Jurnal Komputer Antartika

Rancang Bangun Sistem Penerjemah Multibahasa Daerah Maluku Utara dengan Integrasi GPT Sebagai Pelestarian Budaya Lokal

Anggiah Salim, Abdul Haris Muhammad , Sakina Sudin (Author) — Sat, 20 Jun 2026 00:00:00 +0000

Penelitian ini membahas pengembangan sistem penerjemah multibahasa daerah berbasis web yang mengintegrasikan metode Rule-Based Machine Translation (RBMT) dan GPT untuk menerjemahkan Bahasa Indonesia dengan Bahasa Ternate, Makian Dalam, dan Galela menggunakan 5.572 kosakata berbasis kamus digital, dimana RBMT digunakan untuk pencocokan kata berdasarkan aturan dan GPT digunakan untuk memperbaiki struktur kalimat agar lebih natural sesuai konteks, dengan sistem yang dikembangkan menggunakan HTML, CSS, JavaScript, serta integrasi API GPT melalui Vercel, kemudian diuji menggunakan 468 kalimat yang menghasilkan kategori hasil berupa terjemahan sesuai target, berbeda bentuk namun bermakna sama, tidak sesuai akibat keterbatasan kosakata, serta ketidaktepatan karena ambiguitas makna (satu kata yang memiliki banyak arti), sehingga hasil penelitian menunjukkan bahwa kombinasi RBMT dan GPT mampu meningkatkan kualitas terjemahan meskipun masih dipengaruhi oleh ambiguitas kata, kelengkapan kamus, serta penggunaan tanda baca dan pemisahan kata yang dapat mempengaruhi makna dan akurasi hasil terjemahan.

This research discusses the development of a web-based regional multilingual translation system that integrates the Rule-Based Machine Translation (RBMT) method and GPT to translate Indonesian into Ternate, Makian Dalam, and Galela languages using 5,572 vocabulary entries based on a digital dictionary, where RBMT is used for rule-based word matching and GPT is used to improve sentence structure to make the translations more natural and contextually appropriate. The system was developed using HTML, CSS, JavaScript, and GPT API integration through Vercel, and was tested using 468 sentences that produced several categories of results, including translations that matched the target exactly, translations with different sentence forms but the same meaning, inaccurate translations due to limited vocabulary, and inaccuracies caused by semantic ambiguity (a single word having multiple meanings). The results of the study indicate that the combination of RBMT and GPT is capable of improving translation quality, although it is still influenced by word ambiguity, dictionary completeness, and the use of punctuation and word separation, which can affect the meaning and accuracy of the translation results.

Evaluasi Usabilitas Interaksi Pengguna Aplikasi Shopee Menggunakan System Usability Scale

Sat, 20 Jun 2026 00:00:00 +0000

Platform belanja daring seperti Shopee perlu menyediakan antarmuka yang mudah digunakan oleh pengguna. Penelitian ini bertujuan mengukur tingkat usabilitas aplikasi mobile Shopee menggunakan metode System Usability Scale (SUS). Data dikumpulkan melalui kuesioner Google Form yang memuat 10 pertanyaan standar SUS dengan skala Likert. Kuesioner disebarkan kepada pengguna aktif Shopee dan diperoleh data dari 37 responden. Hasil perhitungan menunjukkan nilai rata-rata skor SUS sebesar 66,71. Nilai tersebut termasuk dalam kategori OK (Marginal High) dengan Grade D. Selain hasil pengukuran SUS, responden juga menyampaikan beberapa kendala dalam penggunaan aplikasi, seperti banyaknya banner iklan, terjadinya lag saat aplikasi digunakan, serta tampilan fitur Live dan gim yang dianggap kurang teratur.

