Publication Search

Classification codes are an important instrument in the management and storage of archives, serving as a guide to facilitate the retrieval of archives quickly, precisely, and accurately. Classification codes can be letters, numbers, or a combination of both. At the Surabaya Industrial Training Center (BDI), a classification code system has been applied in the filing process. However, as the volume of archives increases every year, there has never been a thorough evaluation to ensure their suitability with the development of existing types of archives and the demands of modern administration. This study aims to evaluate the effectiveness of the classification codes used in BDI Surabaya, especially in supporting the process of rediscovery of archives. The research method used is a descriptive method with data collection techniques through observation, interviews, and field documentation conducted for three months. The results of the study show that the classification code structure at BDI Surabaya is adequate to the tertiary level and facilitates the process of rediscovering old archives. However, the existing system has not accommodated some new types of archives, such as student internship archives and business incubator archives. This classification gap results in delays and inaccuracies in the grouping of archives. In addition, the increase in the average archive volume of 34.7% per year further emphasizes the urgency of updating the classification system to be in line with the development of organizational needs. In conclusion, it is necessary to improve the classification code by adding the PP.03.19 subcode for student internship archives and DL.16 code for business incubator archives. It is also necessary to prepare new SOPs, update the archive list format, and train archivists to improve the effectiveness of archive management.

The issue of determining the number of students' graduation times is one of the important indicators in transmitting the quality and effectiveness of the higher education process in universities. The rate of on-time graduation not only impacts accredited institutions, but also becomes a concern for campus management in designing learning strategies and academic guidance. This study aims to apply and compare two classification algorithms in data mining, namely C4.5 and K-Nearest Neighbor KNN, in predicting the accuracy of students' graduation times. Predictions are made based on academic attributes such as Grade Point Average GPA, number of credits that have been achieved, and Semester Grade Point Average IPS as input variables. The method used in this study is Knowledge Discovery in Database KDD which includes data selection, preprocessing, transformation, data mining, and evaluation of results. The study was conducted using the RapidMiner tool, with a dataset of 279 Informatics Study Program students from the 2015 to 2019 intake. The data was classified into two categories: "graduated on time" and "not graduated on time". The test results showed that the KNN algorithm provided better performance compared to C4.5. KNN produced an accuracy of 76.08%, with a precision of 73.11% and a recall of 41.92%. Meanwhile, the C4.5 algorithm produced an accuracy of 73.49%, with a precision of 64.62% and a recall of 41.89%. This difference in accuracy indicates that KNN is more effective in capturing patterns in the data and providing more accurate predictions in this context. Thus, the KNN algorithm can be considered a more optimal method to assist universities in predicting potential student admissions in a timely manner, thus enabling early intervention for students at risk of late graduation. This research also contributes to the development of data mining-based academic decision support systems in higher education.

This research focuses on the development of an Android-based vegetable detection application by utilizing digital image processing technology and data communication through Application Programming Interface (API). This application is designed to make it easier for users to visually recognize different types of vegetables using the device's camera. The detection process is carried out by sending the image to a cloud server, where the image analysis process is carried out to identify the type of vegetable, displaying its name, characteristics, and benefits. The app's implementation includes an intuitive and user-friendly user interface, with key features such as login, registration, and an interactive dashboard. The dashboard displays user information, location, ambient temperature, vegetable detection history, and direct access to the camera for real-time detection processes. The utilization of cloud computing technology not only keeps application performance lightweight and responsive, but also enables high processing efficiency and data scalability. This allows the application to continue to evolve according to the increasing number of users and incoming data. Image processing is done with machine learning algorithms that are trained to recognize the shape, color, and texture of different types of local vegetables. In addition, this system is also equipped with a periodic data update feature to be able to adjust to the development of new vegetable classifications. The test results show that the app is able to recognize different types of vegetables with a high level of accuracy, as well as provide additional relevant information quickly and accurately. Tests are carried out on a variety of lighting and background conditions to ensure the reliability of the system. The success of the development of this application reflects the integration of modern technology in supporting the digital agriculture sector.

