with Driver-Consistency (PVRP-DC) dan Consistency-VRP with Time-Windows (ConVRP-TW). Hasil penelitian ini menemukan perbedaan yang dihasilkan pada kedua model tersebut yaitu PVRP-DC dan ConVRP-TW dan VRP lainnya memiliki persamaan untuk mencari solusi rute yang optimal dengan batasan-batasan tertentu. Dengan permodelan PVRP-DC dapat menghemat jarak sebesar 25% dan ConVRP-TW dapat menghemat jarak 26%.Kata kunci: Permodelan; Sistem distribusi; Periodic VRP with Driver-Consistency; Consistency-VRP with Time-Windows Abstract. The distribution system is an important part of marketing activities to facilitate the delivery of goods and services to consumers. In the distribution system there are components in the form of Customers, Vehicles, Drivers, Routes and Depots which are the purpose of distribution. In determining the route, there are various problems that can be found, namely the Vehicle Routing Problem (VRP). VRP is used to determine several routes in which each route is traversed by a vehicle starting from the initial depot to the final depot with definite or uncertain requests. This study was made to compare the Periodic VRP with Driver-Consistency (PVRP-DC) and Consistency-VRP with Time-Windows (ConVRP-TW) models. The results of this study found the differences between the two models, namely PVRP-DC and ConVRP-TW and other VRPs have similarities to find the optimal route solution with certain limitations. By modeling PVRP-DC can save distance by 25% and ConVRP-TW can save distance by 26%.Keywords: Modeling; Distribution system; Periodic VRP with Driver-Consistency; Consistency-VRP with Time-Windows
Audit Tata Kelola Teknologi Informasi Menggunakan Cobit 4.1 Domain Monitoring Evaluasi Pada Perguruan Tinggi Swasta Khairan Marzuki; Arief Setyanto; Asro Nasiri
Proceeding Seminar Nasional Sistem Informasi dan Teknologi Informasi 2018: Proceeding Seminar Nasional Sistem Informasi dan Teknologi Informasi (SENSITEK)
Publisher : STMIK Pontianak

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30700/pss.v1i1.360

Abstract

Proritas utama Teknologi Informasi diberikan kepada pengendalian interen. Ini dilakukan untuk menjamin pengambilan keputusan yang baik berdasarkan hasil audit terhadap sistem organisasi. Objek penelitian adalah  system informasi Akademik kampus STMIK Bumigora Mataram, Menggunakan Frameworke COBIT 4.1 Domain monitor and evaluate,metode pengumpulan data pada peneilitian ini observasi,wawancara dan kuisioner kepada pihak yang terkait.Hasil dari penelitian ini berupa tingkat kematangan Sistem Informasi Akademik yang mencerminkan kondisi tata kelola saat ini dan tingkat kematangan yang diharapkan di kampus STMIK Bumigora Mataram dengan mengacu pada maturity level yang disediakan kerangka kerja Cobit 4.1.Berdasarkan audit monitoring dan evaluasi yang dilakukan, secara garis besar kondisi kematangan tata kelola TI kampus STMIK Bumigora Mataram berada pada level 2 yakni repeatable but intuitive. Kondisi ini mengacu pada beberapa kelemahan dalam proses-proses TI yang berjalan, di antaranya  penetapan dan dokumentasi tindakan, kebijakan dan prosedur yang minim, serta tidak tersedianya service level yang disetujui bersama.Kata kunci: Audit, system informasi akademiki, tatakelola teknologi informasi, COBIT, Monitoring evaluation
Evaluasi Sistem Informasi Menggunakan Technology Acceptance Model dengan Penambahan Variabel Eksternal Ria Andriani; Arief Setyanto; Asro Nasiri
Jurnal Teknologi Informasi dan Ilmu Komputer Vol 7 No 3: Juni 2020
Publisher : Fakultas Ilmu Komputer, Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25126/jtiik.202073850