Online shopping platforms such as Shopee need to provide an interface that is easy for users to use. This study aims to measure the usability level of the Shopee mobile application using the System Usability Scale (SUS) method. Data were collected through a Google Form questionnaire containing 10 standard SUS questions using a Likert scale. The questionnaire was distributed to active Shopee users, and data were obtained from 37 respondents. The calculation results showed an average SUS score of 66.71. This score falls into the OK (Marginal High) category with a Grade D rating. In addition to the SUS measurement results, respondents also reported several issues in using the application, such as the large number of advertising banners, lag during application use, and the arrangement of the Live and game features, which was considered less organized.

Double Layer Encryption Caesar Cipher dan AES-128 untuk Pengamanan Data Teks Web

Siboy Arisona, Nanda Aulia Ramadlani, Muhlis Tahir (Author) — Sat, 27 Jun 2026 00:00:00 +0000

Keamanan data teks pada aplikasi web menjadi perhatian penting karena tingginya risiko penyadapan dan pencurian informasi digital. Penggunaan algoritma enkripsi tunggal masih memiliki kelemahan terhadap teknik kriptanalisis modern sehingga diperlukan metode pengamanan yang lebih kuat. Penelitian ini bertujuan membangun sistem pengamanan data teks berbasis web menggunakan metode double layer encryption dengan menggabungkan algoritma Caesar Cipher dan AES-128. Proses enkripsi dilakukan dalam dua tahap, yaitu plaintext dienkripsi menggunakan Caesar Cipher kemudian dilanjutkan dengan AES-128 untuk menghasilkan ciphertext yang lebih kompleks. Hasil penelitian menunjukkan bahwa kombinasi kedua algoritma mampu meningkatkan keamanan data karena ciphertext lebih sulit dianalisis dibandingkan penggunaan algoritma tunggal. Sistem yang dibangun juga mampu menjalankan proses enkripsi dan dekripsi dengan baik serta memberikan perlindungan data yang lebih baik.

Text data security in web-based applications has become important due to the increasing risk of interception and digital information theft. The use of a single encryption algorithm still has weaknesses against modern cryptanalysis techniques to modern cryptanalysis techniques; therefore, stronger security methods are required. This study aims to develop a web-based text security system using a double layer encryption method by combining Caesar Cipher and AES-128. The encryption process is carried out in two stages, where plaintext is encrypted using Caesar Cipher and then re-encrypted using AES-128 to produce more complex ciphertext. The results show that the combination of both algorithms improves data security because the ciphertext becomes more difficult to analyze compared to a single algorithm approach. The developed system is also capable of performing encryption and decryption processes properly while providing better protection for digital data.

Pengembangan Sistem Informasi Tracer Study Alumni Berbasis Web Menggunakan Laravel di Politeknik Negeri Bengkalis

Mon, 22 Jun 2026 00:00:00 +0000

Tracer study merupakan kegiatan penting bagi perguruan tinggi untuk mengetahui perkembangan lulusan setelah menyelesaikan pendidikan, khususnya terkait kondisi pekerjaan, kesesuaian kompetensi, dan persebaran alumni. Namun, proses pengumpulan data alumni di banyak perguruan tinggi masih dilakukan secara manual atau menggunakan media yang tidak terintegrasi sehingga data sulit diperbarui dan dikelola secara optimal. Penelitian ini bertujuan untuk merancang dan membangun sistem informasi alumni berbasis web menggunakan framework Laravel pada Politeknik Negeri Bengkalis. Metode penelitian yang digunakan meliputi analisis kebutuhan sistem, perancangan sistem menggunakan Unified Modeling Language (UML), implementasi aplikasi, dan pengujian sistem. Sistem yang dikembangkan menyediakan fitur pengelolaan data alumni, pengisian tracer study, dan pengelolaan laporan oleh admin. Hasil penelitian menunjukkan bahwa sistem informasi alumni berbasis Laravel mampu membantu proses pendataan lulusan secara lebih efektif, terstruktur, dan mudah diakses oleh alumni maupun pihak kampus. Sistem ini diharapkan dapat mendukung kebutuhan pelaporan akademik, akreditasi, serta memperkuat hubungan antara alumni dan institusi.

