Publication Search

Chronic Kidney Disease (CKD) is a major global health issue that can lead to serious complications and long-term medical care. This study aims to identify key clinical factors associated with CKD status using binary logistic regression analysis. The dataset, obtained from Kaggle, contains 400 patient records with various clinical and demographic attributes. The dependent variable is CKD status (positive or negative), while the independent variables include age, blood pressure, hemoglobin level, urine albumin level, and serum creatinine. Initial analysis involved descriptive statistics and multicollinearity checks, followed by model estimation and evaluation using likelihood ratio and Wald tests. The final model identified four significant predictors: blood pressure, hemoglobin, urine albumin, and serum creatinine. The model achieved a high classification accuracy of 95.50% and an Area Under the ROC Curve (AUC) of 98.78%, indicating excellent predictive performance. These results highlight the importance of these clinical indicators in early CKD detection and support their use in risk assessment models for kidney disease screening Keywords: Chronic Kidney Disease, Binary Logistic Regression, Likelihood Ratio Test, Wald Test, Classification Accuracy

Lungs are vital organs in the human respiratory system, responsible for fulfilling the body's oxygen needs. If the lungs experience health problems, it can have adverse effects on the human respiratory system. Common causes of lung diseases are usually due to inhaling air contaminated by dust, smoke, viruses, and bacteria. This study aims to compare the performance of two classification algorithms, namely Random Forest and Naive Bayes, in predicting lung diseases. The data used was obtained from the Kaggle website and processed using RapidMiner software. The attributes involved include smoking habits, pre-existing conditions, staying up late, exercise activities, age, and outcomes. Based on the test results, the Random Forest algorithm demonstrated the best performance with an accuracy of 93%, while the Naive Bayes algorithm achieved an accuracy of 87%. These findings indicate that the Random Forest algorithm outperforms the Naive Bayes algorithm in terms of lung disease prediction accuracy.

Efficient drug inventory management is a critical factor in ensuring medicine availability and optimizing procurement budgets in healthcare facilities. This study aims to analyze drug inventory at Tritya Eye Clinic Surabaya using the ABC (Always, Better, Control), VEN (Vital, Essential, Non-Essential), and EOQ (Economic Order Quantity) methods to improve procurement budget efficiency. A quantitative descriptive approach with a case study method was employed. Data were collected from drug usage records, stock opname reports, and procurement documents from in 2024. The findings reveal that the combined ABC-VEN method effectively identifies priority drug groups based on consumption value and clinical importance, while the EOQ method determines optimal ordering quantities to minimize total inventory costs. The integrated application of these methods successfully reduces overstock and stockout incidents and enhances procurement budget efficiency. This study recommends inventory management based on historical usage data and strategic classification to achieve more accurate and cost-effective drug procurement planning.

This study revisits the classification system of broken plurals (jamak taksir) in Arabic, focusing on the categories of jamak qillah (few) and jamak katsrah (many), through a modern linguistic lens encompassing semantic, pragmatic, and corpus-based approaches. Traditional morphological classifications often fail to reflect actual meanings in context, particularly in Qur’anic discourse. Using a qualitative descriptive method combined with corpus linguistics technology, this research explores the dynamics of meaning and function of plural forms in the Qur'an. The findings reveal that jamak qillah and jamak katsrah forms do not consistently denote quantity in a literal sense, but are often selected for rhetorical, thematic, or communicative purposes. Consequently, the teaching of Arabic morphology and exegetical studies should adopt a more contextual and data-driven approach

Stroke is one of the leading causes of death globally and is particularly prevalent in Indonesia. Early prediction of stroke is critical to reducing the risk of long-term disability and mortality. This study aims to build a stroke prediction model using the Support Vector Machine (SVM) classification method. The dataset used is sourced from Kaggle, containing 5,110 records with class imbalance. To address the imbalance, the Synthetic Minority Over-sampling Technique (SMOTE) was applied during preprocessing. The study evaluates model performance across multiple data splits (70:30, 80:20, 90:10) and k-fold cross-validation values (k=5, 7, 10). The SVM was tested with various kernel types—linear, polynomial, and radial basis function (RBF)—along with parameter tuning for C, gamma, and degree. The results show that the polynomial kernel yielded the highest prediction accuracy of 92%. The model performance was evaluated using accuracy, precision, recall, and F1-score metrics.

