Publication Search

This study proposes the integration of a Hybrid Recommendation method (combining Content-Based and Collaborative Filtering) with Random Forest Regression (RFR) to improve the accuracy of stay duration prediction in web-based boarding house booking systems. The main issue in online boarding booking systems is the inaccuracy of predicting user stay duration, affecting room allocation efficiency and customer satisfaction. The dataset was sourced from the hotel sector due to its attribute similarities and data validity. The research process includes data preprocessing (missing value imputation, normalization, and one-hot encoding), temporal and contextual feature engineering, hybrid recommendation system construction with CBF and CF score weighting, and RFR model training optimized through Grid Search and 10-fold cross-validation. Evaluation was conducted using MAE, RMSE, R² metrics, as well as recommendation metrics such as Precision@5, Recall@5, and Mean Reciprocal Rank (MRR). Results show that this integrated model achieved an R² of 0.7239 and an MAE of 1.0537 days, as well as a Precision@5 of 0.9636. This integration proves effective in improving prediction accuracy and recommendation relevance and contributes to the development of AI-based intelligent systems in the accommodation domain.

BPR in Indonesia. This study uses qualitative research methodology.  The methodology employed is a case study.  The findings of this investigation include (1) Marketing communication strategies in increasing customer loyalty at BPR Kusuma Sumbing Delanggu are by using 1) advertising, BPR Kusuma Sumbing Delanggu utilizes digital media, only using Facebook, Instagram and the BPR Kusuma Sumbing Delanggu website. 2) sales promotion, promotions using distributing brochures, installing banners, personal and non-personal sales by visiting customers directly. 3) Public relations, BPR Kusuma Sumbing Delanggu is building a positive image of the company through events, sponsorships, or CSR. 4) digital media promotion, digital media used in marketing BPR Kusuma Sumbing Delanggu uses social media such as Instagram and Facebook, and we also have a special website for BPR Kusuma Sumbing Delanggu with the website address. (2) BPR Kusuma Sumbing's challenge is that educational communication regarding BPR Kusuma Sumbing Delanggu products to customers is sometimes hampered by a lack of understanding of financial literacy. Therefore, I have to explain in detail and coherently, which takes quite a long time. (3) The solution to addressing the challenges in marketing communication strategies to increase customer loyalty at BPR Kusuma Sumbing Delanggu is to continuously improve customer relationships and expand our reach. By strengthening communication and providing better education, we believe we can increase customer loyalty and the BPR's future growth.

This study aims to analyze the influence of liquidity, leverage, profitability, and company size on the share prices of companies that are members of the Investor33 index on the Indonesia Stock Exchange (IDX) during the 2019–2023 period. This study uses a quantitative approach with purposive sampling techniques, so that 17 companies out of a total of 46 companies that meet the criteria are obtained. The data used is secondary data in the form of annual financial statements obtained from the IDX's official website. The analysis method used was multiple linear regression with the help of the Statistical Program for Social Science (SPSS) software version 25. The results of the analysis show that the leverage and profitability variables have a significant effect on the stock price, which indicates that the company's capital structure and ability to generate profits are important factors in the investor's assessment. In contrast, the liquidity variables and company size do not show a significant influence on the stock price, which means that the company's ability to meet short-term obligations and operational scale are not the main determinants in the formation of the stock price on the index. These findings provide implications for investors and company management to pay more attention to profitability and leverage aspects in financial strategies and investment decision-making. This research can also be a reference for further studies related to the analysis of financial ratios and capital market dynamics in Indonesia.