The Paiton Steam Power Plant (PLTU) is one of the main sources of electrical energy in East Java, which plays a vital role in maintaining a sustainable electricity supply. The reliability of generator units is a key element in maintaining stable energy distribution. However, the high frequency of sudden generator failures poses serious challenges, such as increased downtime and increased maintenance costs. To address these challenges, this study aims to design a generator maintenance prediction model based on the Naive Bayes algorithm with a predictive maintenance approach. This study uses historical maintenance data and key sensor parameters such as temperature, oil pressure, and vibration as input. The data is analyzed through several stages, namely data preprocessing, selection of relevant features, and labeling generator conditions into three categories: Normal, Warning, and Critical. The Naive Bayes model is trained to classify the data probabilistically to generate predictions of future generator conditions. Model evaluation using accuracy metrics and a confusion matrix shows that the model successfully achieved an accuracy rate of 89% and was able to provide early warnings of potential failures up to 3 days before failure occurs. The implementation of this system is expected to support the shift in maintenance strategies from reactive and scheduled systems to data-driven predictive systems. Implementing failure predictions allows the technical team at the Paiton PLTU to conduct planned maintenance, avoid sudden disruptions, and extend equipment lifespan. Thus, this model has the potential to reduce operational downtime by up to 25%, while providing significant savings in operational and logistics costs. This research also shows that integrating machine learning technology into energy facility management can improve the efficiency and resilience of the overall electric power system.

Fatigue is a critical issue in labour-intensive small industries, especially in traditional food production such as tofu manufacturing. This study aims to develop a fatigue classification model using a decision tree algorithm by integrating subjective assessments of the work system through the Macroergonomic Organizational Questionnaire Survey (MOQS) and objective physiological indicators, specifically Cardiovascular Load (CVL). The research was conducted in a tofu home industry located in Kalisari Village, Banyumas, Indonesia. Primary data were collected from 10 workers through MOQS questionnaires and heart rate measurements taken at rest and during work. CVL values were calculated and used as labels for classification into three categories: low, moderate, and high fatigue. Meanwhile, MOQS dimension scores (organization, job, personal, environment, and technology) were transformed into interval data and used as classification features. A decision tree model was built using the CART algorithm and visualized for interpretability. The results show that all workers experienced at least moderate fatigue, with 20% categorized as high fatigue. The decision tree revealed that the dimensions of organizational and personal factors were the most influential in predicting fatigue levels. The model provides a practical and interpretable tool to support decision-making in scheduling, workload balancing, and ergonomic interventions. This study demonstrates a novel approach to combining macroergonomic assessments and physiological data with machine learning for practical fatigue risk management in small-scale food production environments.

This study aims to analyze and compare the performance of the Naive Bayes, K-Nearest Neighbors (KNN), and Decision Tree algorithms in predicting the purchase intention of e-commerce visitors using the Online Shoppers Purchasing Intention Dataset, which consists of 12,330 records and 18 variables, with the Revenue variable serving as the classification target. The preprocessing stage involved transforming categorical and boolean variables into numerical form, standardizing features using StandardScaler, and splitting the dataset into 80 percent training data and 20 percent testing data. Model evaluation was conducted using accuracy, precision, recall, F1-score, and ROC-AUC metrics, and was further strengthened by 10-fold cross-validation to obtain more stable results. The findings indicate that KNN achieved the highest accuracy of 0.866180, while Naive Bayes produced the highest recall value of 0.690998 and the highest ROC-AUC value of 0.821696. Meanwhile, Decision Tree demonstrated relatively balanced performance with an accuracy of 0.857259 and an F1-score of 0.571776, whereas the cross-validation results identified KNN as the model with the highest average accuracy of 0.8770. These findings suggest that the selection of a classification model for purchase intention prediction cannot rely solely on a single evaluation metric, as each algorithm possesses different strengths. Therefore, a comparative approach among algorithms can help determine the most suitable model for supporting consumer behavior analysis on e-commerce platforms.

