Claim Missing Document
Check
Articles

Found 2 Documents
Search

Peningkatan Kompetensi Guru Dalam Menghadapi Era Pembelajaran Berbasis Kecerdasan Buatan Untuk Guru Sekolah Guang-Ming Ratnadewi, Ratnadewi; Hangkawidjaja, Aan Darmawan; Andrianto, Heri; Prijono, Agus; Susanthi, Yohana; Fahlevi, Annisa Maizano; Sari, Puji Nabila; Rajagukguk, Meria Anisa; Tobing, Elisa Magdalena L.; Santoso, Andrew Jonathan Setio; Silaban, Indrawati; Sugiarto, Yossep
Abdimas Mandalika Vol 5, No 1 (2025): November
Publisher : Universitas Muhammadiyah Mataram

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31764/am.v5i1.33846

Abstract

Abstract:  As artificial intelligence technology advances, teachers must become more proficient in addressing existing issues. Therefore, the goal of this program is to increase teachers' ability to meet the opportunities and challenges presented by the artificial intelligence-based learning era. As technology advances quickly, educators must become more creative, adaptable, and digitally literate, particularly when it comes to incorporating AI into the classroom. Kindergarten, elementary, middle, and high schools in the cities of Jakarta, Surabaya, Pekanbaru, and Jambi are overseen by the Pancaran Metta Paramita PKBM Foundation Guang Ming. Teachers at Guang Ming's school served as training participants in the creation of learning resources, the creation of questions, and the analysis of student work. The activity was carried out through the use of Participatory Action Research (PAR), in which participants received instruction and helpers to aid in their learning as they practiced. According to questionnaire results, participants felt that the PKM's content was in line with their needs, that the implementation period was excellent, that the speakers' content was excellent, that the participants understood the material, and that the PKM activity space was sufficient, receiving a very good rating of between 71.4% and 90.5%.Abstrak: Seiring kemajuan teknologi kecerdasan buatan, guru harus menjadi lebih mahir dalam mengatasi masalah yang ada. Oleh karena itu, tujuan pengabdian ini adalah untuk meningkatkan kemampuan guru untuk memenuhi peluang dan tantangan yang disajikan oleh era pembelajaran berbasis kecerdasan buatan. Seiring kemajuan teknologi dengan cepat, para pendidik harus menjadi lebih kreatif, mudah beradaptasi, dan melek secara digital, terutama ketika datang untuk memasukkan AI ke dalam kelas. TK, SD, SMP, dan SMU di Kota Jakarta, Surabaya, Pekanbaru, dan Jambi diawasi oleh Yayasan Pancaran Metta Paramita PKBM Guang Ming. Guru di Sekolah Guang Ming menjabat sebagai peserta pelatihan dalam penciptaan sumber belajar, penciptaan pertanyaan, dan analisis pekerjaan siswa. Metode yang digunakan Participatory Action Research (PAR), di mana peserta menerima instruksi dan pembantu untuk membantu dalam pembelajaran mereka saat mereka berlatih. Menurut hasil kuesioner, peserta merasa bahwa konten PKM sejalan dengan kebutuhan mereka, bahwa periode implementasi sangat baik, bahwa konten pembicara sangat baik, bahwa para peserta memahami materi tersebut, dan bahwa ruang aktivitas PKM sudah cukup, menerima peringkat yang sangat baik antara 71,4% dan 90,5%.
Evaluasi Segmentasi Otak dan Prediksi Overall Survival pada Dataset BRATS 2020 Fahlevi, Annisa Maizano; Saragih, Riko
Journal of Smart Technology and Engineering Vol. 2 No. 1 (2026)
Publisher : Universitas Kristen Maranatha

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.28932/jste.v2i1.13880

Abstract

Overall survival (OS) assessment in glioma patients is a crucial component of MRI-based medical image analysis, as OS estimation directly influences clinical decision-making and treatment planning. One of the central challenges in developing image-based predictive models lies in the dependency on accurate tumor segmentation. This study aims to construct an MRI-based OS prediction model using the Brain Tumor Segmentation 2020 (BraTS 2020) dataset by incorporating two types of masked images: ground truth masks and automatically generated predicted masks derived from a 3D U-Net segmentation model. OS classification was grouped into three categories (< 10 months, 10–15 months, and > 15 months). The predictive model achieved an accuracy of 0.9792 when using ground truth masks and 0.9583 when using predicted masks. These findings suggest that a fully automated deep-learning–based segmentation pipeline can approximate the performance of manual segmentation and holds strong potential for large-scale clinical applications where manual annotation is impractical.