The development of information technology has brought significant changes to the medical device procurement process, particularly within government institutions such as the Health Office. The procurement of appropriate, efficient, and objective medical devices is crucial to supporting optimal medical services, yet the decision-making process is often constrained by limited budgets and the complexity of multiple assessment criteria. This study aims to design and implement a decision support system (DSS) based on the TOPSIS (Technique for Order Preference by Similarity to Ideal Solution) method to provide recommendations for medical device procurement at the Binjai Health Office. The DSS evaluates six main criteria: price, quality, durability, ease of maintenance, medical necessity, and safety level, using procurement data from the 2022–2024 period. The TOPSIS method is applied to calculate the relative closeness of each alternative to the ideal solution, enabling decision-makers to rank medical device options objectively and systematically. The findings show that the DSS successfully prioritizes procurement alternatives, helping stakeholders allocate budgets more effectively and transparently. In addition, the system minimizes subjective bias by integrating quantitative analysis with clearly defined criteria. The system is implemented in a web-based environment with MySQL as the database, ensuring accessibility and scalability for future use. Overall, this research demonstrates that integrating TOPSIS into a decision support system can enhance the efficiency, accuracy, and accountability of medical device procurement in public health agencies. The study is expected to contribute to improving budget management and strengthening the quality of health services through better resource allocation.

The development of digital technology has had a significant impact on the health sector, including eye examination services. This study discusses the development and implementation of a Digital Optoscope-based Eye Diagnostic application designed using a web platform (HTML). This application provides two main features: visual acuity testing and astigmatism testing, which can be accessed independently by users through digital devices such as laptops, tablets, or mobile phones. Users only need to follow the visual instructions presented interactively on the screen, then perform the test according to the procedure. The testing method is carried out by displaying font size settings according to the Snellen chart standard and radial astigmatism patterns. The results of each test session are automatically recorded and can be saved for further analysis. In addition, users can perform repeated tests to improve the accuracy of self-diagnosis, and the system will provide lens type recommendations based on the measurement results obtained. The trial results show that this application is able to provide convenience, efficiency, and initial accuracy in the process of examining vision disorders. This is very useful, especially for people in remote areas or with limited access to professional eye health services. Thus, the Digital Optoscope-based Eye Diagnostic application has the potential to be an innovative solution for the early digital detection of vision disorders. This study recommends further development, particularly in clinical validation, testing on a wider sample size, and integration with electronic medical record systems to enhance its benefits in comprehensive public health services. Furthermore, collaboration with medical professionals is crucial to ensure diagnostic accuracy. With this approach, the app is expected to become a reliable tool for continuous eye health monitoring.

Discipline is a crucial aspect of education that plays a significant role in shaping students’ character and sense of responsibility. However, the manual discipline assessment process at SDIP Baitul Maal presents several issues, such as inaccurate data, limited analysis capabilities, and difficulty for teachers and parents to monitor students effectively. With the advancement of information technology, digital systems offer a potential solution to improve the efficiency and objectivity of the evaluation process. This study aims to design and develop a web-based application for assessing student discipline by implementing the K-Means Clustering method optimized with the Elbow method. The system is designed to cluster students based on numerical data such as attendance, tardiness, neatness, and rule violations, allowing for more accurate classification of discipline levels. The results show that the system successfully groups students into clusters automatically and provides informative visualizations of the outcomes. Additionally, the system facilitates real-time monitoring and evaluation by school staff and parents through a user-friendly interface. Therefore, the application of the K-Means Elbow method proves effective in supporting decision-making within the educational environment. This research is expected to contribute to the digital transformation of school management and enhance the quality of student character development.

The academic information system is a crucial element in managing academic data in higher education institutions. Universities require an efficient information system to manage student data, faculty, courses, and other academic administration. This study develops an SQLPage-based information system to provide a lightweight and user-friendly web-based solution. SQLPage enables the creation of web applications directly from a MySQL database without requiring complex programming. The research results show that this system can improve the efficiency of academic data management and ease of access to information for users