This study aims to examine in depth the effectiveness of the application of the Children Learning in Science (CLIS) learning model in the Natural Science (Science) learning process. The background of this study stems from the problem of low active student participation in class, which is largely caused by difficulties in understanding abstract science concepts. The CLIS model offers a learning approach that emphasizes active student involvement through a series of systematic learning stages. The method used is a literature review with a qualitative descriptive approach. Analysis was conducted on 25 articles from national and international publications. Each article was reviewed based on relevance, research methods, main findings, and the suitability of CLIS application in various science learning contexts. The results of the study indicate that CLIS has proven effective in improving students' understanding of science concepts, developing science process skills such as observation, classification, measurement, and hypothesis testing, and encouraging active student participation during the learning process. In addition, this model is also able to improve critical thinking skills through exploration activities, experiments, group discussions, and reflection on learning outcomes. The CLIS stages, which include exploring students' prior knowledge, introducing new concepts through experiments, strengthening understanding through discussions, and strengthening concepts through reflection, enable students to construct knowledge independently and meaningfully. Based on these findings, CLIS is considered relevant and can be an effective alternative learning model to improve the quality of science learning at various levels of education.

This Community Service Program (PKM) aims to enhance the understanding of the staff at the Environmental and Sanitation Agency (DLHK) of Depok City in utilizing information technology through socialization and training on the development of a waste classification website. The website is designed to assist the public in identifying types of waste and to encourage more responsible and integrated waste management practices. The implementation methods for this program include socialization sessions, technical training workshops, and system usage demonstrations. Participants were introduced to the functionalities of the website, including how to classify various waste types and its role in supporting environmental sustainability. The program also provided hands-on training to ensure the staff could effectively use the website and incorporate it into their daily tasks. As a result, the staff’s understanding of the concept of digital-based waste classification has significantly increased. Additionally, the potential benefits of using such technology to support sustainable environmental management programs were clearly recognized. The program not only enhanced the staff's technical skills but also contributed to a deeper understanding of the importance of waste classification in the broader context of environmental conservation. The outcomes of this initiative are expected to encourage the staff to actively promote the use of the website to the public, thus fostering a more responsible and efficient waste management system in Depok City. This program demonstrates the effectiveness of integrating technology in supporting local government initiatives aimed at improving environmental management and sustainability. Furthermore, it underscores the importance of digital tools in modernizing waste management systems and enhancing public awareness and engagement.

Peningkatan transaksi dalam platform e-commerce seperti Shopee menuntut adanya sistem prediksi status pesanan yang akurat, guna mengoptimalkan pelayanan dan mengurangi pembatalan maupun keterlambatan pengiriman. Penelitian ini bertujuan membangun model klasifikasi status pesanan (selesai atau batal) pada toko Stuftech.Id menggunakan algoritma C4.5. Data yang digunakan merupakan transaksi pesanan mencakup metode pembayaran, kategori wilayah pengiriman, dan ongkos kirim. Proses klasifikasi dilakukan menggunakan RapidMiner dengan tahapan preprocessing, pembangunan decision tree, dan evaluasi model. Hasil analisis menunjukkan bahwa atribut “Kategori Pulau” memiliki nilai gain tertinggi sehingga dipilih sebagai node akar. Model yang dibentuk menghasilkan akurasi sebesar 86%, dengan recall 100% untuk pesanan selesai namun hanya 6,67% untuk pesanan batal. Temuan ini mengindikasikan bahwa algoritma C4.5 efektif dalam memprediksi pesanan yang berhasil, namun perlu peningkatan dalam mendeteksi potensi pembatalan. Implementasi model ini dapat membantu pelaku usaha dalam mengambil keputusan operasional secara proaktif.

As shipping activities through various modes of transportation increase, the need for adequate understanding of dangerous goods is becoming increasingly important, especially among the younger generation. Unfortunately, many students still do not understand the classification and risks associated with transporting these goods. This community service activity aims to increase awareness and understanding of high school students in the Philippines regarding the classification of dangerous goods and the importance of safety in the shipping process. The activity was carried out through an interactive outreach method that included visual presentations, case studies, and simple simulations to make the material easier to understand and apply. The material provided refers to international standards, namely the International Maritime Dangerous Goods (IMDG) Code and ICAO Technical Instructions (ICAO-TI), which are important references in the classification and handling of dangerous goods globally. Evaluation was carried out through pre-tests and post-tests to measure the level of student understanding before and after the activity. The results showed a significant increase in students' ability to recognize symbols, types of dangerous goods, and initial actions to be taken when faced with these goods. These findings confirm that the right educational approach can increase early awareness among students as potential actors in the logistics chain. It is hoped that similar programs can be implemented widely and sustainably in various educational institutions to minimize the risk of sending dangerous goods due to a lack of public knowledge.

