Publication Search

This study aims to optimize the architecture of Artificial Neural Networks (ANN) for rainfall prediction using meteorological data from Indonesia, which is known for its complex and highly variable climate patterns. Climatic variables such as temperature, humidity, air pressure, wind speed, and historical rainfall records serve as the main input features to evaluate the performance of various network configurations. Optimization is carried out by determining the appropriate number of neurons, hidden layers, activation functions, and training algorithms to enhance prediction accuracy. Model evaluation employs indicators such as Mean Absolute Error (MAE) and Root Mean Square Error (RMSE) to ensure output stability. The findings indicate that a multilayer architecture combined with optimized parameters significantly improves the network’s ability to capture non-linear patterns in Indonesia’s tropical rainfall data. The optimized model produces more stable and accurate predictions compared to standard configurations. These results highlight the importance of ANN architecture optimization in supporting early warning systems, agricultural planning, water resource management, and hydrometeorological disaster mitigation across Indonesia.

Indonesia, as an archipelagic country with over 17,000 islands, faces significant challenges in providing electricity access, particularly to small and remote islands. One promising solution is Solar Power Plants (PLTS), both land-based and floating solar plants that utilize water surfaces, suitable for areas with limited land availability. This study evaluates the economic feasibility of floating solar plants and land-based solar plants using the Levelized Cost of Electricity (LCoE) approach. LCoE encompasses all costs of construction, operation, maintenance, and energy production over the plant's lifespan, serving as a key benchmark in selecting power generation technologies. The findings show that the LCoE for floating solar plants is Rp11,197.00/kWh, lower than land-based solar plants at Rp11,769.00/kWh, although both exceed the electricity purchase price in Kodingareng, South Sulawesi, at Rp2,460.00/kWh. This difference is influenced by higher construction costs for floating solar plants but offset by greater energy output and lower operation and maintenance costs. This research provides a basis for developing solar power systems in archipelagic regions, emphasizing efficiency and sustainable energy solutions.

The increasing population triggers a demand for land for housing and other activities. Along with this, issues arise regarding the limited availability of land, especially in rapidly developed areas. This limitation has the potential to create an imbalance between the growing need for space and the existing land capacity. This study evaluates the land carrying capacity in four sub-districts in the southern part of Medan City, namely Medan Tuntungan, Medan Johor, Medan Amplas, and Medan Denai, in dealing with the continuously growing population. Using a spatial analysis approach with ArcGIS 10.8 software and detailed spatial data, this research identifies potential areas for residential development and projects the capacity of land to accommodate future populations. The analysis covers physical and environmental aspects such as land slope, soil type, natural disaster risks, and access to public facilities. The results show that each sub-district has different potentials and challenges. Medan Tuntungan, with its large area and flat land conditions, shows significant potential for residential development, although attention must be given to the existence of protected areas and agricultural land that must be preserved. Medan Johor, as an economic center, faces substantial pressure on land use, with some areas nearing their maximum capacity. Medan Amplas and Medan Denai, which are more urban, experience stricter land limitations. Population growth projections indicate a significant increase in land demand in some sub-districts in the coming decades. Without effective management, this has the potential to exert high pressure on the environment and urban infrastructure. This research emphasizes the importance of spatial planning and sustainable development policies to maintain a balance between housing needs and environmental conservation.

As industries increasingly integrate cloud-based Industrial Control Systems (ICS), the cyber threat landscape expands. While cloud computing offers scalability, cost efficiency, and remote accessibility, it also introduces security vulnerabilities that adversaries can exploit. This study explores AI-driven threat detection models, encryption techniques, and best practices to enhance ICS resilience. Key security measures, including intrusion detection systems, anomaly detection, and robust encryption mechanisms, are analyzed to mitigate cyber risks. The findings highlight the effectiveness of AI-based security solutions in identifying and preventing attacks, ensuring the reliability and integrity of ICS in cloud environments.  

The optimization of thread management in operating systems is essential to improve the performance of multithreading-based applications. This study analyzes various techniques to enhance thread management efficiency, including thread pooling, dynamic scheduling, load balancing, and synchronization contention reduction. Experimental results indicate that thread pooling reduces overhead by reusing threads, while dynamic scheduling improves multitasking responsiveness by prioritizing urgent tasks. Load balancing ensures equitable workload distribution across processor cores, minimizing execution time. Furthermore, reducing synchronization contention using mechanisms like semaphores decreases thread waiting time, thereby boosting application performance. These optimizations enable modern operating systems to efficiently utilize multi-core architectures, improving speed, responsiveness, and user experience. This research highlights the importance of thread management optimization as a foundational step towards developing adaptive and scalable operating systems for future complex and data-intensive applications.

