Claim Missing Document
Check
Articles

Found 32 Documents
Search

Klasifikasi Karya Ilmiah (Tugas Akhir) Mahasiswa Menggunakan Metode Naive Bayes Classifier (NBC) Nurdin Nurdin; M Suhendri; Yesy Afrilia; Rizal Rizal
Sistemasi: Jurnal Sistem Informasi Vol 10, No 2 (2021): Sistemasi: Jurnal Sistem Informasi
Publisher : Program Studi Sistem Informasi Fakultas Teknik dan Ilmu Komputer

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (344.544 KB) | DOI: 10.32520/stmsi.v10i2.1193

Abstract

ABSTRACTThe final project or thesis is the result of research that addresses a problem according to the student's field of science. By increasing the number of graduates, the number of final project documents produced will also be even greater. The large number of scientific papers or final project documents will be difficult to find according to the topic if they are not grouped. A large number of documents will not be effective if classification is done manually. This study makes a scientific paper classification application aimed at classifying the scientific work (final project) of students in the field of Informatics Engineering. This application was built by implementing the Naive Bayes Classifier algorithm based on background parameters and will be classified into 5 categories, namely image processing, data mining, decision making systems, geographic information systems and expert systems. With the research stages, namely data collection, preprocessing, calculation of the Naive Bayes Classifier method, implementation and system testing. This study uses 170 scientific papers, which are divided into 150 data for training and 20 data for testing. The results of this study illustrate that the Naive Bayes Classifier algorithm is a simple algorithm that can be used to classify scientific papers with an average accuracy of 86.68% and the average processing time required in each test is 5.7406 seconds / test.Keywords:scientific work, naive bayes classifier, classification,training, testing ABSTRAKTugas akhir atau skripsi merupakan hasil penelitian yang membahas suatu masalah sesuai bidang ilmu dari mahasiswa. Dengan bertambah jumlah lulusan, maka jumlah dokumen tugas akhir yang dihasilkan juga akan semakin besar. Jumlah dokumen karya ilmiah atau tugas akhir yang besar akan sulit dicari sesuai dengan topik jika tidak dikelompokkan. Jumlah dokumen yang besar akan tidak efektif jika dilakukan klasifikasi secara manual. Penelitian ini membuat aplikasi klasifikasi karya ilmiah bertujuan untuk mengklasifikasikan karya ilmiah (tugas akhir) mahasiswa dalam bidang ilmu Teknik Informatika. Aplikasi ini dibangun dengan mengimplementasikan algoritma Naive Bayes Classifier berdasarkan parameter latar belakang dan akan diklasifikasikan menjadi 5 kategori yaitu pengolahan citra, data mining, sistem pengambilan keputusan, sistem informasi geografis dan sistem pakar. Dengan tahapan penelitian yaitu pengumpulan data, preprocessing, perhitungan metode Naive Bayes Classifier,implementasi dan pengujian sistem.Penelitian ini menggunakan data sebanyak 170 data karya ilmiah, yang dibagi menjadi 150 data untuk pelatihan dan 20 data untuk pengujian. Hasil penelitian ini menggambarkan bahwa algoritma Naive Bayes Classifier merupakan algoritma sederhana yang mampu digunakan untuk melakukan klasifikasi karya ilmiah dengan rata-rata akurasi 86,68% serta rata-rata waktu proses yang dibutuhkan dalam setiap pengujian yaitu 5,7406 detik/pengujian.Kata Kunci:Karya ilmiah, Naive bayes classifier, Klasifikasi, Pelatihan, Pengujian.
Automatic Control System Using Arduino UNO and Web-Based Monitoring For Watering Chili Plants Rizal Tjut Adek; Muhammad Fikry; Helmi Naluri; Risawandi .
JOURNAL OF INFORMATICS AND TELECOMMUNICATION ENGINEERING Vol 5, No 2 (2022): Issues January 2022
Publisher : Universitas Medan Area

