Claim Missing Document
Check
Articles

Implementation of Neural Machine Translation in Translating from Indonesian to Sasak Language Helna Wardhana; I Made Yadi Dharma; Khairan Marzuki; Ibjan Syarif Hidayatullah
MATRIK : Jurnal Manajemen, Teknik Informatika dan Rekayasa Komputer Vol 23 No 2 (2024)
Publisher : LPPM Universitas Bumigora

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30812/matrik.v23i2.3465

Abstract

Language translation is part of Natural Language Processing, also known as Machine Translation, which helps the process of learning foreign and regional languages using translation technology in sentence form. In Lombok, there are still people who are not very fluent in Indonesian because Indonesian is generally only used at formal events. This research aimed to develop a translation model from Indonesian to Sasak. The method used was the Neural Machine Translation with the Recurrent Neural Network - Long Short Term Memory architecture and the Word2Vec Embedding with a sentence translation system. The dataset used was a parallel corpus from the Tatoeba Project and other open sources, divided into 80% training and 20% validation data. The result of this research was the application of Neural Machine Translation with the Recurrent Neural Network - Long Short Term Memory algorithm, which could produce a model with an accuracy of 99.6% in training data and 71.9% in test data. The highest ROUGE evaluation metric result obtained on the model was 88%. This research contributed to providing a translation model from Indonesian to Sasak for the local community to facilitate communication and preserve regional language culture.
IMPLEMENTATION OF CONTINUOUS INTEGRATION/CONTINUOUS DEPLOYMENT TO AUTOMATE COMPUTER NETWORK INFRASTRUCTURE CONFIGURATION MANAGEMENT Hariyadi, I Putu; Raisul Azhar; Heroe Santoso; Khairan Marzuki; I Made Yadi Dharma
TEKNIMEDIA: Teknologi Informasi dan Multimedia Vol. 4 No. 2 (2023): Desember 2023
Publisher : Badan Penelitian dan Pengabdian Masyarakat (BP2M) STMIK Syaikh Zainuddin NW Anjani

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.46764/teknimedia.v4i2.127

Abstract

Computer network infrastructure is one of the supporting components for smooth operations for companies that utilize Information and Communication Technology (ICT). Companies are required to continue to innovate to continue to grow so it requires various adjustments, including changes to the policy configuration of computer network infrastructure. Implementation of configuration changes to computer network infrastructure if done manually will be inefficient and ineffective. In addition, it is prone to errors as a result of human error resulting in downtime. The application of Continuous Integration/Continuous Deployment (CI/CD) can be a solution to overcome these problems. This study analyzes the implementation of CI/CD on network infrastructure which is simulated using the PNETLab and GitLab CI/CD tools as well as Ansible Configuration Management. Based on the tests conducted five times, it can be concluded that the Ansible Playbook that has been created and integrated with the GitLab CI/CD pipeline can be used to automate configuration management of MikroTik-based network infrastructure that is simulated in PNETLab. CI/CD can speed up the implementation of configuration changes on network devices through an automated process. Testing additional configurations on the test network takes an average of 82.6 seconds. Meanwhile, on the production network, it takes an average of 80.2 seconds. On the other hand, testing the configuration deletion on the test network takes an average of 56.6 seconds. Meanwhile, on the production network, the average is 54.4 seconds. In addition, the application of CI/CD can minimize errors because before the configuration is applied to the production network, the configuration is tested first on the test network automatically. Application of the configuration to the production network is carried out only if testing of the configuration on the test network is successful. The CI/CD mechanism can improve the performance and reliability of computer network infrastructure.
Peningkatan Kinerja Metode Random Forest Berbasis Smote-Tomek Link Pada Sentimen Analisis Pariwisata Lombok Marzuki, Khairan; Rady Putra, Lalu Ganda; Hairani, Hairani; Mardedi, Lalu Zazuli Azhar; Guterres, Juvinal Ximenes
Jurnal Bumigora Information Technology (BITe) Vol 5 No 2 (2023)
Publisher : Universitas Bumigora