This study examines the legal protections and enforcement mechanisms against securities dilution in technology‐sector issuers adopting multiple voting rights stock classifications following an initial public offering (IPO) under Indonesia’s Financial Services Authority Regulation No. 22/POJK.04/2021. It addresses two core issues: the adequacy of minority shareholder safeguards embedded within the regulatory framework and the nature and extent of share dilution experienced by existing investors in dual‐class structures. Employing a normative legal research design with a doctrinal approach, the analysis draws on primary sources including UU No. 40/2007, UU No. 4/2023, POJK 22/POJK.04/2021, issuer prospectuses, and PT GoTo Gojek Tokopedia’s 2022–2024 annual reports complemented by secondary literature and tertiary legal references. Findings reveal that POJK 22/POJK.04/2021 integrates quantitative limits (a 90 percent cap on aggregate superior voting rights), procedural safeguards (minimum 5 percent ordinary‐shareholder quorum and independent renewal approval), temporal constraints (10‐year sunset clause), and one‐share‐one‐vote requirements for critical corporate actions, alongside a novel graduated voting ratio system. The GoTo case study underscores persistent misalignment between cash‐flow and voting rights, marked by significant share price volatility and reliance on share buybacks rather than dilutive issuances. While the regulatory framework is comprehensive, its efficacy is contingent on robust enforcement, transparency of indirect ownership, and institutional maturity. Empirical evaluation of post‐IPO dilution events, minority litigation outcomes, and enforcement actions is recommended to assess real‐world impacts.

Stroke is one of the leading causes of death globally and is particularly prevalent in Indonesia. Early prediction of stroke is critical to reducing the risk of long-term disability and mortality. This study aims to build a stroke prediction model using the Support Vector Machine (SVM) classification method. The dataset used is sourced from Kaggle, containing 5,110 records with class imbalance. To address the imbalance, the Synthetic Minority Over-sampling Technique (SMOTE) was applied during preprocessing. The study evaluates model performance across multiple data splits (70:30, 80:20, 90:10) and k-fold cross-validation values (k=5, 7, 10). The SVM was tested with various kernel types—linear, polynomial, and radial basis function (RBF)—along with parameter tuning for C, gamma, and degree. The results show that the polynomial kernel yielded the highest prediction accuracy of 92%. The model performance was evaluated using accuracy, precision, recall, and F1-score metrics.

Dengue Fever (DF) continues to be a major public health threat in Indonesia, especially in urban areas with high population density, such as Purwokerto City. This study aims to develop a predictive model to identify high-risk areas for DF outbreaks by integrating Machine Learning (ML) algorithms and Geographic Information Systems (GIS). The research utilizes historical dengue case data, meteorological parameters (rainfall, temperature, humidity), and population density as predictive variables. Three ML classification algorithms—Naïve Bayes, Logistic Regression, and Support Vector Machine (SVM)—were implemented to develop risk prediction models. Extensive data preprocessing, feature selection, and spatial integration were applied to ensure model robustness. The results show that the SVM model outperformed other methods, achieving the highest accuracy, precision, recall, and F1-score in classifying dengue risk zones. Risk maps generated through GIS visualization successfully identify priority areas for targeted interventions. The novelty of this research lies in the combination of local epidemiological data, multi-algorithm comparison, and geospatial mapping to improve early warning systems for DF in Purwokerto. This integrated approach is expected to support more effective prevention strategies and enhance public health preparedness.

Literary works are a medium to convey messages and values of life through unique language. One form of literary work is a short story that can be studied through a pragmatic approach. This study aims to examine the types of speech acts in the short story Batu di Pekarangan Rumah by Sapardi Djoko Damono. The research method used is descriptive qualitative method. The data were obtained through reading and recording techniques, then analyzed based on the classification of speech acts, namely question, statement, and expressive speech acts. The results show that the main character's speech in this short story contains many questioning and expressive speech acts that reflect the emotional closeness between the character “I” and the stone that is the object of his childhood memories. The speech acts not only show the function of communication, but also imply a deep meaning of loneliness, loss, and nostalgia. This research is expected to contribute to the study of pragmatics in the analysis of literary works, especially short stories.  

