Claim Missing Document
Check
Articles

Found 32 Documents
Search

DETEKSI POLA CANDLESTICK MENGGUNAKAN YOLOV8 UNTUK ANALISIS TEKNIKAL BERBASIS CITRA Maulana Manshur; Odi Nurdiawan; Arif Rinaldi Dikananda; Fathurrohman
Integrative Perspectives of Social and Science Journal Vol. 3 No. 04 April (2026): Integrative Perspectives of Social and Science Journal
Publisher : PT Wahana Global Education

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Perkembangan teknologi computer vision dan deep learning telah meningkatkan analisis data keuangan, khususnya dalam pengenalan pola candlestick untuk pengambilan keputusan investasi. Namun, identifikasi pola secara manual cenderung subjektif, tidak konsisten, dan rentan terhadap kesalahan, terutama pada pola dengan kemiripan visual tinggi. Penelitian ini bertujuan mengevaluasi kinerja model YOLOv8 dalam mendeteksi pola candlestick secara otomatis serta menganalisis kemampuannya dalam membedakan pola yang memiliki kemiripan morfologis tinggi. Metode yang digunakan adalah pendekatan kuantitatif eksperimental dengan dataset sebanyak 4.435 citra yang diperoleh dari Roboflow. Model dilatih menggunakan konfigurasi standar YOLOv8 selama 100 epochs. Evaluasi dilakukan menggunakan metrik precision, recall, F1-score, dan mean Average Precision (mAP) pada rentang IoU 0.5–0.95. Hasil penelitian menunjukkan bahwa model mencapai precision 0.877, recall 0.898, F1-score 0.88, dan mAP sebesar 0.903. Model mampu mendeteksi pola dengan baik, namun performa menurun pada pola dengan kemiripan visual tinggi. Dengan demikian, YOLOv8 dinilai efektif untuk pengembangan sistem analisis teknikal berbasis citra yang lebih objektif dan efisien.
Strengthening Civic Education in Elementary Schools Through a Multiple Intelligence Approach Muhammad Allif Adzkal Fata Assidqi; Fathurrohman Fathurrohman
Journal of Contemporary Islamic Primary Education Vol 4 No 3 (2026): April: Quality of Basic Education in the Indonesian context
Publisher : Yayasan Zia Salsabila

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.61253/jcipe.v4i3.469

Abstract

Citizenship Education (PKn) at the elementary school level (SD/MI) plays a strategic role in shaping the character of young citizens grounded in Pancasila values. The challenges of globalization and digitalization demand more adaptive and holistic learning approaches. This article examines the application of Howard Gardner's Multiple Intelligence theory in PKn learning at the SD/MI level as an effort to strengthen the internalization of Pancasila values among students. Through a literature study method, this review explores various previous research to identify the correlation between diverse intelligences and the pedagogical strategies of PKn teachers. The findings indicate that a multiple intelligence approach can accommodate the diversity of student potential, enhance the effectiveness of national values cultivation, and encourage active student engagement in PKn learning. The practical implication of this study is the need for SD/MI teachers to design PKn learning that is responsive to students' multiple intelligences to realize a complete Pancasila Student Profile.