Claim Missing Document
Check
Articles

Found 2 Documents
Search

SUSTAINABLE MATERIALS NATURAL COLORS THE SUNGGING WAYANG PROCESS AS A REBRANDING OF THE GENDENG BANGUNJIWO WAYANG ARTISAN COMMUNITY IN BANTUL, YOGYAKARTA Susanto, Moh. Rusnoto; Mariah, Siti; Lukitaningsih, Ambar; Surono, Sugiyarto; Kinanti, Marlita Diyah Wening; Idam, Gabriela; Azis, Septiyan Ibnu; Prasetyo, Haryanto Nur; Damayanti, Fanita; Maulida, Tasya
International Journal of Engagement and Empowerment (IJE2) Vol. 5 No. 3 (2025): International Journal of Engagement and Empowerment
Publisher : Yayasan Education and Social Center

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.53067/ije2.v5i3.239

Abstract

This community service project aims to develop natural dyes (sustainability materials) to support the wayang puppet painting process as a rebranding strategy for the artisan community in Gendeng Hamlet, Bangunjiwo, Bantul, Yogyakarta. The implementation method involves a series of activities carried out through a Participatory Action Research (PAR) approach, involving artisans, academics, and facilitators. The stages include training, mentoring, exploration of local materials (such as Indigofera leaves, tingi bark, and turmeric), and applied trials on wayang puppets. The results of the activities showed an increase in the artisans' capacity in natural dye extraction and application techniques, more aesthetically pleasing and environmentally friendly visual quality of wayang, and the formation of a new community identity with the branding “Wayang Warna Alam” (Natural Color Wayang). This innovation not only increases the added value of wayang products but also strengthens cultural and ecological sustainability and opens up market opportunities in the context of the creative economy.
Performance Evaluation of AdamW, RMSProp, and Nadam Optimizers on EfficientNetB2 Model for Image Data Classification Damayanti, Fanita; Surono, Sugiyarto; Thobirin, Aris
International Journal of Advances in Data and Information Systems Vol. 7 No. 1 (2026): April 2026 - International Journal of Advances in Data and Information Systems
Publisher : Indonesian Scientific Journal

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59395/ijadis.v7i1.1482

Abstract

This study examines the effect of different optimization algorithms on the performance of the EfficientNetB2 model in classifying lung and colon histopathology images. Three commonly used optimizers AdamW, RMSprop, and Nadam were analyzed to compare their influence on convergence trends, classification accuracy, and overall learning consistency. Using a five-class dataset covering benign and malignant tissue samples, the experimental results show that all three optimizers are able to deliver reliable predictions, although with varying performance characteristics. RMSprop emerges as the most effective optimizer, achieving the highest accuracy across all evaluation stages, with 99.05% during training, 99.16% on validation, and 98.72% on testing, along with the lowest loss values. This indicates that RMSprop facilitates faster and more stable convergence compared to the other two methods. AdamW also demonstrates strong predictive performance but shows limitations when distinguishing cancer types with closely similar morphological structures. Nadam attains high accuracy in early stages yet exhibits lower initial stability than RMSprop. Overall, pairing EfficientNetB2 with RMSprop provides the most optimal configuration for this classification task. These results offer valuable insights for designing better training strategies and strengthening the effectiveness of medical imaging based computer aided diagnostic systems.