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31289/jite.v5i2.5495

Abstract

Caring for chili plants in addition to fertilization is proper watering. Watering is sometimes done less regularly in this case is the timeliness other than that the temperature and soil moisture are not paid attention to by the chili plant keepers. Moreover, if the chili plant keeper has other activities, then the watering of the plants will be more irregular, making the production of chili plants not optimal and even chili plants can die. By utilizing Arduino and several supporting sensors, we can determine the right watering time. In this research, data is taken from sensors, such as soil moisture sensors, air humidity sensors, temperature sensors and ultrasonic sensors which then the data will be sent to the website to be displayed to the user. Sensors are devices used to detect changes in physical quantities such as pressure, force, electrical quantities, light, motion, humidity, temperature, speed and other environmental phenomena. The purpose of this study was to measure soil moisture, air humidity, temperature as a determinant of the right watering time for chili plants and make it easier for farmers to monitor and water chili plants. This is evidenced in the Blackbox testing method on the system design, from the test results it is known that this system has been running well and is in accordance with what is expected.
News Opinion Classification Application With Support Vector Machine Algorithm Using Framework Codeigniter Rizal Tjut Adek; Muhammad Fikry; Umar Khalil
JOURNAL OF INFORMATICS AND TELECOMMUNICATION ENGINEERING Vol 5, No 1 (2021): EDISI JULY 2021
Publisher : Universitas Medan Area

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31289/jite.v5i1.5189

Abstract

News is an information that contains a lot of data, one of which is data about opinion / sentiment. The opinion / sentiment data of a news can be used for many things. To get the opinion value of a news, it is necessary to do a sentiment analysis technique on the news data that wants to know the level of opinion produced. Sentiment analysis is a technique that uses the data mining method. To see the height of the opinion value of a news item, the Support Vector Machine algorithm is used, which is one of the algorithms in the data mining method that is able to classify data sets into two classes. Using the CodeIgniter framework based on the PHP programming language, an application was developed that can classify the news into two classes, namely the positive class and the negative class. By using 100 pieces of news data from the national news portal, namely detik.com, about 700 sentences and more than 1000 words are generated which are then classified using the SVM algorithm. Applications are able to achieve an accuracy rate of 76%
SOSIALISASI PENGGUNAAN MEDIA SOSIAL DAN INTERNET YANG AMAN UNTUK GURU SMK NEGERI 1 LHOKSEUMAWE munirul ula; Rizal Tjut Adek; Muhammad Muhammad; Mukhlis Mukhlis; Muhammad Fauzan; Bustami Bustami
RAMBIDEUN : Jurnal Pengabdian Kepada Masyarakat Vol. 5 No. 1 (2022): Rambideun: Jurnal Pengabdian Kepada Masyarakat
Publisher : LPPM Universitas Al Muslim

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.51179/pkm.v5i1.818

Abstract

Social media does provide a plethora of fun perks. However, social media and the internet also bring negative impacts and new dangers. Technology of internet can result in many negative things in society when it is not accompanied by knowledge of wise internet use. In this era of globalization, the internet has become a major need in everyday life. The internet has a very good role in helping the role of business, learning, communication and other problems that are found when not using the internet or commonly called the manual method. Not using and following the development of the internet, can lead to lagging business and economic aspects. The method used in this service is direct presentation and workshop. The purpose of the training is to raise awareness about the possible dangers of using social media. The materials presented in this training include cases of fraud through social media, cases of identity theft and others. After that, preventive measures against the threats that may be faced and how to use social media properly are conveyed in this socialization. This training and socialization is very useful to raise awareness of teachers about the dangers that may arise in the use of the internet and social media, so that this knowledge can be conveyed and taught to students at SMK Negeri 1 Lhokseumawe and also the surrounding environment. Key Words: Awareness of social media, healthy and safe Internet, SMK teacher socialization
PELATIHAN DAN PENDAMPINGAN DIGITAL MARKETING BAGI PELAKU USAHA KULINER DI KOTA BIREUEN munirul ula; Rizal Tjut Adek; Muhammad Muhammad; Bustami Bustami; Fasdarsyah Fasdarsyah; Mukhlis Mukhlis
RAMBIDEUN : Jurnal Pengabdian Kepada Masyarakat Vol. 5 No. 1 (2022): Rambideun: Jurnal Pengabdian Kepada Masyarakat
Publisher : LPPM Universitas Al Muslim