Tracer study is an important activity for higher education institutions to monitor the development of graduates after completing their studies, particularly related to employment conditions, competency relevance, and alumni distribution. However, alumni data collection in many higher education institutions is still conducted manually or through non-integrated media, making the data difficult to update and manage effectively. This study aims to design and develop a web-based alumni information system using the Laravel framework at Politeknik Negeri Bengkalis. The research methods used include system requirement analysis, system design using Unified Modeling Language (UML), application implementation, and system testing. The developed system provides features for alumni data management, tracer study data collection, and report management by administrators. The results of this study indicate that the Laravel-based alumni information system is capable of supporting alumni data collection processes more effectively, systematically, and accessibly for both alumni and campus administrators. This system is expected to support academic reporting, accreditation requirements, and strengthen the relationship between alumni and the institution.

Implementasi Algoritma AES dan SHA-256 untuk Acces Control dalam Pengamanan Data Siswa Berbasis Web

Zulfatul Mufida, Muhlis Tahir, Adinda Mulya Rahayu (Author) — Fri, 26 Jun 2026 00:00:00 +0000

Pengembangan sistem berbasis web dalam dunia pendidikan meningkatkan efisiensi pengelolaan data siswa, namun juga memperbesar risiko kebocoran data dan akses tidak sah. Penelitian ini bertujuan untuk mengimplementasikan sistem keamanan data siswa melalui integrasi algoritma kriptografi dan pembatasan hak akses. Metode yang digunakan adalah experimental research yang mencakup tahap perancangan, implementasi, dan pengujian sistem. Sistem keamanan ini dibangun dengan menerapkan fungsi hashing Secure Hash Algorithm 256 (SHA-256) untuk mengamankan proses autentikasi login pengguna. Sementara itu, kerahasiaan data siswa dijaga menggunakan enkripsi Advanced Encryption Standard (AES-GCM) sebelum disimpan ke database, serta didukung oleh mekanisme access control untuk membatasi hak pengaksesan data. Hasil pengujian menunjukkan bahwa sistem berhasil meningkatkan proteksi data siswa melalui pendekatan multi-layer security. Integrasi ketiga metode ini terbukti efektif dalam menjaga aspek kerahasiaan, integritas data, serta mencegah akses dari pihak yang tidak berwenang.

The development of web-based systems in education enhances the efficiency of student data management, yet it increases the risks of data breaches and unauthorized access. This study aims to implement a secure student data management system by integrating cryptographic algorithms and access restrictions. The method employed is experimental research, spanning system design, implementation, and testing phases. The security system is built by applying the Secure Hash Algorithm 256 (SHA-256) hashing function to secure the user authentication login process. Meanwhile, the confidentiality of student data is maintained using Advanced Encryption Standard (AES-GCM) encryption prior to database storage, supported by an access control mechanism to restrict data exposure. The testing results demonstrate that the system successfully enhances student data protection through a multi-layer security approach. The integration of these three methods proves effective in ensuring confidentiality, data integrity, and preventing unauthorized access.

Pengembangan Digital Vault Multi-Format dan Pengujian Kerentanan Terhadap Unauthorized Access

Ahmad Suhaimi, Muhlis Tahir, Anisatur Rohmah (Author) — Wed, 01 Jul 2026 00:00:00 +0000

