Jurnal Politeknik Negeri Batam (PoliBatam)
Not a member yet
3001 research outputs found
Sort by
Pembuatan Animasi Aset 3D dalam Film Pendek Gugu si Gonggong Ajaib sebagai Media Promosi UMKM Menggunakan Blender 3D
No full textThe development of digital technology opens up new opportunities for Micro, Small, and Medium Enterprises (MSMEs) to increase their competitiveness through 3D animation-based promotional media. This study aims to design and animate 3D assets in the short film "Gugu si Gonggong Ajaib" as a promotional media for MSMEs in the Riau Islands using Blender 3D software. The research method used is a qualitative method with a product design approach, which consists of three main stages, namely pre-production, production, and post-production. In the pre-production stage, story idea development, storyboard creation, character design, and environmental design are carried out. The production stage includes modeling, texturing, rigging, animation, lighting, and rendering of 3D assets. While the post-production stage includes compositing and video editing. The result of the study is a 1 minute 13 second animated video with a resolution of 1920 × 1080 pixels (Full HD), which displays local characters with an attractive visual approach to support MSME product promotion. The application of 3D animation has been proven to increase visual appeal, strengthen product image, and expand the reach of digital promotions. This research is expected to be a reference for MSMEs and digital content creators in utilizing 3D animation as an innovative promotional medium.Perkembangan teknologi digital membuka peluang baru bagi pelaku Usaha Mikro, Kecil, dan Menengah (UMKM) untuk meningkatkan daya saing melalui media promosi berbasis animasi 3D. Penelitian ini bertujuan untuk merancang dan menganimasikan aset 3D dalam film pendek "Gugu si Gonggong Ajaib" sebagai media promosi UMKM Kepulauan Riau menggunakan perangkat lunak Blender 3D. Metode penelitian yang digunakan adalah metode kualitatif dengan pendekatan perancangan produk, yang terdiri dari tiga tahapan utama, yaitu pra-produksi, produksi, dan pasca-produksi. Pada tahap pra-produksi dilakukan pengembangan ide cerita, pembuatan storyboard, desain karakter, serta desain lingkungan. Tahap produksi meliputi modeling, texturing, rigging, animasi, lighting, dan rendering aset 3D. Sedangkan tahap pasca-produksi mencakup compositing dan editing video. Hasil penelitian berupa video animasi berdurasi 1 menit 13 detik dengan resolusi 1920 × 1080 piksel (Full HD), yang menampilkan karakter lokal dengan pendekatan visual menarik untuk mendukung promosi produk UMKM. Penerapan animasi 3D terbukti dapat meningkatkan daya tarik visual, memperkuat citra produk, serta memperluas jangkauan promosi secara digital. Penelitian ini diharapkan dapat menjadi referensi bagi pelaku UMKM dan kreator konten digital dalam memanfaatkan animasi 3D sebagai media promosi inovatif
PENGARUH KURIKULUM PEMODELAN 3D TERINTEGRASI AI PADA PEMAHAMAN ANAK USIA 10-12 TAHUN DI DIGIKIDZ
No full textThe growing dominance of digital technology presents a significant challenge for the younger generation, who must be well-prepared to face it. Early exposure to digital skills is essential to equip children with the necessary knowledge and capabilities. One such emerging field is 3D modeling, which has seen rapid development in recent years. Through the learning process of 3D modeling, students can enhance their cognitive abilities, creative thinking, and critical problem-solving skills. This study aims to analyze the effectiveness of a 3D modeling curriculum in improving the understanding of children aged 10–12. A comparative approach is used to determine which curriculum demonstrates a higher level of effectiveness. The research employs a mixed-methods approach, combining both qualitative and quantitative data, to obtain more accurate and comprehensive findings.Tantangan manusia terhadap dunia modern akan dominasi kemajuan teknologi digital semakin nyata di depan mata. Hal ini tak terpungkiri oleh generasi muda sekarang yang akan menghadapinya. Untuk itu diperlukan persiapan matang pada insan muda dengan pembekalan wawasan dan kemampuan di bidang digital sejak dini. Bidang digital seperti pemodelan 3D sudah mulai berkembang pesat. Melalui proses pembelajaran pemodelan 3D, peserta didik dapat mengembangkan kemampuan kognitif, kreativitas ide hingga berpikir lebih kritis terhadap masalah yang dihadapi. Dan melalui penelitian ini, kurikulum akan dianalisis kefektifannya dalam tingkat pemahaman anak-anak usia 10-12 tahun dan dilakukan perbandingan untuk mengetahui kurikulum dengan nilai efektifitas yang lebih tinggi. Penelitian melibatkan metode kombinasi yaitu dari penelitian kualitatif dan penelitian kuantitatif guna mencapai hasil analisis lebih akurat
Prediction of Nile Tilapia (Oreochromis niloticus) Harvest Yield in Brackishwater Pond Aquaculture Using XGBoost
