Institution profile

Institut Teknologi Sepuluh Nopember

Academic institutionasia · id
Official website
Research library12linked papers
Opportunities0open roles
Selected work

Representative Papers

GeoSEAN: Explainable Country-Level Image Geolocation for ASEAN Regions

Jul 13, 2026

This study addresses the challenge of visual geolocation in ASEAN countries, where highly similar urban landscapes hinder accurate and interpretable localization. To tackle this issue, the authors propose the first explainable, nation-level image geolocation framework covering all eleven ASEAN nations. The approach integrates CLIP zero-shot classification with LightGBM and MLP classifiers, and introduces a novel multi-dimensional interpretability pipeline combining CLIP attention rollout, YOLOv8 object detection, and Energy-Based Perturbation Games (EBPG) to uncover the key visual cues driving predictions. Experimental results demonstrate that the MLP model achieves 85.91% accuracy and F1 score on the test set while providing object-level fine-grained interpretability, revealing a notable discrepancy between frequently detected objects and regions receiving high attention weights.

0 citationsRead paper

AI for Cultural Heritage Textiles: Fine-Tuned Latent Diffusion for Novel Ulos Motif Synthesis

Jul 06, 2026

This study addresses the limitations of traditional Ulos textile patterns—restricted variety and time-intensive design—which hinder the balance between cultural preservation and contemporary innovation. For the first time, the authors apply fine-tuned latent diffusion models to generate authentic Batak Ulos motifs from Indonesia, optimizing Protogen v3.4 and Stable Diffusion v1.4 on a high-quality dataset. Experimental results demonstrate that Protogen v3.4 substantially outperforms Stable Diffusion v1.4, achieving approximately a 10.5-fold reduction in FID and a two-fold increase in Inception Score. A guidance scale between 5 and 9 emerges as optimal, effectively balancing cultural fidelity with pattern diversity. This work not only enables creative regeneration while preserving cultural symbolism but also systematically elucidates how generation parameters influence the trade-off between fidelity and diversity.

0 citationsRead paper

A Comparative Study of Penalised, Bayesian, Spatial, and Tree-Based Models for Provincial Poverty in Indonesia: Small Samples and High Collinearity

Apr 07, 2026

This study addresses the challenges of analyzing provincial poverty in Indonesia, where a small sample size (n = 34) and high-dimensional multicollinearity undermine the stability of conventional regression models. To tackle this, the authors develop a systematic comparative framework evaluating several regularization and machine learning approaches—including ridge regression, LASSO, elastic net, Bayesian shrinkage priors, spatial ICAR, and Bayesian additive regression trees (BART)—in terms of predictive performance and robustness. The results demonstrate that parametric linear shrinkage methods, particularly ridge regression, yield the most accurate and stable predictions, whereas more complex ensemble models tend to overfit. Notably, ICT skills emerge as a consistently significant negative predictor of poverty across all well-performing models, highlighting their potential as a strategic priority for development policy. This work offers a reliable modeling paradigm and empirical foundation for evidence-based policymaking in data-scarce settings.

0 citationsRead paper
Recent publications

Latest Papers

GeoSEAN: Explainable Country-Level Image Geolocation for ASEAN Regions

Jul 13, 2026

This study addresses the challenge of visual geolocation in ASEAN countries, where highly similar urban landscapes hinder accurate and interpretable localization. To tackle this issue, the authors propose the first explainable, nation-level image geolocation framework covering all eleven ASEAN nations. The approach integrates CLIP zero-shot classification with LightGBM and MLP classifiers, and introduces a novel multi-dimensional interpretability pipeline combining CLIP attention rollout, YOLOv8 object detection, and Energy-Based Perturbation Games (EBPG) to uncover the key visual cues driving predictions. Experimental results demonstrate that the MLP model achieves 85.91% accuracy and F1 score on the test set while providing object-level fine-grained interpretability, revealing a notable discrepancy between frequently detected objects and regions receiving high attention weights.

0 citationsRead paper

AI for Cultural Heritage Textiles: Fine-Tuned Latent Diffusion for Novel Ulos Motif Synthesis

Jul 06, 2026

This study addresses the limitations of traditional Ulos textile patterns—restricted variety and time-intensive design—which hinder the balance between cultural preservation and contemporary innovation. For the first time, the authors apply fine-tuned latent diffusion models to generate authentic Batak Ulos motifs from Indonesia, optimizing Protogen v3.4 and Stable Diffusion v1.4 on a high-quality dataset. Experimental results demonstrate that Protogen v3.4 substantially outperforms Stable Diffusion v1.4, achieving approximately a 10.5-fold reduction in FID and a two-fold increase in Inception Score. A guidance scale between 5 and 9 emerges as optimal, effectively balancing cultural fidelity with pattern diversity. This work not only enables creative regeneration while preserving cultural symbolism but also systematically elucidates how generation parameters influence the trade-off between fidelity and diversity.

0 citationsRead paper

A Comparative Study of Penalised, Bayesian, Spatial, and Tree-Based Models for Provincial Poverty in Indonesia: Small Samples and High Collinearity

Apr 07, 2026

This study addresses the challenges of analyzing provincial poverty in Indonesia, where a small sample size (n = 34) and high-dimensional multicollinearity undermine the stability of conventional regression models. To tackle this, the authors develop a systematic comparative framework evaluating several regularization and machine learning approaches—including ridge regression, LASSO, elastic net, Bayesian shrinkage priors, spatial ICAR, and Bayesian additive regression trees (BART)—in terms of predictive performance and robustness. The results demonstrate that parametric linear shrinkage methods, particularly ridge regression, yield the most accurate and stable predictions, whereas more complex ensemble models tend to overfit. Notably, ICT skills emerge as a consistently significant negative predictor of poverty across all well-performing models, highlighting their potential as a strategic priority for development policy. This work offers a reliable modeling paradigm and empirical foundation for evidence-based policymaking in data-scarce settings.

0 citationsRead paper