Claim Missing Document
Check
Articles

Found 2 Documents
Search

Peningkatan kompetensi guru dalam literasi digital melalui program “fun learning koding” Irma Darmayanti; Debby Ummul Hidayah; Tyas Pratama Puja Kusuma; Tarwoto Tarwoto; Sitaresmi Sitaresmi; Wahyu Handani
SELAPARANG: Jurnal Pengabdian Masyarakat Berkemajuan Vol 10, No 2 (2026): April
Publisher : Universitas Muhammadiyah Mataram

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31764/jpmb.v10i2.38871

Abstract

Abstrak Perkembangan teknologi informasi yang pesat menuntut peningkatan literasi digital, terutama bagi generasi muda dan para pendidik sebagai ujung tombak pembelajaran. Namun, banyak guru di Indonesia masih menghadapi tantangan dalam memahami literasi digital dan koding, serta kesulitan mengintegrasikan teknologi ke dalam pembelajaran. Untuk mengatasi masalah ini, Universitas Amikom Purwokerto bekerja sama dengan MGMP Informatika MTs Ma’arif NU Kabupaten Banyumas melaksanakan program pelatihan “Fun Learning Koding” pada tanggal 4 September 2025 di RM Rawalo. Program ini bertujuan untuk meningkatkan kompetensi guru dalam literasi digital dan koding melalui pendekatan hands-on learning menggunakan platform MIT App Inventor. Pelatihan diikuti oleh 18 guru dan mencakup empat tahap utama: survey awal, persiapan, pelaksanaan, serta evaluasi. Hasil evaluasi menunjukkan peningkatan signifikan dalam pemahaman guru tentang literasi digital dan koding, dengan skor rata-rata meningkat dari 55–60 (pre-test) menjadi 85–90 (post-test). Selain itu, 95% peserta menyatakan bahwa pelatihan ini relevan dengan kebutuhan mereka dan dapat langsung diterapkan dalam pembelajaran. Output kegiatan meliputi modul pelatihan, prototipe aplikasi edukatif sederhana, serta rencana tindak lanjut berupa pelatihan lanjutan oleh MGMP Informatika. Kegiatan ini berhasil meningkatkan keterampilan guru, mendorong kreativitas dalam menciptakan media pembelajaran digital, dan membangun komunitas belajar antar guru. Untuk meningkatkan efektivitas program serupa di masa mendatang, disarankan untuk menambah durasi pelatihan, menyediakan infrastruktur tambahan, serta memberikan pendampingan pasca-pelatihan. Diharapkan program ini dapat dikembangkan lebih luas untuk mendukung transformasi pendidikan di era digital. Kata kunci: pelatihan; literasi digital; peningkatan kompetensi; fun learning koding; hands-on learning Abstract The rapid development of information technology demands an increase in digital literacy, especially for the younger generation and educators as the spearhead of learning. However, many teachers in Indonesia still face challenges in understanding digital literacy and coding, as well as difficulties in integrating technology into learning. To address this issue, Amikom University Purwokerto collaborated with MGMP Informatika MTs Ma'arif NU Banyumas Regency to conduct a “Fun Learning Coding” training program on September 4, 2025, at RM Rawalo. This program aimed to improve teachers' competence in digital literacy and coding through a hands-on learning approach using the MIT App Inventor platform. The training was attended by 18 teachers and consisted of four main stages: initial survey, preparation, implementation, and evaluation. The evaluation results showed a significant increase in teachers' understanding of digital literacy and coding, with the average score increasing from 55–60 (pre-test) to 85–90 (post-test). In addition, 95% of participants stated that the training was relevant to their needs and could be directly applied in learning. The outputs of the activity included training modules, simple educational application prototypes, and a follow-up plan in the form of further training by the Informatics MGMP. This activity succeeded in improving teachers' skills, encouraging creativity in creating digital learning media, and building a learning community among teachers. To increase the effectiveness of similar programs in the future, it is recommended to increase the duration of training, provide additional infrastructure, and provide post-training assistance. It is hoped that this program can be developed more broadly to support educational transformation in the digital era. Keywords: training; digital literacy; competency improvement; fun learning coding; hands-on learning
Klasifikasi Penyakit Tanaman Cabai Rawit Menggunakan CNN Berbasis MobileNetV2 dan SE-Attention Tarwoto Tarwoto; Nur Fadhilah; Indri Vitriana; Eldas Puspitarini; Fira Nur Zianti
Jurnal Ilmu Komputer dan Teknologi Informasi Vol. 3 No. 2 (2026): September
Publisher : Lembaga Penelitian dan Pengabdian Kepada Masyarakat (LPPM) STMIK Indonesia Banda Aceh

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.63447/jikti.v3i2.2037

Abstract

Diseases affecting bird's eye chili (Capsicum frutescens L) leaves are a primary cause of reduced harvest productivity. A major challenge in implementing deep learning-based automated detection systems is the drop in accuracy during cross-domain testing, where smartphone images captured in the field contain complex background noise compared to laboratory datasets. This study proposes an SE-MobileNetV2 architecture that integrates a Squeeze-and-Excitation (SE) module to enhance cross-domain classification robustness while maintaining memory efficiency for mobile devices. Testing was conducted on 675 cross-domain images (200 from a Kaggle benchmark dataset and 75 smartphone photos) categorized into five leaf condition classes. Experimental results demonstrate that SE-MobileNetV2 achieved the highest overall accuracy at 91.27%, with a weighted average precision of 92.09%, recall of 91.27%, and F1-score of 91.41%. These results outperform the standard MobileNetV2 (90.55% accuracy) and significantly surpass the VGG16 model (84.00% accuracy). Integrating the channel attention mechanism proved effective in mitigating background interference from soil and shadows, thereby boosting precision for the "Spot" class to 84.75% and the "Whitefly" class to 100.00%. Regarding computational efficiency, SE-MobileNetV2 requires only ~14.8 MB of memory, making it far more compact than VGG16 (~528 MB). Thus, SE-MobileNetV2 achieves an optimal balance between robust field accuracy and file size efficiency, making it an ideal model for offline implementation on farmers' smartphones.