Research Method: The community and prospective parents have difficulty accessing information about TK Harapan Bunda because they often have to come directly to the school in the morning or meet the school outside of working hours. This hinders efficiency and is time-consuming for them, as well as burdening educators. Therefore, a modern solution is needed such as an official website or digital platform to facilitate access to information quickly and practically. Research Results: The purpose of implementing the system is to evaluate whether the developed system has met expectations. Through testing and implementation, the quality of the system can be assessed. Conclusion: Based on the research and implementation of the TK Harapan Bunda web-based Information System, it can be concluded that: a) The web-based information system provides easier and faster access for the community and prospective parents to obtain information about the school. b) The professionally designed website has succeeded in improving the image of TK Harapan Bunda with an attractive appearance and informative content, which promotes the school's excellent programs and achievements, thereby increasing the interest of prospective students and parental trust. c) The use of modern technology in the development of this system shows that TK Harapan Bunda is able to adapt to increasingly rapid digital developments.

Indonesia is the world's leading producer of spices, but it still faces challenges in manual visual quality assessment, which is inconsistent. This study aims to develop a spice quality classification system using a Deep Learning approach based on Convolutional Neural Networks (CNN). Data was collected through digital images of five types of spices (cloves, cardamom, cinnamon, pepper, and nutmeg) classified into two categories: good and bad. The dataset was then processed and used to Train the CNN model using Tensorflow. The model architecture consists of several convolution, pooling, and dense layers, and is integrated into a web-based prototype application using Streamlit. Evaluation results show that the model achieves high Accuracy of 98.86% (Training), 98.45% (Validation), and 98.45% (Testing). The prototype application can provide automatic Predictions of spice quality through a simple and responsive interface. The results of this study indicate that CNN is effective in identifying the visual quality of spices and can serve as an objective, efficient technological solution that supports the enhancement of Indonesia's spice export competitiveness.

This research discusses the development of a donor module on the SiKembar (Barang Entry and Exit Information System) web-based application, designed to optimize the management of donor data and donation aid during natural disasters. The module is developed to facilitate the donation submission process from the public, ultimately aiming to improve coordination between the community, government, and BPBD (Regional Disaster Management Agency) of Cianjur Regency in managing and distributing post-disaster aid. The development method used in this module is web-based, utilizing PHP programming language and the CodeIgniter framework. The CodeIgniter framework was chosen for its ease of use in building structured and flexible web applications. The donor module developed is integrated into the existing SiKembar platform, allowing for more efficient and organized donor data management. The main feature introduced in this module is the donation submission, which enables the public to directly donate and track the status of their submitted donations through the platform. The results of the research indicate that this module facilitates a more structured and responsive donation submission process. Both donors and administrators can easily access and manage information related to the aid needed and the status of received donations. This enhances transparency and efficiency in donation data management while minimizing the potential for errors in aid distribution. The donor module on the SiKembar application is expected to increase the effectiveness of managing donor data and handling aid following natural disasters. With this system, the aid distribution process will be more organized and faster, while also facilitating better coordination among the involved parties. Ultimately, this module can contribute to accelerating post-disaster recovery and ensuring that aid reaches those in need in a timely manner.

Groundnut plants must be well maintained so that they can be food crops that have economic value and high fat and protein content. Many farmers still plant with the old pattern so that peanut plants are less fertile because they are affected by pests and other diseases. So with an expert system to diagnose peanut plants can help farmers or the general public in knowing the solution if experiencing problems or symptoms of this peanut plant. The application of the WP (weighted product) method can help the application become structured. From the results of the study, the expert system for diagnosing peanut plants can help many people for use as fundamental insights.