The low mathematics learning outcomes of students are caused by many factors, one of which is the low interest in learning mathematics. One way to increase students' interest in learning mathematics is to apply educational games in the mathematics learning process. This description encouraged the PkM team to carry out community service at SD Kristen Sera with the aim of increasing students' interest in learning mathematics through educational games. This community service was carried out on Friday, December 13, 2024, which was attended by 17 grade VI students. The success of this activity was measured using a questionnaire on students' interest in learning mathematics. The results of the analysis of the learning interest questionnaire data showed that there was an increase in students' interest in learning mathematics before and after participating in the learning process using educational games on the material on integer operations. This shows that the application of educational games in the mathematics learning process needs to be done.

Heart disease is one of the biggest causes of death in the world. This research examines the use of the Artificial Neural Network (ANN) algorithm to classify heart disease based on 303 medical data of heart disease patients obtained from the Kaggle dataset center. The data used includes medical parameters such as age, gender, blood pressure, cholesterol levels and other examination results. Various ANN architectures were tested to find the optimal configuration in terms of the number of hidden layers and neurons in each layer. Model performance is evaluated using metrics such as accuracy, precision, recall, and F1-score. From the results of the performance measurement research, an accuracy rate of 97.06%, precision of 92.30%, recall of 92.30%, and F1-Score of 92.30% were obtained.

This study examines the effectiveness of integrated marketing communication in the development of community-based ecotourism at Bukit Tungkuwiri, Papua, with the aim of linking channel strategies and governance structures to socioeconomic impacts. A qualitative descriptive method was applied using purposive sampling involving visitors, managers, and local leaders. Data were collected through observation, semi-structured interviews, and documentation, and analyzed through reduction, presentation, and conclusion drawing using source and method triangulation. The results indicate that the orchestration of local government social media and printed materials expanded outreach and enhanced engagement, while community oral communication strengthened trust, identity, and educational experience. The appeal of the landscape, culinary and guide training, and local participation stimulated the economic turnover of stalls and small businesses, with tourist reach extending across provinces. The main constraints include dual authority systems, limited funding and human resources, and the absence of ticketing regulations and service SOPs. The discussion highlights the importance of cross-channel message consistency, brand architecture, and a monitoring–evaluation system linking digital metrics with on-site feedback. The study concludes that strengthening governance and local capacity is key to balancing promotion, conservation, and economic empowerment. The findings offer an operational model that can be replicated in similar rural destinations. Implications include establishing transparent ticket pricing, seasonal content calendars, curated experience packages, and cross-level collaboration among provincial, district, community, and business actors to ensure long-term sustainability.

The rapid development of multimedia technology has significantly advanced 3D animation techniques, enabling the production of high-quality visual content across industries such as film, gaming, architecture, and product visualization. Rendering, as the final stage of the 3D production pipeline, plays a crucial role in determining both visual realism and production efficiency. This study compares the performance of three rendering engines—Eevee, Cycles, and Radeon ProRender—by evaluating rendering speed, visual quality, and memory efficiency in Blender. The objective is to provide practical insights for designers and digital content creators in selecting the most suitable rendering engine based on project requirements. In this research, three identical 3D scenes were rendered using each of the three rendering engines under controlled experimental conditions. The comparison was conducted based on several parameters, including rendering time, output file size, shadow accuracy, lighting effects, and overall visual realism. Quantitative measurements were used to evaluate render speed and memory consumption, while qualitative analysis assessed differences in shadow detail, global illumination behavior, reflection accuracy, and material realism. The results indicate that Eevee outperforms the other engines in terms of rendering speed, making it highly suitable for real-time applications and projects requiring fast previews. Cycles produces the highest level of visual realism due to its physically based path-tracing algorithm, although it requires longer rendering time and higher computational resources. Meanwhile, Radeon ProRender demonstrates competitive performance, particularly in shadow quality and lighting effects, offering a balanced alternative between realism and efficiency. Based on the findings, Blender remains a flexible and effective platform. The choice of rendering engine should depend on whether speed, graphic quality, or memory optimization is prioritized.