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30812/bite.v5i2.3166

Abstract

Background: Tourists visiting Lombok Island can access various sources of tourist information and can share their views and tourist experiences through social media such as positive and negative experiences. Objective: This research aims to analyze the sentiment of Lombok tourism reviews using the Smote-Tomek Link and Random Forest algorithms.Methods: The research was carried out in several stages, namely collecting the Lombok tourism dataset, text preprocessing, text weighting using the Term Frequency-Inverse Document Frequency (TF-IDF) method, data sampling using SMOTE-Tomek Link, text classification using Random Forest, and the final stage was performance testing based on accuracy. Result: The research results obtained using the Smote-Tomek Link and Random Forest methods in sentiment analysis analysis of tourist reviews about Lombok were 94%. Conclusion: The use of the Smote-Tomek Link and Random Forest methods in Lombok tourism sentiment analysis produces very good accuracy.
Penerapan Algoritma Cosine Similarity dan Pembobotan TF-IDF System Penerimaan Mahasiswa Baru pada Kampus Swasta Apriani, Apriani; Zakiyudin, Hizbu; Marzuki, Khairan
Jurnal Bumigora Information Technology (BITe) Vol 3 No 1 (2021)
Publisher : Universitas Bumigora

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30812/bite.v3i1.1110

Abstract

The era of globalization is marked by the development of technology and information, this has an impact on the human need for information. PMB(Reception New Students) is a routine college activity at each opening of new teachings. The implementation of PMB is not without questions that has been asked before. By making use of technology information the an FAQ (Frequently Asked Questions) was born which contain answers of the questions that are often asked by people who are need information. To reduce the question repeatedly, then an FAQ answering system was built by applying TF-IDF (Term Frequency - Inverse Document) and the cosine similarity algorithm. TF-IDFweighting is a method for giving weights the relationship of a word (term) to a document is based on two concepts, namely frequency of occurrence of words in a document and frequency inverse documents containing the word. Meanwhile, cosine similarity is a method used to calculate the level of similarity between two objects. This method calculates the similarity between two pieces the object represented in two vectors using keywords of a document as a measure. This study uses 7 data samples from all FAQ data obtained from an interview with Ms. Susilawati, S.Kom. The sample data used will go through a processpreprocessing, TF-IDF weighting, and the cosine similarity method fordetermines the highest level of similarity that will come out as a result end. By using TF-IDF weighting and the cosine similarity method on 7 sample data can get an accuracy rate of up to 64,28%.
Implementation of Neural Machine Translation in Translating from Indonesian to Sasak Language Helna Wardhana; I Made Yadi Dharma; Khairan Marzuki; Ibjan Syarif Hidayatullah
MATRIK : Jurnal Manajemen, Teknik Informatika dan Rekayasa Komputer Vol. 23 No. 2 (2024)
Publisher : LPPM Universitas Bumigora

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30812/matrik.v23i2.3465

Abstract

Language translation is part of Natural Language Processing, also known as Machine Translation, which helps the process of learning foreign and regional languages using translation technology in sentence form. In Lombok, there are still people who are not very fluent in Indonesian because Indonesian is generally only used at formal events. This research aimed to develop a translation model from Indonesian to Sasak. The method used was the Neural Machine Translation with the Recurrent Neural Network - Long Short Term Memory architecture and the Word2Vec Embedding with a sentence translation system. The dataset used was a parallel corpus from the Tatoeba Project and other open sources, divided into 80% training and 20% validation data. The result of this research was the application of Neural Machine Translation with the Recurrent Neural Network - Long Short Term Memory algorithm, which could produce a model with an accuracy of 99.6% in training data and 71.9% in test data. The highest ROUGE evaluation metric result obtained on the model was 88%. This research contributed to providing a translation model from Indonesian to Sasak for the local community to facilitate communication and preserve regional language culture.
IMPLEMENTASI PENGGUNAAN HAPROXY LOAD BALANCING DAN FAIL2BAN PADA SERVER MENGGUNAKAN VIRTUAL PRIVATE SERVER Maulid Putra Perdana; Marzuki, Khairan; Ondi Asroni; Husain; Lillik Widyawati; Lalu Zazuli AzharMardedi
Jurnal Manajemen Informatika dan Sistem Informasi Vol. 8 No. 2 (2025): MISI Juni 2025
Publisher : LPPM STMIK Lombok