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.51179/pkm.v5i1.837

Abstract

During the Covid-19 disaster, the condition of Micro, Small and Medium Enterprises (MSMEs) in Bireuen Regency was very alarming. The impact of the pandemic outbreak and regulations related to the Enforcement of Restrictions on Community Activities have caused sales turnover to decline, therefore culinary entrepreneurs are required to be more creative and innovative in conducting marketing activities. Digital marketing activities is one solution to increase sales during this pandemic. However, there are still many culinary business actors in Bireuen Regency who have not mastered digital marketing strategies. Therefore, digital marketing training and assistance is needed for culinary entrepreneurs in Bireuen Regency to be able to compete and innovate to increase sales turnover in this pandemic era. This Digital Marketing Training and Assistance aims to provide knowledge and skills for entrepreneurs in Bireuen Regency to increase sales through digital marketing. The results of the evaluation of this service activity are very useful for increasing the knowledge and expertise of participants in online marketing. Through this training and mentorship activity, culinary business actors in Bireuen Regency can improve social media marketing, generate marketing material to assist digital marketing, and raise sales turnover.
Emarketplace Performance Analysis Using PIECES Method Munirul Ula; Rizal Tjut Adek; Bustami Bustami
International Journal of Engineering, Science and Information Technology Vol 1, No 4 (2021)
Publisher : Master Program of Information Technology, Universitas Malikussaleh, Aceh Utara, Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (360.5 KB) | DOI: 10.52088/ijesty.v1i4.138

Abstract

E-Marketplace is a place in cyberspace where prospective buyers meet each other to conduct transactions electronically through the internet medium. Like the market in the conventional sense, namely a meeting place for sellers and buyers, in the E-Marketplace, various companies in the world also interact without being limited by the territory of space (geography) and time. Therefore, an analysis of the performance of the website is needed to ensure the performance of the Bireuen emarketplace (meukat.com) website can run effectively in the future. The role of this emarketplace is very important, therefore in building emarketplace we must pay attention to several factors, namely: performance, information, economic, control, efficiency, and service, which is better known as the PIECES method. To analyze the performance of our self-developed emarketplace, was done by PIECES method. While the testing method in the performance analysis of the website uses the GTMetrix and Google Transparency applications. The results of the PIECES questionnaire on the dimensions of Information, Economy, Efficiency, and Service. The average score for the all dimensions is moderate, it is ranging from 42.8% to 51.45% and is in line with the expectations. The GTMetric test results of the Emarketplace website, shows that the average performance grade is 66% or grade D. This means that the quality of the Emarketplace website based on the index generated by Google is still low. It should be improved to provide good quality of service for users in future. The Emarketplace are also being analyzed by the Google transparency report, the result is “no unsafe content” was found, means this website is safe to visit. There are no applications that harm the users.
Pendeteksian Dokumen Plagiarisme dengan Menggunakan Metode Weight Tree Nurdin Nurdin; Rizal Rizal; Rizwan Rizwan
Telematika Vol 12, No 1: Februari (2019)
Publisher : Universitas Amikom Purwokerto

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (694.81 KB) | DOI: 10.35671/telematika.v12i1.775

