Dian Puteri Ramadhani

Eucalyptus pellita is a key species in Indonesia’s pulp and paper industry. However, it remains vulnerable to various foliar diseases, including Xanthomonas infections and pest infestations, particularly those caused by leaf roller caterpillars, which significantly reduce nursery productivity. This study presents a leaf disease classification system utilizing a Convolutional Neural Network (CNN) based on the MobileNet architecture and a transfer learning approach. A dataset of 600 images was compiled and categorized into three classes: healthy leaves, Xanthomonas-infected leaves, and caterpillar-damaged leaves. The dataset was divided into training (80%), testing (10%), and validation (10%) subsets. Multiple hyperparameter configurations were tested, with the optimal performance achieved using a learning rate of 0.0001, 20 training epochs, a batch size of 32, and the Adam optimizer. The resulting model achieved 97.29% training accuracy and 100% accuracy on both the validation and testing sets, demonstrating strong reliability in detecting leaf diseases. These findings provide a solid foundation for the development of technology-assisted disease management tools to support agronomic decision-making and agricultural extension services.

The growing beauty industry requires efficient management tools for Makeup Artist (MUA) teams, who often face operational challenges due to the use of manual or non-integrated digital tools. This study contributes by providing an integrated, mobile-first workflow that directly links bookings, schedules, and financial records with role-based access and automated reminders, reducing fragmentation from manual or separate tools and offering consolidated insights for MUAs’ decision-making. The application's quality was validated through Black-Box testing, achieving a 100% success rate across 35 functional test cases that covered all main features. Usability was then evaluated in a case study with a professional MUA and two team members (N=3) who used the application for one week before completing the Computer System Usability Questionnaire (CSUQ). The results yielded an overall mean score of 6.52 out of 7, indicating very high user satisfaction, with subscale scores showing that users found the system both helpful and easy to navigate. Future development may include expanding the dashboard's analytical capabilities or integrating a direct client payment gateway.

Lecture scheduling is a complex and essential task in academic settings, particularly for optimizing the use of resources such as classrooms, time slots, and teaching staff. This study developed a web-based lecture scheduling application using a genetic algorithm for the Faculty of Engineering, University of Riau. Genetic algorithms were selected due to their effectiveness in solving complex optimization problems and producing efficient solutions in a relatively short time. The application successfully generated conflict-free schedules that met the faculty’s requirements, encompassing 634 courses, 345 lecturers, 38 classrooms, and 12 study programs. The best outcome was achieved in test 7, with a population size of 40, 100 generations, 75% crossover probability, 10% mutation probability, a fitness value of 1, and a generation time of approximately 5 hours and 8 minutes. These results demonstrate the potential of genetic algorithms to streamline the scheduling process, reduce administrative workload, and enhance operational efficiency. This research offers a practical tool for academic institutions and highlights the real-world applicability of advanced computational methods in education management.

Background: Higher education institutions face information fragmentation and cognitive overload as students struggle to access learning materials scattered across multiple digital platforms. Large Language Models encounter hallucination issues and static knowledge bases, limiting their educational application.Aims: This research aims to design and evaluate a Retrieval Augmented Generation (RAG)-based chatbot system integrated with Learning Management Systems to address information fragmentation in educational environmentsMethods: We employed Design Science Research Methodology (DSRM) to develop the RAG-based chatbot. Technology Acceptance Model (TAM) assessment with 267 undergraduate students and semi-structured interviews with five faculty members evaluate user acceptance and pedagogical perspectives.Results: The RAG chatbot achieved strong initial user acceptance (mean score 4.097). Students valued perceived usefulness over ease of use, with high usage intentions and recommendation willingness. Faculty recognized pedagogical value while emphasizing quality assurance needs.Conclusion: This exploratory study demonstrates technical feasibility and baseline user acceptance for RAG-based chatbots in education, showing promise for addressing information accessibility challenges. Demonstration-based evaluation requires validation through longitudinal field studies.

Digital transformation in public services has emerged as an urgent necessity to enhance operational efficiency and effectiveness across various levels of government. Sukagalih Village, located in Tarogong Kidul District, Garut Regency, with a population of 17,145 residents and 12,000 households, faces complex challenges in public service delivery. The primary issues encompass manual administrative systems that cause operational inefficiencies, challenges in tracking demographic data for social assistance and community empowerment programs, and fragmented regional monographic data that hinders data-driven decision-making. Additional challenges including risks of illegal levies and lack of transparency in public services further reinforce the urgency for digital solution implementation. This research aims to develop an integrated digital public service ecosystem that incorporates administrative service management information systems and geospatial-based analytics dashboards in Sukagalih Village. The system development approach follows the System Development Life Cycle (SDLC) framework with the Scrum methodology, involving village officials participatively throughout each development stage. The system is designed reduce physical office visits, featuring document upload capabilities through digital platforms and analytics dashboards for empowerment program monitoring. The implementation of this digital ecosystem is expected to reduce administrative document processing time, improve the accuracy of regional monographic data with precise geospatial coordinates, minimize illegal levy practices, and enhance transparency and accountability in public services. The research outcomes are projected to serve as a smart village model that can be adopted by other villages or sub-districts in realizing transparent, accountable, and data-driven governance.