Abstract

Dalam rangka pengelolaan akademik, sebelum mengikuti perkuliahan mahasiswa wajib untuk mengisi KRS. KRS (Kartu Rencana Studi) berfungsi untuk mengelola mata kuliah yang akan diambil pada Semester yang bersangkutan oleh mahasiswa, pengisian KRS dilakukan menggunakan akun yang telah diberikan oleh pihak kampus dengan cara masuk menggunakan identitas berupa Nomor Induk Mahasiswa dan kata sandi, mahasiswa dapat melakukan pengisian Kartu Rencana Studi dari manapun dengan informasi yang telah disediakan pada website, sehingga dapat dikatakan bahwa Sistem KRS merupakan penjembatan antara mahasiswa dengan pengelola dalam hal ini bagian akademik di Universitas Amikom. Pada penelitian ini penulis melakukan evaluasi tingkat penerimaan mahasiswa terhadap sistem KRS online yang telah diimplementasikan dengan jumlah responden yang digunakan sebanyak 200 mahasiswa, adapun model yang digunakan adalah Technology Acceptance Model (TAM) yang dimodifikasi dengan menambahkan Eksternal variabel berupa kemudahan akses dan kenyamanan tempat. Penelitian ini melakukan pengkajian terhadap penerimaan pengguna berdasarkan variabel yang terdapat pada Technology Acceptance Model diantaranya adalah  Kemudahan Penggunaan/ Perceived Ease Of Use (PEOU), Manfaat yang dirasakan / Perceived Usefulness (PU), Sikap Terhadap Penggunaan Attitude Toward Using (ATT) dan Penerimaan Teknologi/ Acceptance Of Technology (AOT).Hasil dari penelitian ini didapatkan pengaruh yang signifikan antara variabel PEOU terhadap PU dengan nilai 0,356, PEOU terhadap ATT dengan nilai 0,251, PU terhadap ATT dengan nilai 0,578, ATT terhadap AOT dengan nilai 0,337, Ext terhadap PEOU dengan nilai 0,263, Ext terhadap PU dengan nilai 0,233 sedangkan PU terhadap AOT tidak terdapat pengaruh yang siginifikan dengan nilai sebesar 0,169. Hasil dari analisis data yang didapatkan bahwa penerimaan sistem KRS online dipengaruhi oleh faktor kemudahan penggunaan sistem, kemudahan akses, kenyamanan tempat serta sikap perilaku mahasiswa dalam menggunakannya.  AbstractIn the context of academic management, before attending lectures students are required to fill KRS. KRS (Study Plan Card) functions to manage courses that will be taken in the relevant semester by students, filling in KRS using the account given by the campus by entering using an identity in the form of a Student Identification Number and password, students can fill in the Card Study Plan from anywhere with information that has been provided on the website, so that it can be said that the Card Study Plan System is a bridge between students and managers in this case the academic section at the University of Amikom.In this study the authors evaluated the level of student acceptance of the Card Study Plan online system that has been implemented with the number of respondents used by 200 students, while the model used is the Technology Acceptance Model (TAM) which was modified by adding External variables in the form of ease of access and comfort of the place. This study examines user acceptance based on variables contained in the Technology Acceptance Model including Ease of Use / Perceived Ease of Use (PEOU), Perceived Usefulness (PU), Attitudes Towards Attitude Toward Using (ATT) and Technology Acceptance / Acceptance Of Technology (AOT).The results of this study found a significant influence between PEOU variables on PU with a value of 0.356, PEOU on ATT with a value of 0.251, PU on ATT with a value of 0.578, ATT on AOT with a value of 0.337, Ext on a PEOU with a value of 0.263, Ext on PU with a value 0.233 while PU on AOT did not have a significant effect with a value of 0.169. The results of data analysis found that the acceptance of the online KRS system is influenced by the ease of use of the system, ease of access, comfort of the place and the attitude of students' behavior in using it. 
Studi Komparatif Dua Model Skema Sistem Smart Charging Eksternal untuk Laptop Ahmad Afief Amrullah; Arief Setyanto; Sudarmawan Sudarmawan
Jurnal Dinamika Informatika Vol 9 No 1 (2020): Jurnal Dinamika Informatika
Publisher : Universitas PGRI Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (1368.228 KB)

Abstract

In recent years, external smart charging, especially on laptop devices, has become quite an interesting topic due to the need for a response to a decrease in battery capacity and damage. As the development of embedded systems such as Arduino which is commonly used, this system offers more flexible data communication, which initially used cables to be wireless, ranging from Bluetooth to WiFi. As for this topic, there are controls based on the user's electricity needs and the condition of the electrical system, which is called dynamic demand control. The key to this method is the frequency of the electricity network and the battery. This method can provide extensions to smart charging to only charge when needed. The positive impact of using this method in addition to preventing the battery from being damaged is electricity savings. In this study the authors tried to study two models of the smart charging system schemes that have never been compared, namely the standalone and centralized models. The results of this study indicate that although the centralized model is more efficient in terms of reading the frequency value of the electricity network, in terms of performance the standalone model is more stable and reliable.
Pengukuran Kualitas Informasi dengan Menerapkan Augmented Reality pada Media Promosi (Brosur) Berbasis Android Miftahul Madani; Arief Setyanto; Amir Fatah Sofyan; Danang Tejo Kumoro
JTIM : Jurnal Teknologi Informasi dan Multimedia Vol 1 No 4 (2020): February
Publisher : Puslitbang Sekawan Institute Nusa Tenggara