Abstract

Sistem pengelolaan dokumen plagiarisme masih ada yang dilakukan secara manual yaitu dengan mengecek satu persatu sehingga membutuhkan waktu yang lama dan kurang efektif. Salah satu algoritma yang dapat digunakan untuk pendeteksian dokumen plagiarisme adalah algoritma Weight Tree yaitu sebuah metode untuk melakukan klasifikasi kemiripan dokumen berdasarkan bobot dari dokumen. Tujuan penelitian ini adalah untuk membangun sebuah sistem pendeteksian kemiripan dari dua dokumen teks yang berbeda untuk jenis dokumen teks berbahasa indonesia dengan format file dokumen yaitu: doc, docx, pdf, rtf. Tahapan yang dilakukan pada penelitian ini terdiri dari pengumpulan data, perancangan sistem, pembuatan aplikasi dan pengujian terhadap aplikasi. Hasil pengujian sistem dapat dikategorikan sebagai sistem pendeteksian atau pengetesan kemiripan dokumen. Pada pengujian sistem ini, penulis yang mengkategorikan dokumen tersebut sebagai dokumen plagiat berdasarkan persentase kemiripan. Nilai rata-rata persentase kemiripan dalam pengujian sistem ini adalah 71,60%. Sistem yang di bangun ini berhasil dengan tingkat keakuratan mencapai 90%. Algoritma Weight Tree yang diterapkan pada sistem ini terbukti mampu mengidentifikasi dengan baik kemiripan dokumen plagiarisme.
OPINION MINING ABOUT PARFUM ON E-COMMERCE BUKALAPAK.COM USING THE NAÏVE BAYES ALGORITHM Rizal Rizal; Muhammad Fikry; Annisa Helmina
JITK (Jurnal Ilmu Pengetahuan dan Teknologi Komputer) Vol 6 No 1 (2020): JITK Issue August 2020
Publisher : LPPM Nusa Mandiri

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (1403.945 KB) | DOI: 10.33480/jitk.v6i1.1448

Abstract

Information plays a very important role in the rapid development of the world. Many people use online media to search for information, one of which is to find out information about the negative or positive of a product in e-commerce based on the comments that exist. To find out the classification of all comments-comet takes quite a long time in reading it. So, to make it easier than that all made a classification system to determine the classification of comments. In this classification process, the Naive Bayes algorithm is used as a solution to the problem. The process with the Naïve Bayes algorithm requires training data which is used as learning material from the system. The training data used is taken from one e-commerce site, Bukalapak.com regarding perfume products. Taking comments from Buakalapak.com used crawling techniques to retrieve comments from the whole product. The training data needed in this system is 1000 comments consisting of 500 positive training comments and 500 negative training comments. To get the accuracy value, it requires 300 test comments consisting of 150 positive test comments and 150 negative test comments. From the results of testing with Naive Bayes, the accuracy rate can be quite good, namely with a precision value of 96.44%, 96.34% recall, and an accuracy of 96.33%.
PROTOTIPE HAND-GEOMETRY SEBAGAI SISTEM VERIFIKASI Rizal Tjut Adek
TECHSI - Jurnal Teknik Informatika Vol 4, No 1 (2012)
Publisher : Teknik Informatika Universitas Malikussaleh

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29103/techsi.v4i1.102

Abstract

Geometric measurements of the human hand have been used for identity authentication in a number of commercial systems. In this project we have developed a prototype hand geometry-based verification system and analyzed it's performance. We have demonstrated the practical utility of this system by designing an application that uses hand geometry as opposed to password for restricting access to a web site. We present our preliminary verification results based on hand measurements of 50 individuals captured over a period of time.
DIAGNOSA KERUSAKAN MESIN TIPE OM366A PADA MOBIL MERCEDES-BENZ MENGGUNAKAN SISTEM PAKAR Rizal Rizal
TECHSI - Jurnal Teknik Informatika Vol 5, No 2 (2013)
Publisher : Teknik Informatika Universitas Malikussaleh

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29103/techsi.v5i2.148

Abstract

An expert system is a transfer of knowledge from an expert to a computer system, so the  system can be used by people who are not experts in solving the problem as was done by experts. Many cases can be used as research in expert systems, one of which diagnoses the cause engine damage. This research will design an expert system that can diagnose the cause of damage to the engine type OM366A ercedes-Benz. The method used in this study is the use of backward chaining method in the process of diagnosing it. This expert system is very useful to make it easier for technicians to perform diagnostics, so that will speed in getting a solution to the cause engine damage and repair actions in accordance with the selected type of damage and without the presence of an expert. This expert system application designed using Microsoft Visual Basic.Net 2008, Add-On Develover Express 2011and Microsoft Access 2010 as a repository for the knowledge base.