This study aims to determine the forecasting of stock return volatility of energy companies listed on the Indonesian Sharia Stock Index (ISSI) using the ARCH/GARCH method. This study uses purposive sampling method and uses secondary data in the form of daily stock returns from January 2022 to June 2024 on 10 selected stocks. Data processing is done using Stata software. The results showed that of the 10 selected stocks, only 6 stocks, namely BYAN, ADRO, GEMS, PTBA, AKRA, and BSSR, were suitable for analysis using the ARCH/GARCH model. Meanwhile, PGAS, ITMG, PTRO, and HRUM do not show ARCH effect or do not contain heteroscedasticity. Statistical evaluation of volatility prediction shows that the selected models provide good predictions. Among the six stocks analyzed, ADRO, PTBA, and BSSR show high volatility, while BYAN, GEMS, and AKRA show low volatility. Therefore, investors should consider investment risk when evaluating stocks with different levels of volatility.

Indonesia, as the largest archipelagic country in the world, has enormous fisheries potential with a sea area of 5.8 million km². The fisheries sector contributes significantly to the national economy, but faces serious challenges in the form of illegal fishing practices, the use of environmentally damaging fishing gear, and weak law enforcement. This research aims to analyze the role of law and professional ethics in supporting the sustainability of the fisheries sector. A normative approach is used by examining primary, secondary, and tertiary legal materials. The results showed that Law No. 45/2009 on Fisheries has provided a strong legal basis, but its implementation is constrained by weak coordination between institutions and limited monitoring infrastructure. On the other hand, the application of professional ethics by entrepreneurs is still not optimal, with many cases of using illegal fishing gear and injustice to small fishermen.

This Letter Archiving Information System is designed to enhance the efficiency and effectiveness of document management at the Department of Manpower Office in Asahan Regency. The system focuses on managing incoming and outgoing letters, which are routine tasks performed by an agenda officer as part of administrative duties. The management of incoming letters includes receiving, verifying, recording, and archiving, while outgoing letter management begins with drafting and continues to the delivery process. To support these processes, the system separates the management of letters into two main parts: incoming and outgoing letters. For incoming letters, data such as letter number, date, content, attachments, and destination are recorded and stored automatically. Meanwhile, outgoing letters follow a similar format to streamline the recording process and minimize manual errors. The system is developed using web-based technology, including HTML and other supporting tools, to ensure flexibility and ease of access for users. With the implementation of this system, it is expected that letter archiving can be carried out more efficiently, effectively, and accurately, thereby improving administrative performance at the Department of Manpower Office in Asahan Regency.

The Jayapura City Transportation Agency faces significant challenges in managing traffic violation data due to rapid population and economic growth. The use of Excel-based systems has proven inadequate, so a more integrated and efficient information system update is needed. Thus, the research and development method to design a web-based data archiving information system application with a waterfall methodology approach. It is hoped that this application can improve the efficiency of filing and searching for violation data, as well as support better traffic control in Jayapura City.

Effectiveness of Credit File Archiving Using BRImen at PT. Bank Rakyat Indonesia (Persero) Tbk. Kuanino Kupang Unit. The purpose of this study was to determine how credit file archiving uses BRImen at BRI Kuanino Kupang Unit. The type of research used in writing this paper is qualitative with a descriptive approach that explains about credit file archiving using BRImen. The data sources used are primary data and secondary data, primary data in the form of history, organizational structure, main tasks and authorities and credit file archiving procedures at BRI Kuanino Unit. While secondary data in the form of explanations quoted from books or the internet. Data collection techniques in this study are observation, documentation and interviews. Data collection techniques by observation, namely by conducting direct observations on how credit file archiving uses BRImen, data collection techniques by documentation, namely taking credit file archiving data using BRImen on Microsoft Excel and the BRImen register, and data collection techniques by interview, namely interviewing BRImen officers (Customer Service) regarding the file archiving procedure using BRImen at BRI Unit Kuanino Kupang. The results of this study indicate that credit file archiving using BRImen at BRI Unit Kuanino Kupang is quite effective because it meets several indicators of effectiveness, namely regarding the provision of facilities and infrastructure, effectiveness of program objectives, individual effectiveness in implementing program policies, effectiveness of work units in implementing program policies, efficiency of program operations, and clarity of program objectives. The results of this study are expected to help companies in increasing the effectiveness of credit file archiving using BRImen at BRI Unit Kuanino Kupang.

