Publication Search

Health services at the Puskesmas (Community Health Center) are an important sector directly related to the community. However, there are still various challenges in patient data management and handling complaints that can hinder service efficiency. One of the efforts to improve service quality is by developing a complaint information system that can efficiently manage and record patient complaints. This study aims to develop a complaint information system for services at the Puskesmas Waimangura using the Prototype method. This method was chosen because of its ability to produce system prototypes that can be immediately tested and developed according to user needs. The system is designed to allow patients to submit complaints related to the services received, as well as enabling Puskesmas staff to follow up on and record each complaint systematically. With the implementation of this system, it is expected to increase efficiency in managing complaint data, speed up problem resolution processes, and improve accuracy in recording patient and complaint data. The results of prototype testing show that this system simplifies the complaint process and provides convenience for staff in following up on patient complaints. The implementation of this information system is expected to improve the quality of services at Puskesmas Waimangura and accelerate responses to issues faced by patients.

The house renovation program is one of the government's efforts to improve the quality of housing for low-income people. However, the process of selecting recipients of home surgery assistance is often faced with obstacles in determining the right and fair priorities for recipients. Therefore, this study aims to design and implement a home surgery decision-making system at the Housing, Residential Areas, and Land Office using the Weight Product (WP) method. The WP method was chosen because of its ability to conduct an objective assessment of various relevant criteria, such as the condition of the house, ownership status, level of welfare, and socioeconomic needs of the recipient. This system will give weight to each criterion used to determine the priority of home surgical assistance for residents in need. In its implementation, this system is able to process data from various prospective recipients and produce an automatic and transparent order of priority recipients. The results of the evaluation show that this system can improve efficiency and accuracy in the decision-making process, as well as assist the Housing Office in implementing the house renovation program more on target. With this system, it is hoped that the home renovation program can provide greater benefits to people in need, as well as accelerate the implementation of better housing programs.

This study examines the development of a Crude Palm Oil (CPO) price forecasting model using an artificial neural network algorithm, specifically the backpropagation algorithm. As one of Indonesia’s main export commodities, CPO has a significant economic impact and influences the income of oil palm farmers. The CPO price data used in this study were obtained from CIF Rotterdam, covering the period from January 2019 to December 2023. The research methodology consists of several stages, including data collection, preprocessing, model design, and model implementation using Python programming. The training results of the backpropagation algorithm show an error value of 0.537829578 after 1,000 epochs, while the evaluation using Mean Squared Error (MSE) indicates an MSE of 0.022709 during the training process and 0.017604 during the testing process. The model also produces CPO price predictions for the next three months, namely 932.578 for the first month, 949.568 for the second month, and 774.855 for the third month. These findings indicate that the developed model is capable of predicting future CPO prices with adequate accuracy, which can assist companies in making better financial decisions and managing risks associated with CPO price fluctuations.

The retail industry generates an extremely large and continuously growing volume of transactional data along with the advancement of digital technology, thereby requiring sophisticated and systematic data analysis approaches to support effective and evidence-based business decision-making. This study aims to analyze retail sales data by utilizing the Retail Sales Dataset obtained from the Kaggle platform, which consists of 100,000 transaction records and broadly represents the characteristics of retail transactions. The main focus of this study is to classify product categories and predict customer segments, including the identification of high-spending customers (high spenders), based on demographic attributes such as age and gender, as well as various transaction-related features. The research methodology includes data preprocessing, label encoding, and feature engineering to generate additional variables, including Age_Group, Is_Holiday, and Spender_Group, which are expected to enhance the predictive capability of the models. Several machine learning algorithms, namely Decision Tree, Random Forest, and XGBoost, were implemented and evaluated to compare their respective performance. The experimental results indicate that multiclass product category classification achieves relatively low accuracy, ranging from 27% to 34%. These findings suggest the high complexity of retail data and highlight the need for further model optimization, class balancing techniques, and feature refinement to improve predictive performance in future studies.