No full textNile tilapia aquaculture is one of the aquaculture subsectors with significant development potential. However, the productivity of Nile tilapia cultured in brackishwater ponds is often constrained by variability in technical factors such as the number of fingerlings stocked, pond area, stocking density, land status, planting season, and feed quantity. To address these challenges, a predictive model based on machine learning was developed. Data were collected through field observations and interviews with Nile tilapia farmers in Wanantara, Sindang, Indramayu. The data were then processed using label encoding and normalization techniques. The dataset was divided into 80% for training and 20% for testing. XGBoost, Random Forest, and Support Vector Regression algorithms were trained using hyperparameter tuning and five-fold cross-validation, and evaluated using RMSE and R² metrics. The results show that XGBoost achieved the best performance (R² = 0.9798 and RMSE = 442.05 kg), followed by Random Forest (R² = 0.955 and RMSE = 679.742 kg) and SVR (R² = 0.888 and RMSE = 1065.367 kg)
Analysis of the Impact of Lateral Stock Transfers in Distribution Network with a Central Warehouse and Two Storage Points
No full textOur study, Analysis of the impact of lateral Transfers in a stock distribution system with a central warehouse and two stocking points, aims to analyze the effet of lateral stock transfers between the two stocking points on minimizing the total inventory management cost system, retailers manage their inventories according to the (R,S) policy. This study also examines the service level and the stockout rate resulting from the implementation of lateral stock transfers. Each point i (i=1,2) manages its inventory independently in order to meet the consomer demand yi. Each stocking point has a maximun inventory level Si , when customer demand is less than or equal to the reorder point si , an order of quantity Qi= Si-si is placed with the central warehouse. This quantity is delivered after a known lead time Li. If the delivery lead time is too long, stocking point i may request a lateral transfer of quantity Xji from stocking point j, which has excess inventory, in order to avoid a stockout. The originality of this publication stems from the implementation of a numerical application using MATLAB, which allowed us to conduct this analysis
Aspect-Based Sentiment Analysis of Tourist Attractions in Labuanbajo Using the Transformer Model as a Recommendation for Improving Service Quality
No full textLabuan Bajo as super-priority destinations experience improvement visit in a number of year lastly, however quality service Not yet fully fulfil expectation tourists . Study This analyze perception traveler through Aspect-Based Sentiment Analysis (ABSA) approach using the IndoBERT model. A total of 2,564 reviews multilingual from Google Maps and TripAdvisor processed through translation, pre-processing, extraction aspects, sentiment labels automatic, and model training. Four aspects analyzed based on framework SERVQUAL theory and Tourism Destination Quality: attractions, amenities, accessibility, and price. Model evaluation was conducted using precision, recall, and F1-score per aspect. The results show performance best The amenity and attraction aspects obtained the highest and most consistent scores across all metrics (around 0.83–0.88), indicating that reviews for these two aspects were more explicit and easily mapped by the model. In contrast, the access and price aspects showed lower scores (around 0.65–0.72), indicating linguistic challenges such as implicit aspects, variations in the context of the travel experience, and figurative complaints . The study This give recommendation policy connected data based direct with model findings. Limitations such as translation noise, biased datasets dominated by review positive-neutral, and not existence baseline comparison also discussed. These results confirm that ABSA approach can help stakeholder’s policy, however Still need improvement through other models such as IndoBERTweet, mBERT, or IndoBART.Labuan Bajo as super-priority destinations experience improvement visit in a number of year lastly, however quality service Not yet fully fulfil expectation tourists . Study This analyze perception traveler through Aspect-Based Sentiment Analysis (ABSA) approach using the IndoBERT model. A total of 2,564 reviews multilingual from Google Maps and TripAdvisor processed through translation, pre-processing, extraction aspects, sentiment labels automatic, and model training. Four aspects analyzed based on framework SERVQUAL theory and Tourism Destination Quality: attractions, amenities, accessibility, and price. Model evaluation was conducted using precision, recall, and F1-score per aspect. The results show performance best The amenity and attraction aspects obtained the highest and most consistent scores across all metrics (around 0.83–0.88), indicating that reviews for these two aspects were more explicit and easily mapped by the model. In contrast, the access and price aspects showed lower scores (around 0.65–0.72), indicating linguistic challenges such as implicit aspects, variations in the context of the travel experience, and figurative complaints . The study This give recommendation policy connected data based direct with model findings. Limitations such as translation noise, biased datasets dominated by review positive-neutral, and not existence baseline comparison also discussed. These results confirm that ABSA approach can help stakeholder’s policy, however Still need improvement through other models such as IndoBERTweet, mBERT, or IndoBART