Feminacare, a women's health consultation application with a chatbot, previously used the LSTM model, which had an accuracy of 61% but often gave less relevant responses. This research proposes the use of the SeaLLM model with the Retrieval-Augmented Generation (RAG) approach to improve the accuracy of the chatbot. Based on three trials in the evaluation of 120 questions, the chatbot obtained a mean accuracy of 87%, with a precision of 93%, recall of 89%, and F1-score of 91%. Compared to previous models, this approach produced more relevant and accurate responses. Overall, this research proves that the application of SeaLLM with RAG can improve the effectiveness of chatbots in providing women's health information. However, further improvements are still needed, especially in handling more complex questions by expanding the dataset.

The growth of the tourism industry in Southeast Asia, particularly in Indonesia, Thailand, and Vietnam, establishes the region as a leading global tourism destination. Numerous studies have explored tourist behavior within specific regions. However, the question of whether tourists’ experience perceptions differ based on their cultural backgrounds is still insufficiently addressed. Previous articles suggest that an individual’s cultural background plays a significant role in shaping tourist values and expectations. This study investigates how tourists’ cultural backgrounds, represented by their geographical regions of origin, impact their entertainment experiences, sentiments, and mobility patterns across the three countries. We gathered 387,010 TripAdvisor reviews and analyzed them using a combination of advanced text mining techniques and network analysis to map tourist mobility patterns. Comparing sentiments and behaviors across cultural backgrounds, this study found that entertainment preferences vary by origin. The network analysis reveals distinct exploration patterns: diverse and targeted exploration. Vietnam achieves the highest satisfaction across the cultural groups through balanced development, while Thailand’s integrated entertainment creates cultural divides, and Indonesia’s generates moderate satisfaction regardless of cultural background. This study contributes to understanding tourism dynamics in Southeast Asia through a data-driven, comparative analysis of tourist behaviors. The findings provide insights for destination management, marketing strategies, and policy development, highlighting the importance of tailoring tourism offerings to meet the diverse preferences of visitors from different global regions.

Riau Batik, a treasured cultural heritage, faces challenges in its preservation due to limited public awareness of its unique motifs. This research aims to bridge the knowledge gap by developing a website-based classification system that can identify and recognize Riau batik patterns, offering round-the-clock accessibility to users. By leveraging the Convolutional Neural Network (CNN) algorithm, the classification system was trained using a dataset of 1,440 images. The model was fine-tuned through optimization of batch size and epoch parameters to maximize classification accuracy. The training process culminated in a model with an accuracy of 89%, achieved using a batch size of 16 and 50 epochs. This system seeks to elevate public appreciation and knowledge of Riau Batik, thereby contributing to the preservation of its cultural and historical significance. The accessible classification tool presents a practical approach to ensuring the motifs and legacy of Riau Batik are preserved for future generations. The proposed CNN-based model demonstrates the potential to enhance digital engagement with traditional culture through modern technology, facilitating widespread recognition and appreciation of Riau's rich batik heritage.

The tourism sector plays a crucial role in the global economy, encompassing both physical infrastructure and cultural engagement. Indonesia has a wide range of attractions and has experienced remarkable growth, with Bali as a notable example of this. With the rapid advancements in technology, travelers now have the freedom to explore independently, while online travel agencies (OTAs) serve as important resources. Reviews from tourists significantly impact the service quality and perception of destinations, and text mining is a valuable tool for extracting insights from unstructured review data. This research integrates multiclass text classification and a network analysis to uncover tourists’ behavioral patterns through their perceptions and movement. This study innovates beyond conventional sentiment and cognitive image analysis to the tourists’ perceptions of cognitive dimensions and explores the sentiment correlation between different cognitive dimensions. We find that destinations generally receive positive feedback, with 80.36% positive reviews, with natural attractions being the most positive aspect while infrastructure is the least positive aspect. We highlight that qualitative experiences do not always align with quantitative cost-effectiveness evaluations. Through a network analysis, we identify patterns in tourist mobility, highlighting three clusters of attractions that cater to diverse preferences. This research underscores the need for tourism destinations to strategically adapt to tourists’ varied expectations, enhancing their appeal and aligning their services with preferences to elevate destination competitiveness and increase tourist satisfaction.

The future of the internet is moving toward decentralization, with decentralized networks and blockchain technology playing essential roles in different sectors. Decentralized networks offer equality, accessibility, and security at a societal level, while blockchain technology guarantees security, authentication, and openness. Integrating blockchain technology with decentralized characteristics has become increasingly significant in finance; we call this “decentralized finance” (DeFi). As of January 2023, the DeFi crypto market capitalized USD 46.21 billion and served over 6.6 million users. As DeFi continues to outperform traditional finance (TradFi), it provides reduced fees, increased inclusivity, faster transactions, enhanced security, and improved accessibility, transparency, and programmability; it also eliminates intermediaries. For end users, DeFi presents asset custody options, peer-to-peer transactions, programmable control features, and innovative financial solutions. Despite its rapid growth in recent years, there is limited comprehensive research on mapping DeFi’s benefits and risks alongside its role as an enabling technology within the financial services sector. This research addresses these gaps by developing a DeFi classification system, organizing information, and clarifying connections among its various aspects. The research goal is to improve the understanding of DeFi in both academic and industrial circles to promote comprehension of DeFi taxonomy. This well-organized DeFi taxonomy aids experts, regulators, and decision-makers in making informed and strategic decisions, thereby fostering responsible integration into TradFi for effective risk management. This study enhances DeFi security by providing users with clear guidance on existing mechanisms and risks in DeFi, reducing susceptibility to misinformation, and promoting secure participation. Additionally, it offers an overview of DeFi’s role in shaping the future of the internet.