The increasing intensity of traffic object movement in urban areas has not been accompanied by adequate road infrastructure, resulting in traffic congestion, air pollution, and a higher risk of traffic accidents. One of the primary causes of accidents is traffic violations, particularly wrong-way driving behavior. This study develops a video-based automated traffic violation detection system using the YOLOv5 algorithm. A computer vision approach is employed to detect, classify traffic objects, and count wrong-way violations in real time. Due to limited access to real-world traffic violation footage, simulated traffic scenarios are used as testing data. The system is evaluated on four traffic object classes: motorcycles, cars, buses, and trucks. Experimental results demonstrate strong performance, achieving a precision of 90%, a recall of 92%, and an F1-score of 91%, while the traffic object counting accuracy reaches 89%. These findings indicate that the proposed system has significant potential to support traffic analysis and assist authorities in making more effective decisions to reduce congestion and traffic accidents.

This study was conducted to review the quality of test items in Business Economics and General Administration subjects using a classical analysis approach. The assessment process included examining validity, reliability, difficulty level, the ability of questions to differentiate student abilities, and the accuracy of distractors. The research approach used was descriptive quantitative, with 32 students from grades XI and XII majoring in Accounting as subjects and 50 multiple-choice questions as instruments. The main focus of this study was to ensure that the evaluation tools used were truly capable of describing students' competency achievements. Data analysis was conducted through observation results and student responses on Google Forms, which were then processed using the Anates Version 4.0 application. The results of the analysis showed that most of the questions had high validity and reliability, good discrimination power, and a moderate level of difficulty. However, the overall quality of the distractors was not good enough, and there were no questions in the difficult category. Overall, the quality of the questions in this subject can be categorized as good and suitable for evaluating the learning of vocational high school students in grades XI and XII.

This study aims to analyze the inventory management practices of qurban cattle at Purnomo Sapi Mulyo Farm in Boyolali, Central Java, particularly in facing the surge in demand prior to Eid al-Adha. The research is motivated by the unique characteristics of qurban cattle inventory, which involves living assets, seasonal demand, and biological risks that differ significantly from conventional inventory management. A qualitative descriptive approach with a case study design was employed to capture in-depth information regarding inventory planning, procurement, storage, and sales practices. Data were collected through in-depth interviews with the business owner as the key informant, direct observation of operational activities, and documentation review. The findings reveal that inventory management at the farm is conducted in a responsive manner based on consumer orders, enabling the business to minimize overstock risks and operational costs. However, inventory recording remains manual and unstructured, potentially limiting the accuracy of cost calculation and long-term planning. Price fluctuations and supply availability are strongly influenced by the Eid al-Adha momentum, while cattle health and lead time are critical factors affecting inventory effectiveness. From a theoretical perspective, the study extends inventory management concepts to the context of live and seasonal inventory. Practically, the findings suggest that implementing a simple yet structured inventory recording system could enhance operational efficiency and decision-making accuracy in local qurban cattle farms.

Because it directly impacts revenue, customer loyalty, and long-term business sustainability, customer churn is a critical issue for the e-commerce industry. High churn rates indicate that a business is unable to retain existing customers, which means it is more expensive to acquire new customers. Therefore, a precise analytical approach is needed to identify customer behavior patterns that are likely to churn. Using machine learning methods, this study analyzes and predicts customer churn. For this study, the E-Commerce Customer Churn 2025 dataset, obtained from Kaggle, was used. This dataset consists of 10,000 customer data and contains fifteen variables covering transaction behavior, customer characteristics, and churn status. Data preprocessing, descriptive analysis, exploratory data analysis (EDA), and classification model development using Logistic Regression and Random Forest algorithms were part of the research project. Model evaluation was conducted using a Confusion Matrix and Receiver Operating Characteristic (ROC) Curve to evaluate the model's accuracy and ability to distinguish between churned and non-churned customers. The results showed that the Random Forest model performed better than Logistic Regression, with an ROC-AUC of 1.00. Furthermore, feature importance analysis revealed that the days_since_last_purchase variable was the most dominant factor in predicting customer churn. These findings are expected to help e-commerce companies design more effective, data-driven customer retention strategies.  