Indobert-Based Sentiment Analysis of Political Discourse on Platform X: The Case Of Prabowo-Gibran Administration
No full textThe 2024 Indonesian presidential election inaugurated the Prabowo Subianto–Gibran Rakabuming Raka administration, whose early performance has been widely discussed on digital social networks, particularly X (Twitter). This study evaluates public sentiment toward the administration\u27s performance up to June 30, 2025 using an IndoBERT-based text classification approach. A total of 2,612 public posts were collected via web scraping and processed through text preprocessing steps (noise removal, slang correction, normalization, and lemmatization). The data were labeled into three sentiment classes (positive, neutral, and negative) and split into training, validation, and test sets (2,092 / 418 / 105). The fine-tuned IndoBERT model achieved an overall test accuracy of 0.78, with the highest F1-score on the negative class (0.82), followed by neutral (0.76) and positive (0.75). The confusion matrix indicates that neutral posts are more frequently confused with positive posts, suggesting that neutral sentiment remains harder to separate in politically nuanced and noisy social-media text. This study also compares IndoBERT with a traditional baseline (TF-IDF + SVM using polynomial kernel). Results show that IndoBERT (78% accuracy) significantly outperforms SVM (72.19%), particularly in detecting negative sentiment (F1: 0.82 vs 0.72), demonstrating superior contextual understanding of politically nuanced text. This work also highlights methodological and ethical considerations for political opinion mining, including representativeness limits of X users and privacy-preserving handling of public posts. Future work should expand the dataset, address class imbalance, and explore additional transformer-based architectures to strengthen generalizability and benchmarking.The 2024 Indonesian presidential election inaugurated the Prabowo Subianto–Gibran Rakabuming Raka administration, whose early performance has been widely discussed on digital social networks, particularly X (Twitter). This study evaluates public sentiment toward the administration\u27s performance up to June 30, 2025 using an IndoBERT-based text classification approach. A total of 2,612 public posts were collected via web scraping and processed through text preprocessing steps (noise removal, slang correction, normalization, and lemmatization). The data were labeled into three sentiment classes (positive, neutral, and negative) and split into training, validation, and test sets (2,092 / 418 / 105). The fine-tuned IndoBERT model achieved an overall test accuracy of 0.78, with the highest F1-score on the negative class (0.82), followed by neutral (0.76) and positive (0.75). The confusion matrix indicates that neutral posts are more frequently confused with positive posts, suggesting that neutral sentiment remains harder to separate in politically nuanced and noisy social-media text. This study also compares IndoBERT with a traditional baseline (TF-IDF + SVM using polynomial kernel). Results show that IndoBERT (78% accuracy) significantly outperforms SVM (72.19%), particularly in detecting negative sentiment (F1: 0.82 vs 0.72), demonstrating superior contextual understanding of politically nuanced text. This work also highlights methodological and ethical considerations for political opinion mining, including representativeness limits of X users and privacy-preserving handling of public posts. Future work should expand the dataset, address class imbalance, and explore additional transformer-based architectures to strengthen generalizability and benchmarking
A SEIR Metapopulation Model for Mpox Transmission Dynamics in the DRC
No full textUnderstanding the mechanisms of infectious disease spread is a fundamental prerequisite for any control, management, or eradication strategy. This understanding relies on the rigorous integration of biological knowledge, mathematical tools, and computational resources, which enable in-depth analysis, the formulation of approximate numerical solutions, and the simulation of the temporal evolution of the pathological phenomenon. In this study, we develop an SEIR-type compartmental model to represent the transmission dynamics of Mpox, taking into account a metapopulation structure between two interconnected geographical areas, designated as patches 1 and 2. This model allows us to integrate the effects of interregional mobility on the spread of infection. The SageMath environment (version 9.3) was used to simulate viral dynamics within each patch, incorporating migration flows between the two regions. The system equilibria were determined and adjusted based on available data. The analysis focused on calculating the basic reproduction number, studying the stability of equilibria, and evaluating parameter sensitivity. The results suggest a gradual extinction of the disease in both patches, under certain conditions relating to mobility and recovery rates. Finally, this investigation highlights the relevance of SageMath software as a powerful tool for exploring and simulating spatially structured epidemiological models, with the ability to adapt to a variety of contexts and pathologies