Currently, the use of data mining technology has become essential in enhancing business management efficiency, including in the trending coffee shop industry. Data mining allows business owners to analyze sales information in depth, enabling more accurate decision-making regarding inventory management, promotions, and sales strategies. This study aims to implement the Apriori algorithm to analyze sales data at Menrabic Coffee Shop. The Apriori algorithm is used to discover association patterns or relationships between products frequently purchased together by customers, which can assist management in providing inventory that aligns with customer preferences. The research method illustrates the detailed implementation process of the Apriori algorithm, starting from sales data collection, data cleaning, programming, and analysis of the results. The implementation uses web programming languages such as HTML, CSS, MySQL, and JavaScript, while back-end logic is programmed with PHP. The results of applying this algorithm reveal the most popular sales patterns among customers, providing valuable insights for management to improve operational performance and customer satisfaction. Therefore, this study demonstrates that applying data mining with the Apriori algorithm can be an effective tool for understanding consumer behavior and supporting data-driven decision-making at Menrabic Coffee Shop. By utilizing these insights, management can optimize inventory, enhance sales strategies, and ultimately increase overall business efficiency.

Posters are an important means of conveying information and promoting products or services to a wider audience through the power of visual communication. This research focuses on redesigning promotional and informational posters to support the marketing strategy of the Kopi Es Tak Kie website, a long-standing Chinese culinary heritage in Jakarta. The main objectives of this research are to enhance visual appeal, expand market reach, and strengthen cultural values ​​through print media designs that are representative and relevant to the development of the digital era. The approach used is visual communication design with the Design Thinking method. The stages in this method include audience needs research, design concept design, prototyping, and usability evaluation involving target respondents. In the visualization process, Figma software was used to arrange the poster layout, while Procreate was utilized to create complementary illustrations that provide an artistic and authentic feel. The resulting poster design emphasizes the use of a color palette of brick red, cream, and dark blue, combined with script and sans-serif typography. This combination was chosen to convey a cultural message while emphasizing the exclusive image of the Kopi Es Tak Kie brand. The visual harmony of color and typography enhances the cultural narrative while emphasizing the modern brand identity. The primary audience for this poster is young adults aged 22–40 who are interested in the fusion of traditional coffee culture and modern lifestyle. The findings of this study indicate that the redesigned poster is effective in bridging cultural heritage with digital branding, strengthening the identity of Kopi Es Tak Kie across both offline and online platforms. Thus, the poster medium is proven to act as a communication bridge connecting historical values ​​with contemporary marketing strategies.

Coffee is a leading commodity in Indonesia's agricultural sector, possessing high economic value and providing a livelihood for many farmers. However, coffee plant productivity often declines significantly due to various diseases affecting the leaves, stems, and berries. This situation is exacerbated by the lack of knowledge among most farmers in recognizing early disease symptoms, resulting in delayed treatment. Consequently, crop losses are unavoidable. Based on these challenges, this study aims to design and build an expert system capable of diagnosing coffee plant diseases quickly, precisely, and accurately using the Bayesian Theorem method. This method was chosen because it can calculate the probability of a disease occurring based on observed symptoms in plants. The Bayesian approach allows the system to provide more reliable diagnostic results by updating the probability values ​​as new evidence is introduced. The developed expert system is web-based, making it easily accessible to users, both farmers and other interested parties. Users simply select the symptoms observed in coffee plants, and the system will then provide a diagnostic result in the form of possible diseases and their probability levels. Test results indicate that the system is capable of providing fairly accurate diagnostic results and can be used as a basis for farmers in making initial decisions regarding coffee plant disease management. With this expert system, farmers are expected to improve their ability to detect coffee plant diseases early, thereby maintaining crop productivity. This expert system is expected to be an effective decision support tool for farmers to reduce crop losses and improve agricultural sustainability.