The integration of Artificial Intelligence (AI) into precision agriculture has significantly improved plant disease recognition; however, many existing deep learning models remain computationally expensive and feature-redundant, limiting their deployment on low-power and edge devices. To address these limitations, this study proposes a lightweight framework for maize leaf disease recognition based on serial deep feature extraction, dimensionality reduction, and machine-learning–based classification. A pre-trained MobileNetV2 network is employed as a fixed feature extractor to obtain discriminative visual representations, while Principal Component Analysis (PCA) is applied to reduce feature dimensionality by approximately 76%, retaining 95% of the original variance and improving computational efficiency. The compressed features are subsequently classified using a Radial Basis Function Support Vector Machine (RBF-SVM), optimized via grid search and cross-validation. Experiments conducted on a four-class maize leaf disease dataset (Northern Leaf Blight, Common Rust, Gray Leaf Spot, and Healthy), with class imbalance handled during training, demonstrate that the proposed MobileNetV2–PCA–SVM pipeline achieves 97.58% accuracy, 96.60% precision, 96.59% recall, and 96.59% F1-score, outperforming the DenseNet201 + Bayesian-optimized SVM baseline (94.60%, 94.40%, 94.40%, and 94.40%, respectively). This improvement corresponds to a 2.98% accuracy gain, a 55% reduction in error rate, an 86% reduction in model parameters (20.31M to 2.75M), and an 85% reduction in model size (81 MB to 12 MB). These results indicate that the proposed framework provides a compact and efficient solution with strong potential for deployment in resource-constrained agricultural environments.

English Correspondence is an important course for university students from non-English departments as it equips them with professional writing skills needed in the workplace, including job application letter writing. This study aims to describe students’ writing outcomes in writing job application letters after receiving instruction in an English Correspondence course. The study employed a descriptive qualitative research design. The participants consisted of 22 students from a non-English department enrolled in the English Correspondence course at Stekom university. The data were obtained from students’ final job application letters and analyzed using an analytic writing assessment rubric focusing on content relevance, completeness of letter structure, organization, and use of formal English. The findings reveal that students generally achieved good writing outcomes in writing job application letters. The strongest aspect was the completeness of letter structure, indicating that most students were able to apply the standard format and components of a job application letter appropriately. Students also demonstrated relatively good performance in content relevance and use of formal English. However, weaknesses were identified in organization and language accuracy, particularly in developing coherent ideas and using grammatically accurate formal expressions. The analysis of representative excerpts from students’ letters further illustrates variations in writing quality across aspects. Overall, the findings suggest that instruction in the English Correspondence course contributed positively to students’ ability to write job application letters. This study highlights the importance of examining students’ writing outcomes holistically to provide insights for improving instructional practices in teaching professional writing.

The E-Kinerja Program is a policy innovation developed by the Madiun City Government to support the digitalization of civil servant performance management as part of bureaucratic reform and the implementation of the Electronic-Based Government System (SPBE). This study aims to evaluate the implementation of the E-Kinerja Program in Madiun City using six policy evaluation criteria proposed by William N. Dunn, namely effectiveness, efficiency, adequacy, equity, responsiveness, and appropriateness. This research employs a qualitative descriptive approach, with data collected through interviews, direct observation of the E-Kinerja application usage, and documentation review of related policies. The findings indicate that the E-Kinerja Program is relatively effective and efficient in supporting the monitoring of civil servant attendance and daily activities through features such as QR Code-based attendance, photo documentation, and daily activity reporting. However, several challenges remain, including unstable GPS accuracy, limited internet connectivity, and the practice of non real time input of daily activities. In addition, differences in digital literacy levels and device compatibility among civil servants affect the equitable utilization of the application. Overall, the implementation of the E-Kinerja Program is considered appropriate as part of bureaucratic digital transformation in Madiun City, although further improvements in technical aspects and human resource capacity are required to optimize its implementation.

The process of determining eligibility for social assistance recipients is often constrained by subjective assessments and uncertainty in decision-making criteria. This condition can lead to inaccurate targeting and unfair distribution of aid. Therefore, an appropriate decision support method is required to handle data uncertainty effectively. This study aims to apply the Fuzzy Mamdani method to determine the eligibility of social assistance recipients based on several assessment criteria. The criteria used in this study include monthly income, number of dependents, and housing conditions. The research method consists of data collection, fuzzification, formulation of fuzzy rules, inference using the Mamdani approach, and defuzzification to obtain a crisp output value. The results show that the Fuzzy Mamdani method is able to classify recipients into eligible and non-eligible categories more flexibly compared to conventional methods. The generated eligibility values reflect real conditions more accurately by considering degrees of membership for each criterion. The implementation of this method can assist decision-makers in improving the accuracy, objectivity, and fairness of social assistance distribution. This research is expected to contribute to the development of intelligent decision support systems in the social welfare sector.