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35746/jtim.v1i4.67

Abstract

Augmented reality is a technology that is part of the development of the multimedia world that brings many ideas in various fields of promotion is no exception. The idea of using augmented reality in promotional media (brochures) that aims to improve the quality of information that is applied to the android platform one of them. The analytical method used in this study on validation testing is the product moment correlation technique, then the interval will be made as a measuring tool to determine the variable value of effectiveness, efficiency and satisfaction. The results concluded that the effectiveness variable showed at the number 59.817 on a scale > 52.85 - 61.442 which is very close to effective, the efficiency variable showed at the number 23.833 on a scale > 21.145 - 24.574 which is very close to efficient, and the satisfaction variable showed 47.417 at a scale > 42.285 - 49,142 which is very close to satisfying. Based on this, the use of augmented reality technology applied to promotional media can affect the level of quality of information and can display video and audio information on promotional media (brochures) STMIK Bumigora Mataram based on Android.
Pengaruh Normalisasi Teks Dengan Text Expansion Dalam Deteksi Komentar Spam Pada Youtube Imam Thoib; Arief Setyanto; Suwanto Raharjo
Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) Vol 2 No 3 (2018): Desember 2018
Publisher : Ikatan Ahli Informatika Indonesia (IAII)

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (886.168 KB) | DOI: 10.29207/resti.v2i3.602

Abstract

The popularity of Youtube as the largest video sharing website in the wolrd give spammers opportunities to get benefit from Youtube in illegal ways by putting spam comments on Youtube's videos. Spam comments are very troubling to channel owners. The variants of spam comments are becoming more difficult to detect. One of them is spam comments using abbreviations, symbols, terms or misspelled word to make detection difficult. This research evaluate some classification techniques and employ text normalization method called TextExpansion to deal with this problem. This research uses Youtube Spam Collections dataset from UCI Machine Learning Library composed by five different datasets, which each one contains text comments extracted from YouTube videos (Psy, Katty Perry, LMFAO, Eminem and Shakira). The evaluation results shows TextExpansion is able to produce the highest accuracy value of 90.23%. To determine the impact of applying the TextExpansion method, this research conducted t-test for each dataset. The results of t-test for each dataset shows P(T<=t) two-tail < 0.05 which indicates a significant impact after applying text normalization using TextExpansion.
Implementasi Algoritma Firefly pada Kasus N-Queens Problem Dedy Abdianto Nggego; Arief Setyanto; Sukoco
Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) Vol 4 No 2 (2020): April 2020
Publisher : Ikatan Ahli Informatika Indonesia (IAII)

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (750.643 KB) | DOI: 10.29207/resti.v4i2.1506

Abstract

N-Queen problem is a form of puzzle game that uses chess rules for the queen on the standard chessboard with modified size. The challenge of the n-queen problem is finding the N ( N is positive integer) queens position on the chessboard, so that no queen can attack another queen on the board in a single move. Implementation of firefly algorithm in n-queens problem in this study aims to find n-queen problem solutions and count the number of iterations to achieve the optimal solution of each queen which will then be compared with the results of Sarkar and Nag's research (2017). This study uses an experimental method with a number of N between 10 to 20 and uses a population of 15 and 1000 firefly. The results showed that the firefly algorithm is able to find all the optimal solutions for the queen's position on a chessboard with dimensions 10 to 20 in a population of 1000 firefly. The firefly algorithm can find the optimal solution fewer iterations compared to the genetic algorithm. According to the experiment, firefly algorithm shows better performance in finding the optimal solution compared to genetic algorithm.
Analisis Prediksi Curah Hujan Bulanan Wilayah Kota Sorong Menggunakan Metode Multiple Regression Muhammad Yusuf; Arief Setyanto; Komang Aryasa
J-SAKTI (Jurnal Sains Komputer dan Informatika) Vol 6, No 1 (2022): EDISI MARET
Publisher : STIKOM Tunas Bangsa Pematangsiantar

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30645/j-sakti.v6i1.455

Abstract

Currently, climate change in Indonesia, which is a tropical region, is always uncertain and makes it difficult to predict weather conditions. Weather conditions can be influenced by temperature, air pressure, wind speed, humidity and rainfall. Rainfall is a climate parameter that has a high level of diversity due to climate anomalies. There are several factors that influence the characteristics of the diversity of rainfall, namely geographical, orographic, topographical, orientation and structure of the islands. These factors cause the distribution pattern of rainfall to be uneven between one area and another. For that we need a method that can solve the problem of predicting rainfall both daily, monthly and yearly. Prediction of rainfall with a statistical approach can be done through the Multiple Linear Regression method. Where in this study, rainfall is the dependent variable, while temperature and humidity are independent variables. The results obtained from the WEKA Application with a total of 60 data from 2017 to 2021, the correlation coefficient value is 0.8175, and from the evaluation results using Linear Regression, the MAE error rate is 78.8695 and the RMSE is 95.1982. It can be concluded that the effect of temperature and air on the occurrence of rainfall is 81.75%