This research aims to develop a transaction data security system on the web-based Pancadaya Waste Bank application by applying a hybrid cryptographic algorithm that combines Advanced Encryption Standard (AES) and Rivest Shamir Adleman (RSA). The problem faced in the previous system is the weak recording and security of customer transaction data, because the process is still carried out manually so that it is prone to recording errors, loss of important information, and potential misuse of data by unauthorized parties. To answer these problems, this study uses the Rapid Application Development (RAD) method which allows the application development process to be carried out quickly, flexibly, structured, and according to user needs. The research method used was a qualitative approach with interview techniques with the management of the Pancadaya Waste Bank and the Environment Office, as well as an in-depth literature study on the application of hybrid cryptographic algorithms in modern information systems. The system is built using the PHP programming language, MySQL database, and OpenSSL library as the main support for the data encryption and decryption process. The implementation of the algorithm is carried out by encrypting transaction data using AES for efficiency and speed, then the AES key is secured through RSA to ensure a higher level of security while preventing illegal access. The test results showed that the system was able to encrypt and decrypt transaction data in real-time, as well as display transaction results in the form of digital notes on deposit and balance withdrawal activities. In addition, performance tests using GTmetrix showed that the application has excellent speed, stability, and processing efficiency, making it feasible to be widely implemented in Pancadaya Waste Bank operations.

Public Financial Management (PFM) is a critical element of good governance, transparency, and accountability, with direct implications for education and youth development. Despite its significance, research on PFM in these sectors remains fragmented, limiting a holistic understanding of its impact. This study conducts a Systematic Literature Review (SLR) to synthesize existing scholarship on PFM in education and youth affairs, following the PRISMA 2020 guidelines. A comprehensive search across Scopus and Web of Science identified peer-reviewed studies addressing financial governance, budgeting practices, accountability mechanisms, and financial literacy programs. The findings reveal that effective PFM contributes to improved educational outcomes by enhancing financial literacy, ensuring timely budget disbursement, promoting student savings, and enabling equitable access to financial education. Conversely, persistent challenges such as delays in fund allocation, weak accountability, and disparities in program implementation continue to hinder progress. The review also highlights the broader implications of SLRs in advancing curriculum innovation, guiding evidence-based policymaking, and strengthening accountability frameworks in education finance. This study contributes to both theory and practice by offering an integrated synthesis of PFM in education and youth affairs, identifying critical research gaps, and providing recommendations for policymakers and practitioners. The results underscore the importance of embedding financial literacy into school curricula, adopting performance-based budgeting, and fostering collaboration between researchers and policymakers. Ultimately, strengthening PFM in education not only enhances institutional efficiency but also equips youth with the financial skills and opportunities required for sustainable social and economic development The findings from this review contribute to the ongoing discourse on PFM by offering an integrated synthesis of current knowledge. The study not only uncovers critical research gaps but also provides actionable recommendations for both policymakers and practitioners.

Lake Maninjau specialty food souvenir shop is one of the micro businesses that sells a variety of traditional regional food products. So far, the marketing process and transaction management are still done manually, which causes limited market reach, difficulty in recording sales, and lack of effectiveness in product promotion. This research aims to design a web-based marketing information system to support the sales process, promotion, and data management in a more efficient and integrated manner. The system development method uses the System Development Life Cycle (SDLC) approach of the waterfall model, which includes the planning, needs analysis, system design, implementation, and testing stages. Data collection was conducted through field observations, interviews with business owners, questionnaires to customers, and literature studies related to information systems and digital marketing strategies. The designed information system includes various main features such as product data management, sales transaction recording, automatic sales report generation, social media integration, and product promotion pages. In the marketing aspect, this system allows businesses to display product catalogs online, provide real-time promotional information, and establish direct interaction with customers through contact and ordering features. In addition, the use of this system allows stores to reach a wider market, including potential customers from outside the Lake Maninjau area, through an integrated digital marketing strategy. The implementation results show that this web-based system can increase the effectiveness of product promotion, speed up the transaction process, and improve the quality of customer service. With this system, souvenir shops can compete more competitively in the digital era, as well as strengthen brand image and customer loyalty through more structured and sustainable marketing.