Perkembangan teknologi pengelolaan dokumen digital menuntut mekanisme keamanan tingkat file yang andal untuk mencegah risiko kebocoran data akibat unauthorized access. Banyak perangkat lunak pengamanan saat ini hanya optimal dalam menangani dokumen teks statis, namun mengalami kegagalan berupa kerusakan struktur file (file corruption) saat memproses berkas multimedia berukuran besar. Penelitian ini merancang dan mengimplementasikan sistem Digital Vault universal multi-format berbasis Python dan Streamlit dengan mengintegrasikan algoritma Advanced Encryption Standard (AES-128) untuk enkripsi konten berkas dan Secure Hash Algorithm (SHA-256) untuk pengamanan kredensial serta pembentukan kunci kunci kriptografi yang presisi. Sistem ini dirancang untuk mendukung fungsionalitas multi-format, mencakup dokumen administratif (.pdf, .xls) hingga berkas multimedia (.jpg, .mp4) secara utuh (lossless). Pengujian keamanan dilakukan secara agresif melalui tiga parameter serangan nyata: pembukaan paksa (Bypass Test), kunci salah (Invalid Key Test), dan simulasi pencurian berkas keluar dari platform server (Data Exfiltration Test). Hasil pengujian membuktikan bahwa Digital Vault berhasil mempertahankan integritas data tepat 100%, kebal terhadap bypass aplikasi standar, secara akurat menolak kunci tidak sah, dan file cipherteks yang dicuri tetap mempertahankan enkapsulasi keamanannya sehingga tidak dapat dieksploitasi oleh peretas.

The advancement of digital document management technology demands reliable file-level security mechanisms to prevent data leakage risks due to unauthorized access. Many current security software applications are only optimized for static text documents, yet they suffer from file corruption when processing large multimedia files. This study designs and implements a universal multi-format Digital Vault system based on Python and Streamlit, integrating the Advanced Encryption Standard (AES-128) for file content encryption and the Secure Hash Algorithm (SHA-256) for credential securing and precise cryptographic key derivation. The system is engineered to support multi-format functionalities, ranging from administrative documents (.pdf, .xls) to multimedia assets (.jpg, .mp4) with lossless integrity. Security testing was aggressively conducted through three real-world attack parameters: forced opening (Bypass Test), wrong cryptographic key submission (Invalid Key Test), and data theft simulation outside the host server platform (Data Exfiltration Test). The empirical results prove that the Digital Vault successfully maintains 100% data integrity, is fully resilient against standard application bypasses, accurately rejects unauthorized keys, and the exfiltrated ciphertext completely retains its security envelope, rendering it unexploitable to intruders.

Segmentasi Perilaku Pengguna Kartu Kredit untuk Prediksi Default dengan K-Means Clustering

Faiz Daffa Kurnia, Supriatin, Dwi Nurani, Alfie Nur Rahmi (Author) — Sat, 04 Jul 2026 00:00:00 +0000

Peningkatan penggunaan kartu kredit di berbagai lapisan masyarakat diikuti oleh meningkatnya risiko credit default yang berpotensi menimbulkan kerugian finansial bagi institusi keuangan. Penelitian ini bertujuan untuk melakukan segmentasi perilaku pengguna kartu kredit serta menganalisis potensi default pada setiap segmen menggunakan metode K-Means Clustering. Data yang digunakan berasal dari Credit Card User Behavior and Default Dataset dari Kaggle, yang mencakup 10.000 nasabah dengan 24 atribut. Metodologi penelitian meliputi praproses data, seleksi fitur berbasis korelasi, penentuan jumlah cluster optimal menggunakan Elbow Method dan Silhouette Analysis, serta visualisasi dengan Principal Component Analysis (PCA). Hasil penelitian menunjukkan bahwa jumlah cluster optimal diperoleh pada K=2 dengan nilai Silhouette Score sebesar 0,250, lebih tinggi dibandingkan K=3 (0,195) dan K=4 (0,178). Segmentasi yang dihasilkan mampu mengidentifikasi perbedaan karakteristik perilaku nasabah yang berkaitan dengan tingkat risiko default. Kontribusi penelitian ini terletak pada integrasi metode unsupervised learning untuk segmentasi perilaku dengan analisis risiko pada tiap cluster, serta pengembangan aplikasi berbasis web menggunakan Streamlit untuk mendukung prediksi segmen nasabah secara interaktif.