This study used a descriptive qualitative method, with the principal, vocational studies teacher as well as the deputy head of student affairs, administrative staff and students of SMK Cerdas Murni as the research subjects. Data were collected through interviews, observations, and document studies. Then it was analyzed using Farida Nugrahani's Interactive Analysis Model (2014: 173), and tested for validity using the triangulation method. The results showed that the performance of administrative staff in providing student administration services, and correspondence and archival administration at SMK Cerdas Murni was considered quite good. This is evident from the timely completion of tasks, the existence of discipline, a sense of responsibility, the ability to cooperate and communicate well. Supporting factors for performance are the ability of administrative staff, reward and punishment, facilities and work atmosphere, and good relationships with coworkers and superiors. Conversely, the inhibiting factors are the lack of technical competence and damage to work tools. And the steps in streamlining administrative services at SMK Cerdas Murni are, hastening the completion of tasks, conducting discussions with the principal and teachers, attending workshops to improve competence and keep up with existing developments.

This essay focuses on sustainable development in archipelagic nations like Indonesia and how the Green and Blue economies may work together. This study identifies and analyzes a range of ideas, policies, and practices that bring the two economies together using a qualitative methodology and a literature review technique. A Green Economy is one that prioritizes social inclusion, resource efficiency, and low-carbon development. In the meantime, there's the Blue Economy, which promotes coastal environment preservation and economic growth via responsible resource management. According to this article's literature review, today's social and environmental problems may have their answers in the merging of these two economies. Sustainable development goals (SDGs) may be achieved, human well-being can be enhanced, and Indonesia's natural resource potential can be fully used by integrating sustainability concepts from both economies. This study's findings highlight the critical need of coordinating Green Economy and Blue Economy initiatives in order to foster mutually beneficial synergies that promote ecologically conscious and socially equitable sustainable growth.

One of the biggest problems faced by several countries is the rapid increase in population growth, especially in an archipelagic country like Indonesia. One of the cities in North Sumatra Province that has experienced a significant increase in population is Medan City. This study discusses the population growth each year in Medan City. This study predicts the future population by combining historical data on population, birth rate, death rate, and migration using the Adams-Bashforth-Moulton approach in logistic modeling. This study shows the progress of the approach in predicting the population growth of Medan City. With an area of ​​265.10 thousand km2, and a population reaching 2,474,166 people in 2023. The Adams-Bashforth-Moulton method as a logistic growth model is very effective for decision making in predicting population growth in the city of Medan.

Abstract. Traditional Javanese architecture, especially joglo houses, reflect the harmonious relationship between humans, nature, and God through designs that are loaded with symbolism and philosophy. The joglo house not only serves as a place to live, but also as a space for religious and social rituals, reflecting the spiritual values and belief system of the Javanese people. In this article, we discuss the elements of joglo house design, such as soko guru, towering roofs, and spatial layouts that depict social and spiritual hierarchies. This study uses a qualitative approach based on literature studies to analyze how traditional Javanese architectural design reflects the cultural values and spirituality of its people. The results of the study show that the preservation of joglo houses as a cultural heritage is very important, but it faces great challenges due to modernization and urbanization. Preservation efforts through cultural education, culture-based tourism, and cross-sectoral cooperation are relevant solutions to maintain the continuity of this traditional architecture.

This research discusses the design of correspondence filing applications at the Subdivision of the Gerindra Faction of the North Sumatra Provincial DPRD. The letter filing system that is still done manually causes various obstacles such as difficulty in finding documents, the risk of damage and loss of physical documents, and inefficiency in archive management. The purpose of this research is to design a computer-based application to optimize the process of filing incoming letters and outgoing letters. The system development method used is waterfall with the stages of needs analysis, system design, implementation, and testing. The application is designed using PHP programming language and MySQL database to store mail data. The results showed that the designed application can facilitate the process of archiving, searching, and managing correspondence digitally and increase work efficiency in the Gerindra Faction Subdivision of the North Sumatra Provincial DPRD. This system is also equipped with a security feature in the form of a user login to maintain document confidentiality.

Indonesia, as an archipelagic country rich in ethnic, cultural and religious diversity, faces great challenges in maintaining unity amidst differences. In this context, tolerance and cooperation between communities are important foundations for strengthening national unity. Tolerance is not only about respecting differences, but also about understanding and accepting diversity as a force that can enrich social life. Meanwhile, cooperation creates synergy between individuals and groups to achieve common goals, making diversity a tool for building harmony. National unity is a solid foundation for the younger generation to achieve a bright future. In an era of globalization full of dynamics, unity becomes increasingly crucial. Without unity, various challenges such as division, radicalism and instability will threaten the survival of the nation. The young generation as agents of change has a central role in maintaining and strengthening unity. By uniting, the young generation can create strong synergy to overcome various problems and advance the nation.