The dynamic fluctuations in stock prices present a major challenge for investors in making informed decisions. To anticipate such uncertainties, forecasting methods that can provide accurate predictions are required. This study compares two time series forecasting methods Autoregressive Integrated Moving Average (ARIMA) and Double Exponential Smoothing (Holt) in predicting the stock prices of PT Telkom Indonesia (TLKM). The dataset consists of monthly closing prices from January 2018 to December 2023. The performance of each model is evaluated using three error metrics: Mean Absolute Error (MAE), Mean Squared Error (MSE), and Root Mean Squared Error (RMSE). The results show that the ARIMA(1,1,1) model yields higher predictive accuracy than the Holt method, with MAE of 787.71, MSE of 771,844.2, and RMSE of 878.55. In contrast, the Holt method records a MAE of 837.19, MSE of 878,393.4, and RMSE of 937.23. These findings confirm that ARIMA is superior in capturing the complex patterns of stock price movements and is more effective in volatile market conditions such as the stock exchange.

Congenital Megacalyces is a rare anomaly of the renal pelvis-calyceal system characterized by non-obstructive calyx dilatation due to renal medulla hypoplasia. This condition is often misinterpreted as hydronephrosis, leading to unnecessary surgical interventions. Advances in genomic technology and precision imaging have opened up opportunities to understand the molecular basis and anatomical structure of this anomaly more deeply. A literature review was conducted through PubMed, ScienceDirect, and Google Scholar, covering publications that discuss the relationship between genomics, imaging, and clinical management of congenital kidney abnormalities. The integration of Next Generation Sequencing (NGS), 3D MRI reconstruction imaging, and AI-based radiomics analysis has proven to enhance diagnostic accuracy, differentiate between obstructive and non-obstructive abnormalities, and assist in determining appropriate conservative therapies. Case studies demonstrate the association between SETBP1 mutations and the development of bilateral megacalyces, as well as the effectiveness of long-term monitoring based on multimodal data. The integration of genetic, imaging, and clinical data is a strategic step toward precision medicine in the management of Congenital Megacalyces. This approach improves diagnostic accuracy, reduces unnecessary invasive interventions, and supports individualized therapy based on genetic and anatomical risk factors.

This study aims to analyze the considerations of the judge in the decision of the Kupang District Court No. 81/Pid.Sus-TPK/2022/PN Kpg and the legal implications of the application of Article 3 of the Corruption Eradication Law. This research uses a normative legal method with a statutory and conceptual approach. The results show that the application of Article 3 of the Corruption Eradication Law in this case is incorrect, as the defendant is not a public official and does not have authority over the management of state finances or assets. It was also found that there was a misapplication of the law (error in juris), an error in determining the subject of the law (error in persona), and an inaccuracy in the object of the case (error in objecto). This study concludes that the case is more appropriately classified as an administrative error by state apparatus rather than a corruption crime. Academically, this research reinforces the distinction between administrative law and criminal law regarding corruption. Socially, this research emphasizes the importance of legal certainty protection and the prevention of criminalization of civil society. This study provides an important contribution to the development of legal theory, as well as the protection of individual rights in the context of criminal law.

The quality of assessment instruments plays an important role in determining the accuracy of measuring student learning outcomes in science learning in elementary schools. A good test instrument must meet certain criteria, such as validity, reliability, difficulty level, and discrimination power. This study aims to analyze the quality of daily science test items in grade VIc elementary schools based on these four criteria. The study used a quantitative. The subjects were 19 sixth-grade students, while the instrument analyzed consisted of 25 multiple-choice questions. Data processing and analysis were carried out using Microsoft Excel to calculate item validity through item correlation with total score, test reliability using internal consistency, difficulty level index, and discrimination index. The analysis results showed that 17 questions (68%) were declared valid, while 8 questions (32%) were invalid and needed to be improved. The results of the reliability test indicated that the test instrument had good reliability and was suitable for use as a measuring tool for student learning outcomes. Judging from the level of difficulty, 20 questions (80%) were moderate and 5 questions (20%) were easy, indicating a relatively balanced level of difficulty. Based on the discrimination power, 16 questions (66%) had very good discrimination power, 4 questions (16%) were good, 4 questions (16%) were sufficient, and 1 question (4%) was poor. Based on these findings, it can be concluded that the quality of the sixth grade science daily test questions is classified as good and the test instrument is suitable for use, but improvements are still needed on invalid questions and those with low discrimination power so that the quality of the assessment is more optimal. This study emphasizes the importance of teachers' abilities in compiling and analyzing test items to ensure that the assessment of science learning is objective, valid, and reliable.