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36595/misi.v8i2.1593

Abstract

Seiring meningkatnya kebutuhan layanan berbasis web, performa dan keamanan server menjadi aspek krusial dalam pengelolaan infrastruktur jaringan. Beban yang tinggi pada server dapat menyebabkan penurunan kinerja hingga kegagalan layanan (server down). Oleh karena itu, diperlukan sistem Load Balancing untuk mendistribusikan lalu lintas secara merata dan sistem keamanan tambahan untuk melindungi server dari ancaman serangan. Penelitian ini menganalisis penerapan Load Balancing menggunakan HAProxy dengan algoritma Round Robin untuk meningkatkan kinerja server serta penerapan Fail2Ban sebagai sistem keamanan dalam mencegah seseorang yang mencoba login berulang kali pada Virtual Private Server (VPS). Metode penelitian yang digunakan adalah Network Development Life Cycle (NDLC), yang mencakup analisis kebutuhan, desain sistem, simulasi prototype. Pengujian dilakukan dengan Apache JMeter untuk mengukur kinerja server dan simulasi percobaan login gagal dilakukan dengan PuTTy untuk menguji efektivitas Fail2Ban. Hasil penelitian menunjukkan bahwa HAProxy load balancing berhasil mendistribusikan beban secara merata, meningkatkan ketersediaan layanan, dan mengurangi waktu respons. Selain itu, penerapan Fail2Ban terbukti efektif dalam mendeteksi serta memblokir alamat IP yang berulang kali gagal melakukan login, sehingga meningkatkan keamanan server. Penelitian ini memberikan kontribusi dalam optimalisasi performa dan keamanan server berbasis VPS, yang dapat diterapkan pada berbagai layanan web seperti e- commerce, blog, sistem perusahaan, maupun sekolah.
EVALUASI MANAJEMEN RISIKO TEKNOLOGI INFORMASI BERDASARKAN FRAMEWORK NIST SP 800-30 REV.1 Yudistira, Yudha; Anas, Andi Sofyan; Marzuki, Khairan
Jurnal Manajemen Informatika dan Sistem Informasi Vol. 8 No. 2 (2025): MISI Juni 2025
Publisher : LPPM STMIK Lombok

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36595/misi.v8i2.1623

Abstract

Perkembangan teknologi informasi yang pesat memberikan banyak manfaat bagi perusahaan dalam meningkatkan efisiensi operasional, kualitas layanan, serta pengambilan keputusan berbasis data. Namun, di balik berbagai manfaat tersebut, terdapat risiko yang dapat mengganggu kelangsungan bisnis apabila tidak dikelola dengan baik. Oleh karena itu, manajemen risiko teknologi informasi menjadi aspek krusial yang harus diterapkan secara sistematis. Penelitian ini dilakukan di PT Air Minum Giri Menang untuk mengevaluasi bagaimana praktik manajemen risiko TI dijalankan di lingkungan perusahaan. Framework NIST SP 800-30 digunakan sebagai pendekatan utama dalam mengidentifikasi aset informasi, menganalisis potensi ancaman, mengevaluasi kerentanan, serta menilai dampak dan kemungkinan risiko yang dapat terjadi. Hasil dari penelitian ini menunjukkan bahwa sebagian besar risiko berada pada tingkat sedang (medium), dengan jenis ancaman yang paling menonjol berasal dari brute force attack dan kesalahan manusia (human error). Temuan ini menjadi dasar penting dalam perencanaan tindakan mitigasi risiko yang lebih efektif dan terstruktur ke depannya.
Application of Domain Keys Identified Mail, Sender Policy Framework, Anti-Spam, and Anti-Virus: The Analysis on Mail Servers Marzuki, Khairan; Hanif, Naufal; Hariyadi, I Putu
International Journal of Electronics and Communications Systems Vol. 2 No. 2 (2022): International Journal of Electronics and Communications System
Publisher : Universitas Islam Negeri Raden Intan Lampung, Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24042/ijecs.v2i2.13543

Abstract

Viruses spread through email are often sent by irresponsible parties that aim to infect email users' servers. This background encouraged the author to analyze the application of DKIM, SPF, anti-spam, and anti-virus to avoid spam, viruses, and spoofing activities. The goal is for the server to prevent spam, spoofing, and viruses to ensure the security and convenience of email users and prevent the impact of losses caused by them. The design and analysis of DKIM, SPF, anti-spam, and anti-virus applications use the NDLC methodology. The process includes designing spam, spoofing, and virus filtering systems and performing installation and configuration simulations. The next stage is implementation, during which the previously developed system is tested on the spam filtering system, spoofing, and viruses. The last stage is the monitoring stage, where supervision is conducted on the approach to determine its success level. This study concludes that applying the DKIM protocol can prevent spoofing through private and public key-matching methods for authentication. Meanwhile, the application of the SPF protocol can prevent spoofing by authorizing the IP address of the sending server. Additionally, SpamAssassin, ClamAV and Amavisd-New can prevent spam and viruses from entering by checking email headers, bodies, and attachments.
Automation of Open VSwitch-Based Virtual Network Configuration Using Ansible on Proxmox Virtual Environment Marzuki, Khairan; Kholid, Muhammad Idham; Hariyadi, I Putu; Mardedi, Lalu Zazuli Azhar
International Journal of Electronics and Communications Systems Vol. 3 No. 1 (2023): International Journal of Electronics and Communications System
Publisher : Universitas Islam Negeri Raden Intan Lampung, Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24042/ijecs.v3i1.16524