Enhanced Multi-Objective Green Vehicle Routing with a New Fuzzy Speed-Driven Fuel Consumption Model
No full textToday, decision-makers begun to prioritize the concept of green logistics, which is based on strategies aimed to promote more environmentally sustainable practices during vehicle routing. Among key factors influencing fuel consumption in such problems, vehicle speed plays a crucial role. This article adapts the Comprehensive Modal Emission Model (CMEM) for fuel consumption by treating vehicle speed as a fuzzy variable. This enhanced version, referred as Fuzzy-CMEM, enables the formulation of a more realistic fuzzy multi-objective Green Vehicle Routing Problem (GVRP). The proposed methodology follows four main steps. First, we formulate the problem considering the vehicle speed as a fuzzy variable. Second the initial fuzzy problem is defuzzified using the interval approximation approach. Third, a sequential approach is adopted where the sweep heuristic is used to construct feasible routes, and the BicriterionAnt metaheuristic is employed to generate optimal Pareto-front solutions of the resulting deterministic problem. Finally, a numerical simulation is addressed, followed by a comparative analysis of results and discussion
Transformer-based Models for Cardiovascular Disease Predictions from Electronic Health Records: A Systematic Review
No full textThis systematic literature review (SLR) analyses 16 studies published between 2020 and 2025 that applied transformer-based or other machine learning models to predict cardiovascular disease (CVD) using electronic health records (EHRs). Following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines, the review ensures transparency in the identification, screening, and quality appraisal of eligible studies. The key findings reveal a rapid shift from traditional machine learning models, such as Random Forest, toward transformer architectures like the Bidirectional Encoder Representation from Transformers for Electronic Health Record (BEHRT) and its variants. These models demonstrate a superior discrimination (Area Under Curve:0.84 to 0.93) due to their capacity to model long-term temporal dependencies. Explainable AI (XAI) tools, such as attention visualisation, were frequently employed, yet clinical interpretability and integration into decision support remain underexplored. The review also highlights opportunities in federated and privacy-preserving learning, multimodal data fusion, and hybrid architectures that integrate transformers with traditional machine learning methods. This review addresses a gap in the past literature by being the first SLR to compare transformer variants for the prediction of CVDs. Other SLRs examined general CVD risk models, but the present SLR analyses interpretability, external validation and methodological limitations to transformer models. The findings of the recent SLR reported challenges that include data-shift limitations, model-poor population generalisation and their limitations to clinical adoption, which highlights the need for more evaluation protocols and clinicians’ interpretability frameworks
Multi-Agent Retrieval Augmented Generation for Clinical Decision Support: A Systematic Review and Integrative Conceptual Framework
No full textMulti agent retrieval augmented generation (RAG) systems are increasingly explored as advanced architectures for clinical decision support combining information retrieval, reasoning and verification through coordinated agent interactions. This study systematically reviews applications of agentic and multi agent RAG in clinical decision support systems (CDSS) and synthesizes an integrative conceptual framework linking technical design to technology adoption considerations. Following PRISMA guidelines, searches were conducted from PubMed, IEEE Xplore and ScienceDirect using structured Boolean strings combining terms for multi agent architectures, RAG and CDSS.The search yielded 12 studies published between 2020 and 2025 that met the inclusion criteria. The review synthesises evidence on multi agent role configurations retrieval and reasoning strategies, verification mechanisms and reported clinical contexts. Across studies, dominant challenges include data and corpus limitations retrieval quality dependency, limited clinical validation and computational overhead, alongside governance concerns such as privacy, bias and accountability. Building on the synthesis, we propose a four-agent CDSS framework retriever, reasoner, verifier, safety and map its deployment determinants to Technology Acceptance Model constructs perceived usefulness, perceived ease of use, trust and diffusion of Innovations attributes. The review concludes with design-oriented recommendations for safer, explainable, and adoption-ready multi-agent RAG CDSS, particularly for low-resource contexts