The automotive industry requires fast and accurate sales services, particularly in vehicle credit simulation processes. At Mazda dealerships, credit simulations are still commonly conducted using conventional tools such as printed installment tables or static PDF documents, which often cause delays and calculation errors. This study aims to design and develop a mobile-based vehicle credit simulation application using the Human-Centered Design (HCD) approach and the Flutter framework. The HCD method was implemented through the inspiration, ideation, and implementation stages to ensure that the application meets the real needs of Mazda sales representatives. The application supports flexible credit calculations based on vehicle on-the-road price, down payment, loan tenor, interest rate, and insurance schemes, including All Risk and combination insurance. Usability testing results show that the proposed application significantly improves calculation speed, accuracy, and overall user experience compared to conventional methods. Therefore, the application effectively supports sales performance, minimizes human error, and enhances professionalism in automotive sales services.

This study aims to design, implement, and compare the performance of the Backpropagation algorithm from Artificial Neural Networks and the Seasonal Autoregressive Integrated Moving Average (SARIMA) model in predicting the optimal daily rice requirement at Grillme Restaurant in Pontianak. The main problem faced by the restaurant is the uncertainty in determining the required daily rice stock, which periodically results in either understocking (shortage) or overstocking (wastage), leading to operational losses. To address this, the study utilizes historical daily rice sales data from January 2023 to April 2025 as the database for training and testing both predictive models. The SARIMA approach is employed to capture time series components (trend and seasonality), while Backpropagation is utilized to model non-linear patterns. Comparative test results indicate that the SARIMA model achieved superior accuracy compared to the Backpropagation model. This is confirmed by the Mean Absolute Percentage Error (MAPE) value of the SARIMA algorithm being 17.35%, which is lower than the MAPE value of Backpropagation at 19.62%. The MAPE values obtained by both models demonstrate good predictive capability, but it is concluded that SARIMA is more recommended for a more efficient and planned management of rice stock at Grillme Restaurant in Pontianak.

Public relations management is a strategic approach employed by the Ministry of Tourism and Creative Economy (Kemenparekraf) in providing public information related to tourism. This study aims to analyze the public relations management process of Kemenparekraf in disseminating tourism-related public information by using a descriptive qualitative approach and the public relations management theory proposed by Cutlip, Center, and Broom. Research data were obtained through in-depth interviews, literature review, and observation. The results indicate that Kemenparekraf implements the four stages of public relations management comprehensively: defining public relations problems, planning and programming, taking action and communicating, and evaluating the program. Kemenparekraf utilizes various digital and conventional platforms to disseminate tourism information, with an emphasis on transparency, accuracy, and information accessibility. The implementation of the Public Information Disclosure Act is also a major focus, including the provision of information that must be periodically disclosed, immediately announced, and available at all times. Effective public relations management enables Kemenparekraf to address challenges in the dissemination of complex and dynamic tourism information and to ensure equitable access to tourism information for various stakeholders, thereby supporting sustainable tourism development in Indonesia.

Cloud-native systems are essential for modern software development, offering enhanced scalability, flexibility, and resilience through cloud computing environments. However, ensuring the reliability and performance of these systems presents a challenge due to their dynamic and distributed nature. Traditional testing methods, such as unit and integration testing, while valuable for detecting individual component defects and interactions, are insufficient for predicting failure rates in complex, cloud-native applications. This study explores the effectiveness of various testing techniques and quality metrics in predicting failure rates within scalable cloud-native systems. A comparative experimental study was conducted using three primary testing techniques: unit testing, integration testing, and chaos testing. The results indicate that chaos testing, when combined with advanced quality metrics such as migration rate and mismigration rate, significantly outperforms traditional methods in predicting failure rates and evaluating system resilience. These findings suggest that chaos testing offers a more comprehensive evaluation, simulating real-world disruptions to test system behavior under stress, which is essential for cloud-native environments where high availability and fault tolerance are critical. The study also highlights the importance of integrating predictive quality metrics, which improve the accuracy of failure predictions and enhance system reliability. The study concludes that for cloud-native systems, a combination of advanced testing techniques and predictive metrics is essential for ensuring high availability, scalability, and reliability in dynamic environments. Future research should focus on refining predictive testing approaches, developing standardized frameworks, and empirically validating new testing methods to address the growing complexity of cloud-native systems.