Kecelakaan lalu lintas di Kabupaten Brebes merupakan masalah kritis karena tingginya frekuensi insiden yang terjadi di wilayah tersebut. Penelitian ini bertujuan untuk menentukan area yang rentan terhadap kecelakaan dengan menggunakan algoritma K-Means Clustering , yang mendukung proses pengambilan keputusan berbasis data. Isu utama yang dieksplorasi dalam penelitian ini adalah bagaimana algoritma K-Means dapat diimplementasikan untuk mengelompokkan zona rawan kecelakaan dan meningkatkan kesadaran masyarakat terhadap keselamatan jalan. Metodologi yang digunakan meliputi pengumpulan data melalui tinjauan pustaka, observasi langsung, dan wawancara, yang dilanjutkan dengan penggunaan algoritma K-Means untuk mengklasifikasikan data kecelakaan berdasarkan jumlah kejadian, korban jiwa, dan cedera. Temuan menunjukkan bahwa algoritma K-Means secara efektif mengelompokkan lokasi rawan kecelakaan ke dalam tiga tingkat risiko yang berbeda: tinggi, sedang, dan rendah. Dengan demikian, informasi yang terklasifikasi ini dapat membantu otoritas terkait dalam meningkatkan langkah-langkah keselamatan lalu lintas dan mengedukasi masyarakat tentang area berisiko tinggi. Hasil penelitian ini diharapkan dapat berkontribusi pada pengembangan kebijakan keselamatan lalu lintas yang lebih terinformasi dan strategis di Kabupaten Brebes.

State Senior High School 7 Surakarta is one of the public schools located in Surakarta City. The library activities, including member data management, book processing, and book borrowing and returning, are still conducted manually using physical logbooks. This manual process is considered inefficient and prone to errors. The purpose of this study is to develop a book borrowing system at State Senior High School 7 Surakarta that serves as a tool to assist officers in recording, loans, and returning books. This system is designed using the CodeIgniter framework to support WEB displays, programming in PHP, and using MySQL for database management. This system is created using the System Development Life Cycle (SDLC) method with a waterfall model that includes the stages of analysis, design, implementation, testing, and maintenance. System testing was conducted using Black-Box Testing and the System Usability Scale (SUS). The Black-Box Testing results showed that all features and functions operated correctly. The SUS evaluation produced a score of 75.68%, indicating that users generally agreed with the implementation of the system, which falls under the "acceptable" classification.

The study presents a comprehensive framework for optimizing customer retention budget by integrating clustering, classification, and mathematical optimization techniques. The study begins with the IBM Telco dataset, which is prepared through data cleansing, encoding, and scaling.  In the preliminary phase, customer segmentation is performed using K-Means clustering, with k = 3 and k = 4 identified as optimal based on the elbow method and Silhouette score. The configurations produced three (Premium, Standard, Low) and four (Premium, Standard Plus, Standard, Low) customer segments based on purchase preferences, which served as input features for churn prediction. In the second phase, the dataset was divided into training and test sets in an 80:20 ratio, followed by data balancing using the Synthetic Minority Over-sampling Technique (SMOTE) and Edited Nearest Neighbors (ENN). Multiple classification algorithms were evaluated, including Naive Bayes (NB), Random Forest (RF), Categorical Boosting (CatBoost), Light Gradient Boosting Machine (LightGBM), Extreme Gradient Boosting (XGBoost), Gradient Boosting (GB), Support Vector Machine (SVM), Logistic Regression (LR), K-Nearest Neighbors (KNN), and Multi-Layer Perceptron (MLP) using F1-score as the performance metric. CatBoost and LightGBM, with k values of 3 and 4, respectively, were the highest-performing classification models, with only minimal differences in performance.    Ultimately, customer segmentation established customer prioritization, whereas churn prediction assessed customer churn likelihood. Four distinct configurations were assessed utilizing mixed-integer linear programming (MILP) to optimise retention budget allocation within uniform budget constraints, discount amounts, and churn thresholds. In both the k=3 and k=4 scenarios, CatBoost surpassed LightGBM, with CatBoost at K=3 effectively discounting 66% of at-risk consumers across all three segments, hence improving the intervention's efficacy and budget allocation, making it the ideal choice for maximizing customer retention. The results demonstrate the importance of segmentation in enhancing retention budgeting and budget optimization, particularly concerning parameter sensitivity.