The increasing use of credit cards across various segments of society has led to a higher risk of credit default, potentially causing financial losses for financial institutions. This study aims to segment credit card user behavior and analyze default risk within each segment using the K-Means Clustering method. The dataset used is the Credit Card User Behavior and Default Dataset from Kaggle, consisting of 10,000 customers with 24 attributes. The research methodology includes data preprocessing, correlation-based feature selection, determination of the optimal number of clusters using the Elbow Method and Silhouette Analysis, and visualization using Principal Component Analysis (PCA). The results indicate that the optimal number of clusters is K=2, achieving the highest Silhouette Score of 0.250, compared to K=3 (0.195) and K=4 (0.178). The resulting segmentation identifies distinct behavioral characteristics associated with different levels of default risk. The main contribution of this study lies in integrating unsupervised learning for behavioral segmentation with risk analysis in each cluster, as well as implementing the model in a web-based application using Streamlit to support interactive decision-making.

Analisis Kerentanan Keamanan Website Sekolah Menggunakan Metode Vulnerability Assessment Berbasis OWASP ZAP

Nur Fadhillatur Rahmadayanti, Muhlis Tahir, Ayu Sanusih (Author) — Fri, 10 Jul 2026 00:00:00 +0000

Perkembangan teknologi informasi yang pesat telah mendorong pemanfaatan website dalam berbagai sektor, termasuk pada lingkungan pendidikan sebagai media penyampaian informasi dan layanan akademik. Website sekolah berperan penting dalam pengelolaan data dan akses informasi secara daring, namun juga rentan terhadap berbagai ancaman keamanan siber. Oleh karena itu, diperlukan pengujian keamanan secara terstruktur untuk mengidentifikasi celah yang berpotensi disalahgunakan. Penelitian ini bertujuan untuk menganalisis tingkat kerentanan keamanan pada website sekolah menggunakan metode vulnerability assessment berbasis OWASP. Proses pengujian dilakukan dengan memanfaatkan tools OWASP ZAP sebagai vulnerability scanner melalui tahapan scanning, analisis kerentanan, dan pelaporan hasil berdasarkan standar OWASP Top 10. Hasil pengujian menunjukkan ditemukan 1 kerentanan kategori high, 8 kerentanan kategori medium, dan 6 kerentanan kategori low yang menunjukkan masih terdapat celah keamanan pada website yang perlu segera diperbaiki. Oleh karena itu, diperlukan tindakan mitigasi melalui validasi input, peningkatan kontrol akses, serta konfigurasi keamanan server guna meningkatkan keamanan sistem secara keseluruhan.

The rapid development of information technology has encouraged the utilization of websites in various sectors, including the educational environment as a medium for delivering information and academic services. School websites play an important role in managing data and providing online access to information; however, they are also vulnerable to various cybersecurity threats. Therefore, structured security testing is required to identify potential vulnerabilities that could be exploited. This study aims to analyze the level of security vulnerabilities in a school website using an OWASP-based vulnerability assessment method. The testing process was conducted using the OWASP ZAP tool as a vulnerability scanner through several stages, including scanning, vulnerability analysis, and reporting based on the OWASP Top 10 standard. The results of the testing showed that there was 1 high-risk vulnerability, 8 medium-risk vulnerabilities, and 6 low-risk vulnerabilities, indicating that the website still contains security gaps that need immediate attention. Therefore, mitigation efforts are required through input validation, improved access control, and proper server security configuration to enhance the overall security of the system.