Examinations in radiology installations have increased annually, resulting in a higher risk of radiation hazards to staff, particularly in interventional, conventional X-ray, and CT-Scan environments. Furthermore, not all hospitals are equipped with radiation survey meter monitoring devices. Therefore, an innovative radiation exposure monitoring system based on the Internet of Things (IoT) was developed. This study aims to: (1) develop an IoT-based radiation exposure monitoring system, (2) evaluate the device’s performance, and (3) assess the effectiveness of the system. The research method used was research and development (R&D), which included preliminary information gathering, product planning and development, expert validation, device performance testing, effectiveness testing, and final outcomes. This system was developed for real-time radiation dose monitoring.  The product development involved a Geiger-Muller M4011, an ESP32 microcontroller, and a Node-Red web application. Performance testing of the IoT-based radiation exposure monitoring device and a standard survey meter in CT-Scan and conventional X-ray rooms used the T-Test and Mann-Whitney tests. The results showed p-values > 0.05, indicating no significant difference between the two devices. Effectiveness testing through pre-test and post-test questionnaires demonstrated improved usability—namely flexibility, operability, learnability, and understandability—with an N-Gain value of 78.95%, indicating effectiveness. In conclusion, the IoT-based radiation exposure monitoring system proved effective and feasible for real-time radiation dose monitoring in radiology installations, offering advantages in IoT-based data integration, ease of access, and structured data recording. In addition to performance testing, the system was evaluated in terms of its integration with hospital infrastructure. It was designed to provide real-time radiation dose monitoring, automatically updating the dose data and sending alerts when safe exposure levels are exceeded. The system also enables remote monitoring, making it easier for radiology departments to oversee radiation safety without the need for direct physical checks.

This community service activity was carried out to increase the digital capacity and expand the market reach of the Peyek Bayam Yusr MSME located in Rajabasa Lama I Village, East Lampung, through the application of appropriate technology in the form of website creation and management training. In the rapidly developing digital era, the presence of online media is a key factor in supporting product marketing, but most MSMEs in this region do not yet have the skills or knowledge to utilize it optimally. This activity was designed in several stages: identifying needs, socialization, technical training, mentoring, and evaluation. The training included creating an account on a free platform, selecting a template, filling in product content, and managing supporting features such as photo galleries, contact information, and integration with social media. This approach was carried out directly by students so that MSME owners could follow each process. The results showed that after the training, all participants were able to create a simple website and began using it for promotions. Identified direct impacts included increased product visibility in online media, increased orders, and demand from outside areas that were previously difficult to reach. In addition, this activity also encouraged a shift in marketing patterns from conventional methods to technology-based strategies. The analysis of the results indicates consistency with various previous studies, such as Santoso (2020) and Ginting et al. (2021), which emphasize the importance of MSME digitalization to increase competitiveness. This process has had a significant positive impact on MSMEs. This program is recommended for other MSMEs, as it is hoped that this program will have a positive impact in line with market needs. This process is accompanied by direct mentoring so that the achieved results can be maintained and developed

Administrative services for correspondence and public complaints in villages are still largely handled manually, resulting in challenges in efficiency, speed of service, and poorly documented records. These issues are crucial to address to ensure better organized and responsive public services at the village level. This study aims to develop a website-based correspondence and complaint system accessible to the public and village officials. This study utilizes the Laravel Framework and Waterfall system development techniques. The results demonstrate that the system successfully simplifies the digital submission process for letters and complaints, and assists village officials in verifying and documenting data more efficiently. Based on implementation and testing, the system is considered effective and feasible to use, even though it is still operating locally. Therefore, it is recommended that the system be continuously developed, its features enhanced, and its online implementation be implemented immediately to provide broader benefits. This study aims to develop a website-based correspondence and complaint system accessible to the public and village officials. With this system, the public can submit letters and complaints digitally without having to visit the village office in person. This system also makes it easier for village officials to verify and document incoming complaints and letters in a more organized and efficient manner. The system development method used is the Waterfall method, which has clear and structured stages in each system development process. The results of this study indicate that the developed system successfully facilitates the digital submission of letters and complaints, which was previously done manually. The verification and documentation processes by village officials have also become more structured and efficient.