The research departs from educational problems in Islamic boarding schools with distinctive educational characteristics and the diversity of cultural backgrounds of students. So researchers are interested in conducting a more in-depth analysis of a harmonious environment despite having students with diverse cultural backgrounds. The purpose of the study is to identify; 1) the characteristics of multicultural Islamic education planning, 2) the characteristics of organizing multicultural Islamic education, 3) Identification of the characteristics of implementing multicultural Islamic education, 4) Identification of the characteristics of supervision of multicultural Islamic education, 5) Analysis of the impact of the characteristics of multicultural Islamic education management in producing moderate students. The research framework departs from theory of multicultural education management in Islamic boarding schools which includes; planning, organizing, implementing, and supervising educational programs in Islamic boarding schools. Managing the elements of education in Islamic boarding schools in; objectives, values, curriculum, teaching methods and facilities and funds, carried out by the Kiyai Ustadz Santri Manager will have an impact on the attitude of religious moderation in students with indications of national commitment, tolerance, anti-violence, accommodating to local culture. This study used a qualitative approach, using ethnography. Data collection techniques are carried out through interviews, observations, and documentation analysis. Data analysis technique uses the Miles and Huberman analysis technique. The validity test is carried out with data validity by conducting tests; on credibility, transferability, dependability, and confirmability. Results of the study found that the characteristics of multicultural education management in Islamic boarding schools: First, Planning in the form of a curriculum containing multicultural values, involving various elements of the Islamic boarding school through deliberation and open meetings of curriculum preparation studies, integrating the madrasah curriculum with Islamic boarding school. Second, organizing; there is empowerment in fostering Islamic boarding schools, Conventional traditional systems, and Guidance patterns depending on the figure of kiai, the existence of organizational work procedures. Third, Implementation of education is carried out; structured through learning classification, planned, organized, and evaluated with the basic pattern of Islamic boarding school education, internalized in attitudes, methods, and exemplary behavior of the kiai. Fourth, Supervision of learning through assessment of learning of multicultural values, Tests are contextual and comprehensive. Fifth, impact of the characteristics of multicultural Islamic education management in producing students who are able to act in the middle by prioritizing Islamic brotherhood and basyariyah, are tolerant for the sake of realizing Islam rahmatan lil aalamiin.

This study aims to examine the effect of media coverage on anti-corruption disclosure by State-Owned Enterprises (SOEs) listed on the Indonesia Stock Exchange (IDX) during the period 2009–2023. The research analyzes 195 sustainability reports published by listed SOEs in 2023. Content analysis is employed to assess the extent of anti-corruption disclosure, which serves as the dependent variable in this study. Media coverage is treated as the independent variable, while firm size, firm age, and industry classification are included as control variables. Legitimacy theory is used as the theoretical framework to explain the research findings. Multiple linear regression analysis is applied to test the hypotheses. The results indicate that media coverage has a highly significant positive effect on anti-corruption disclosure in the same year and a significant positive effect on disclosure in the following year. These findings suggest that media exposure encourages companies to respond to public pressure by enhancing transparency and accountability in addressing anti-corruption issues.

The implementation of the Job Creation Law has brought significant changes to the regulation of foreign investment in Indonesia, particularly through the establishment of a minimum capital requirement for a Foreign Investment Limited Liability Company (PT PMA) of IDR 10 billion. This study aims to examine the formal minimum capital requirements for PT PMA in notarial deeds under the Job Creation Law using normative juridical methods with statutory, conceptual, and case study approaches, and referring to the theory of legal certainty, responsibility, and legal protection. The analysis includes the evolution of PT minimum capital regulations, capital classification within the company's legal structure, the phenomenon of fictitious PT PMAs such as the PT BKG case, and the status and limitations of notary responsibilities. The results of the study indicate that although the minimum capital requirement for PT PMAs has been explicitly stipulated in Government Regulation No. 5 of 2021 and Regulation of the Head of the Investment Coordinating Board (BKPM) No. 4 of 2021, there are legal loopholes in the form of unclear capital deposit periods, weak verification and oversight mechanisms, and the prevalence of nominee practices and fictitious PT PMAs that reduce the effectiveness of the policy. The notary's position as a public official plays a strategic role in drafting deeds of establishment, verifying documents, and providing legal counseling, but has limited authority in verifying material truth. The study concluded that regulatory improvements are needed through establishing clear capital deposit periods, strengthening verification and oversight mechanisms, and harmonizing regulations between institutions to ensure the effective implementation of minimum capital requirements for foreign-owned companies (PT PMA) in accordance with the principle of economic sovereignty.

