Claim Missing Document
Check
Articles

Found 13 Documents
Search

Implementation of Website-Based Graduate Learning Outcomes Measurement System Erdiansyah, Umri; Syahputra, Guntur; Rudi, Fachri Yanuar
Journal of Artificial Intelligence and Software Engineering Vol 5, No 4 (2025): Desember
Publisher : Politeknik Negeri Lhokseumawe

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30811/jaise.v5i4.8584

Abstract

Digital transformation in higher education quality assurance has become imperative following the enactment of the Minister of Education, Culture, Research, and Technology Regulation No. 53 of 2023. This study proposes the development of a web-based Graduate Learning Outcomes (GLO) measurement system to accelerate academic evaluation effectiveness at Politeknik Negeri Lhokseumawe. Employing a Research and Development (RD) approach with the Waterfall development model, this research designs the system architecture using the Model-View-Controller (MVC) pattern to ensure application scalability and modularity. The system integrates academic data management features, automated GLO calculations, and analytical data visualization to support data-driven decision-making. System testing involved User Acceptance Testing (UAT), yielding a System Usability Scale (SUS) score of 82.3, indicating an 'excellent' user acceptance level. The results confirm that this platform not only meets national regulatory compliance standards but also enhances transparency and objectivity in graduate quality reporting. This implementation makes a strategic contribution to the modernization of institutional academic governance.
Implementation of WebSocket in an IoT-Based Smart Home Door Security System Using ESP32-CAM with Face Recognition Safriadi, Safriadi; Nasir, Muhammad; Erdiansyah, Umri
Journal of Artificial Intelligence and Software Engineering Vol 6, No 1 (2026): Maret
Publisher : Politeknik Negeri Lhokseumawe

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30811/jaise.v6i1.9052

Abstract

The advancement of Internet of Things technology, especially in the field of information technology, opens up opportunities in the development of smarter, more efficient, and flexible home security systems. Frequently used systems such as fingerprints and RFID still have limitations in flexibility, scalability, and effectiveness against threats. To overcome these problems, an IoT-based home door security system was developed using ESP 32 - CAM and face recognition technology. This system utilizes the Haar Cascade Classifier algorithm for face detection and the Local Binary Pattern Histogram for face recognition. Test results show a fast response, communication stability, and an increase in accuracy of 66.07% with 10 datasets, 86.07% with 50 datasets, and 93.03% with 100 datasets. This shows that the more datasets used, the higher the system's accuracy in recognizing user faces.
PENERAPAN RANDOM SAMPLING WITHOUT REPLACEMENT PADA GAME KUIS MATEMATIKA DESKTOP MENGGUNAKAN FITUR SEQUENTIAL LEVEL UNLOCKING Erdiansyah, Umri
Djtechno: Jurnal Teknologi Informasi Vol 7, No 1 (2026): April
Publisher : Universitas Dharmawangsa

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.46576/djtechno.v7i1.8613

Abstract

Penelitian ini bertujuan untuk mengembangkan aplikasi game kuis edukasi matematika berbasis desktop yang ditujukan bagi siswa  sekolah dasar. Aplikasi ini dirancang dengan dua fitur utama: penerapan metode Random Sampling Without Replacement untuk pengacakan soal dan mekanisme penguncian level secara berurutan (sequential level unlocking). Tujuan metode pengacakan adalah untuk menjamin tidak ada soal yang berulang dalam satu sesi permainan dan urutan soal selalu bervariasi, sementara mekanisme penguncian level memastikan alur pembelajaran yang progresif. Prosedur pengembangan aplikasi menggunakan metodologi Penelitian dan Pengembangan (R&D) yang mencakup beberapa fase, khususnya pra-produksi, produksi, dan pasca-produksi. Hasil pengujian fungsional menunjukkan bahwa metode pengacakan berhasil diimplementasikan, terbukti dengan tidak adanya duplikasi soal dalam beberapa sesi percobaan. Selain itu, mekanisme penguncian tingkat juga beroperasi sesuai dengan desain, di mana tingkat selanjutnya bisa diakses hanya setelah individu menyelesaikan tingkat sebelumnya.