Claim Missing Document
Check
Articles

Found 2 Documents
Search

Design of a Web-Based Household Worship Scheduling Information System at GBI Wangga Intan G. Lika Yanggu; Pingky A. R. Leo Lede
Journal of Artificial Intelligence and Engineering Applications (JAIEA) Vol. 5 No. 3 (2026): June 2026
Publisher : Yayasan Kita Menulis

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59934/jaiea.v5i3.2332

Abstract

The rapid development of information technology has increased the need for effective information management in various organizations, including churches. At GBI Wangga, the scheduling of Household Fellowship Worship (PA) is still conducted manually through written records and verbal announcements, resulting in delays and uneven distribution of information among congregation members. This study aims to design and develop a web-based Household Fellowship Worship Scheduling Information System to facilitate schedule management and improve access to information. The system was developed using the Waterfall method, which includes requirements analysis, system design, implementation, and testing. The resulting system enables users to access worship schedules quickly and accurately through a web platform. It is expected to improve scheduling efficiency, reduce information delivery errors, and support better church services for the congregation.
Sistem Pendeteksi Kemiripan Abstrak Proposal Skripsi Menggunakan Metode TF-IDF dan Cosine Similarity Berbasis Web Rosny Kabida; Pingky A. R. Leo Lede; Murry Albert Agustin Lobo
Jurnal Inovatif Vol. 5 No. Special (2026): Volume 05 Edisi Khusus Agustus 2026
Publisher : Universitas Kristen Wira Wacana Sumba

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.58300/6se7ez03

Abstract

Penelitian ini mengembangkan SI-KEMA, yaitu sistem berbasis web untuk mendeteksi kemiripan abstrak proposal skripsi menggunakan pembobotan TF-IDF dan Cosine Similarity. Sistem mendukung validasi awal dengan membandingkan abstrak yang diunggah dengan dokumen dalam repositori lokal. Tahapan pemrosesan meliputi ekstraksi teks PDF, verifikasi hasil ekstraksi oleh pengguna, preprocessing, pembobotan TF-IDF, perhitungan Cosine Similarity, kategorisasi kemiripan, dan validasi pakar. Pengujian akhir menggunakan 10 abstrak repositori dan empat abstrak uji. Sistem menghasilkan tiga data berkategori kemiripan tinggi dan satu data berkategori rendah, dengan nilai tertinggi sebesar 92,81%. Validasi pakar menghasilkan Mean Squared Error sebesar 25,6535 dan rata-rata error absolut sebesar 3,7075. Black Box Testing menunjukkan bahwa fungsi utama, meliputi ekstraksi dokumen, perhitungan kemiripan, penyimpanan hasil, pengaturan threshold, validasi pakar, dan pencetakan laporan, berjalan sesuai kebutuhan. SI-KEMA dapat membantu penyaringan awal abstrak, sedangkan keputusan akademik akhir tetap menjadi kewenangan program studi.