This study investigates the educational role of a mother in Iwan Setyawan’s Novel 9 Summers 10 Autumns. The research addresses three main problems: (1) How does the mother prioritized family needs in 9 Summers 10 Autumns novel a translated by Maggie Tiojakin (2) How does the role of mother to create children’s educations in 9 Summers 10 Autumns novel a translated by Maggie Tiojakin. Using a qualitative approach, data were collected through documentation. The data collection process in this research involves identified, classified, analyzed, and organized systematically to support the completion of the research. The data were analyzed through identification, classification, description, and interpretation. The findings reveal that she manages household needs with precision, provides warmth and security, and remains strong despite her husband's imprisonment. Her modest home, though small, becomes a place filled with love, simplicity, and gratitude. Her sacrifices selling belongings and borrowing money reflect her unwavering dedication to her family’s survival and harmony. Her commitment to education is shown through her tireless support, never letting her children work, and always encouraging them to study and succeed. Her love and sacrifices result in her children graduating from university and eventually improving the family’s quality of life. The novel illustrates the power of maternal love, perseverance, and the profound impact of a mother’s role in shaping her children’s future.

This research aims to describe the ability to recite poetry by Taufik Ismail, a class XII student at MAN 1 Makassar City. The research method used is quantitative descriptive. The population in this study was all class XII MAN 1 Makassar City. The sample for this research was 35 people from class XII MIPA 1 using saturation sampling. Data collection techniques used declamation tests and observation sheets. The data analysis technique uses descriptive statistics. The results of this research show that Taufik Ismail's ability to recite poetry was declared capable with the average recapitulation classification score in the range of 70-84, namely 70.34. There were 4 students who got the very capable category with a score of 85-100 (12%), 18 students who got the capable category with a score of 70-84 (51%), 4 people (12%) who got the moderately capable category with a score of 60-69, 4 people (12%), the sample who got the less able category with a score of 50-59, 5 people (14%), and 4 people (11%) who got the less capable category with a score of 0-49. Students who get the very capable category and the capable category are categorized as capable. There were 22 students who received the capable category (63%) and 13 students who received the unable category (37%). So, it can be concluded that the ability to recite the Taufik Ismail poetry of class XII MAN 1 Makassar City students is categorized as capable.

The growing demand for affordable transportation has significantly expanded the used car market. This study aims to develop optimal sales strategies by analyzing seller types and vehicle categories through exploratory data analysis and linear regression techniques. Using a cleaned public dataset of over 150,000 used car listings in Germany, key variables such as registration year, mileage, vehicle type, and seller type were examined. Results indicate that individual sellers dominate the market, although dealers set higher and more stable prices. SUVs and limousines typically hold higher market value. The linear regression model achieved an R-squared value of 0.34, suggesting that registration year and mileage account for 34% of the price variance. These findings offer practical insights for stakeholders in the used car business to tailor pricing strategies based on vehicle attributes and seller classification

This study aims to develop an accurate predictive model for identifying students at risk of academic dropout using Decision Tree and Random Forest algorithms. The research utilizes a publicly available dataset sourced from Kaggle, which includes academic and demographic features such as GPA, attendance, credit load, financial aid status, and exam scores. The methodology involves several stages: data collection, preprocessing (handling missing values, encoding categorical variables, and feature scaling), model training, and evaluation using performance metrics such as Accuracy, Precision, Recall, F1-Score, and Confusion Matrix. Results show that the Random Forest algorithm outperforms Decision Tree in terms of accuracy and robustness, with notable feature importance on math, reading, and writing scores. The findings highlight the potential of machine learning in early detection of dropout risks and provide actionable insights for academic institutions to design timely interventions. This research contributes to the growing field of educational data mining and supports data-driven decision-making processes in higher education management.