Abstract

Proxmox has a feature that can build a private network in it. Each host on a private network on Proxmox generally shares physical resources, including network connections using a virtual network, one of which is a VLAN. The Proxmox server supports Open VSwitch as a virtual switch. Open virtual switch, an alternative virtual switch quite popular among cloud developers, can be a solution for managing traffic between Virtual Machins and external communications. The method used in this study is the Network Development Life Cycle (NDLC). After applying the automation engine using Ansible, it overcame the problem, namely speeding up configuration and reducing human error or errors in configuring virtual networks. The automation system can speed up the virtual network management process compared to the manual method based on 5 (five) experiments, namely when the manufacturing operation has an average time of 08 minutes and 42 seconds faster. Whereas when the addition operation has an average faster time of 08 minutes 17 seconds. On the other hand, when the deletion operation has an average time of 42 seconds faster.
Analysis and Implementation of Comparison Between Podman and Docker in Container Management Husain, Husain; Marzuki, Khairan; lauw, Christopher Michael; Azhar Mardedi, Lalu Zazuli
International Journal of Electronics and Communications Systems Vol. 3 No. 2 (2023): International Journal of Electronics and Communications System
Publisher : Universitas Islam Negeri Raden Intan Lampung, Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24042/ijecs.v3i2.19860

Abstract

The increasing use of the internet makes the implementation process more accessible, but the problem is that it is difficult to manage network management, with the emergence of container technologies such as Docker and Podman as efficient application management solutions. This research compares Docker and Podman regarding container management using the Network Development Life Cycle (NDLC) methodology. This study evaluates three parameters: accessing the Fedora project registry, handling images or ISOs, and user access in containers. The results show that Podman performs better regarding registry access, is slightly faster with images, and offers faster user creation. Overall, the study concludes that Podman is superior, demonstrating compatibility with Docker and proving its efficacy in container management.
Co-Authors Abdurraghib Segaf Suweleh Affan, Usman Ibnu Andi Sofyan Anas Anthony Anggrawan Apriani Apriani Apriani Apriani Apriliana, Zikriati Arief Setyanto Asro Nasiri As’ary Ramadhan Ayu Dasriani, Ni Gusti azhar mardedi, lalu zazuli Azhar, Raisul Baiq Chandra Herawati Canggih Wahyu Rinaldi Dedy Febry Rachman Dewa Ayu Oki Astarini Dewi, Puspita Dyah Susilowati Dyah Susilowaty Eria Raudhatul Jannah Guterres, Juvinal Ximenes Hairani Hairani Hanif, Naufal Hariyadi, I Putu Helna Wardhana Husain Husain Husain I Made Yadi Dharma I Putu Hariyadi Ibjan Syarif Hidayatullah Ikang Murapi Ikrom, Paizul Indah Puji Lestari Ismail Husein, Ismail Juliyanto, Fery Jusmita Weriza Khairul Imtihan Kholid, Muhammad Idham Kurniadin Abd Latif Lalau Ganda Rady Putra Lalu Ahmad Najmul Munir Lalu Ganda Rady Putra Lalu Zazuli AzharMardedi lauw, Christopher Michael Lilik Widyawati Lillik Widyawati M Fakhariza Mardedi, Lalu Zazuli Azhar Mardedi, Lalu Zazuli Azhar Maulana Ashari Maulid Putra Perdana Mia Mubiatma Mohammad Taufan Asri Zaen Muhammad Idham Kholid Naufal Hanif Ni Ketut Sriwinarti Noranizamardia Noranizamardia Ondi Asroni Parama Diptya Widayaka PUTRA, MUHAMAD ALVAN EKAWAN R. Ayu Ida Aryani Radimas Putra Muhammad Davi Labib Regina Pricilia Yunika Rifqi Hammad Safii, M Sahimin, Sahimin Santoso, Heroe Sirojul Hadi Siti Soraya Sunardy Kasim Syamsurrijal, Syamsurrijal Syarif Hidayatullah, Ibjan Tomi Tri Sujaka Usman Ibnu Affan Yadi Dharma, I Made Yudistira, Yudha Yusri Ikhwani Zakiyudin, Hizbu