Integrasi Simple Additive Weighting dan Analisis Selisih Jarak Untuk Meminimalisir Bias Pemilihan Jurusan SMK

Nazaruddin Ahmad, Danil Arianda, Tin Salwa, Muhammad Faridi (Author) — Sun, 19 Jul 2026 00:00:00 +0000

Sistem Pendukung Keputusan (SPK) merupakan sistem yang dirancang untuk membantu proses pengambilan keputusan dalam memilih alternatif terbaik berdasarkan sejumlah kriteria yang telah ditentukan. Pemilihan jurusan sekolah lanjutan merupakan fase krusial bagi siswa kelas IX, namun seringkali terhambat oleh minimnya pemahaman potensi diri dan kurangnya sistem rekomendasi yang objektif. Penelitian ini bertujuan untuk membangun SPK guna merekomendasikan jurusan Sekolah Menengah Kejuruan (SMK) yang tepat bagi siswa sekolah menengah pertama menggunakan metode Simple Additive Weighting (SAW). Pengambilan keputusan didasarkan pada enam kriteria akademik, yaitu nilai Matematika, IPA, Bahasa Inggris, TIK, Bahasa Indonesia, dan Prakarya. Kebaruan penelitian ini terletak pada penerapan metode SAW dalam dua tahap, yaitu menghitung nilai prefrensi profil ideal setiap jurusan dan menghitung nilai preferensi masing-masing siswa secara terpisah. Selanjutnya, kedua nilai preferensi tersebut dibandingkan menggunakan analisis selisih (gap analysis) untuk memperoleh jurusan dengan tingkat kedekatan tertinggi terhadap profil akademik siswa. Berbeda dengan penggunaan metode SAW pada umumnya yang menentukan rekomendasi alternatif terbaik berdasarkan nilai preferensi tertinggi, penelitian ini menghasilkan rekomendasi berdasarkan nilai selisih terkecil antara siswa terhadap profil ideal jurusan. Hasil pengujian terhadap 35 data siswa dan lima alternatif jurusan menunjukkan bahwa sistem mampu menghasilkan rekomendasi jurusan secara objektif sesuai karakteristik akademik sehingga dapat membantu guru Bimbingan Konseling (BK) dalam memberikan arahan yang presisi, konsisten, dan terukur. Dengan demikian, rekomendasi jurusan tidak ditentukan berdasarkan nilai preferensi tertinggi sebagaimana implementasi SAW pada umumnya, melainkan berdasarkan nilai selisih preferensi terkecil antara profil akademik siswa dan profil ideal masing-masing jurusan.

A Decision Support System (DSS) is a computer-based system designed to assist decision-making processes by selecting the most appropriate alternative based on a set of predefined criteria. Choosing an appropriate study program for upper secondary education is a crucial stage for ninth-grade students, as it significantly influences their future academic and career development. However, this decision is often hindered by students' limited understanding of their academic potential and the lack of an objective recommendation system. This study aims to develop a Decision Support System to recommend suitable vocational majors at Vocational High Schools (SMK) for junior high school students using the Simple Additive Weighting (SAW) method. The decision-making process is based on six academic criteria, namely Mathematics, Natural Sciences, English, Information and Communication Technology (ICT), Indonesian Language, and Craftsmanship (Prakarya). The novelty of this study lies in the implementation of the Simple Additive Weighting (SAW) method through a two-stage evaluation process. In the first stage, the preference values representing the ideal profile of each vocational major are calculated. In the second stage, the preference values of individual students are computed independently using the same evaluation criteria. Subsequently, the two preference values are compared using a gap analysis approach to identify the vocational major with the highest level of similarity to the student's academic profile. Unlike conventional implementations of the Simple Additive Weighting (SAW) method, which determine the best alternative solely based on the highest preference value, the proposed approach recommends a vocational major by identifying the smallest preference gap between the student's academic profile and the ideal profile of each vocational major. Experimental results obtained from 35 student records and five vocational major alternatives demonstrate that the proposed system is capable of generating objective recommendations that accurately reflect students' academic characteristics. Consequently, the system can assist Guidance and Counseling (GC) teachers in providing more precise, consistent, and evidence-based recommendations for selecting the most appropriate vocational major. Therefore, unlike the conventional implementation of the Simple Additive Weighting (SAW) method, which selects the best alternative based on the highest preference value, the proposed approach determines the recommended vocational major by identifying the smallest preference gap between the student's academic profile and the ideal profile of each vocational major.