This research analyzes the ethics of broadcasting advertisements on television media, especially related to  broadcasting time regulations. The significant role of television in shaping people's thoughts and  behaviors, coupled with the proliferation of potentially unethical and inappropriate broadcasts, highlights  the urgency of this issue. Such violations, especially those concerning children and adolescents, pose  significant risks due to exposure to inappropriate content and the normalization of unethical behavior. This  study emphasizes the importance of media commitment to the Broadcasting Behavior Guidelines and  Broadcast Program Standards (P3SPS) and Law No. 32 of 2002, which aims to protect viewers from  harmful information. This study uses a library observation method with a qualitative approach, analyzing  existing reports, research, and written sources. Data analysis uses Miles and Huberman's qualitative  decomposition technique, which includes data reduction, data presentation, and drawing conclusions. The  findings of the study are in line with previous studies, indicating that violations of broadcasting ethics and  broadcasting hours are systemic problems that have not been resolved. This underlines the need for stricter  supervision, sanctions, re-evaluation of broadcasting time classifications, and media literacy education for  the community.

Law Number 1 Year 2023 on the Criminal Code (KUHP) is a form of national criminal law reform that recognises the existence of customary criminal law. However, it has not been regulated in detail how the implementation and position of customary criminal law as a reason for criminal prosecution, and there are fundamental differences between the two concepts of the legal system. The problems in this research are how the position between customary criminal law and national criminal law in the new Criminal Code, how the legal certainty of the regulation of customary criminal law in the new Criminal Code, and how the challenges in enforcing customary criminal law using the current criminal justice system in Indonesia. This research uses normative juridical method with regulatory and conceptual approaches. The results show that the applicability of customary criminal law is limited to the area where the law lives and applies to customary criminal acts committed in the area where the law lives. The position of customary criminal law can be valid as a reason for criminal prosecution if the customary law that is still alive in the community has been stipulated in the form of Regional Regulations, and customary offences that are similar to offences in the New Criminal Code will be ruled out, and the classification of customary sanctions as additional sanctions, positioning customary penalties to be complementary or secondary, because additional sanctions can only be imposed together with the main sanctions. Legal certainty towards the regulation of customary criminal law is highly dependent on the formulation of the elements of each offence of customary criminal law stipulated in regional regulations. The current criminal justice system in Indonesia (KUHAP) cannot realise the objectives of customary criminal law. The objectives, characteristics, and procedures in the concept of customary law are contrary to those in the criminal justice system. Restorative Justice can be utilised as an alternative to the settlement of customary criminal cases when the New Criminal Code comes into effect.

This study aims to conduct customer segmentation and develop a classification model to predict the clusters of new customers at Monex Toys Abadi Bekasi, a micro, small, and medium enterprise (MSME). Segmentation was performed using the K-Means Clustering algorithm, incorporating parameters such as Recency, Frequency, Monetary (RFM), purchased products, payment methods, shipping cost discounts, and the total number of products purchased by customers. The segmentation results revealed two clusters: (1) Discount Hunters and (2) Loyal Customers. Subsequently, a classification process was conducted to predict customer clusters using the K-Nearest Neighbor (KNN) and Support Vector Machine (SVM) algorithms. Evaluation results indicated that all models achieved high accuracy exceeding 98%. The best-performing model was obtained with SVM using a 70:30 data split, achieving an accuracy of 98.81%. This classification model was then implemented into a Streamlit-based cluster prediction application, enabling users to identify customer segments in real-time. The findings of this research are expected to assist MSMEs in understanding customer behavior, enhancing service quality, and supporting more effective marketing strategies.

The utilization of Artificial Intelligence (AI) in healthcare services and medical diagnosis in Indonesia has grown rapidly alongside the digital transformation of the health sector. AI technology has been employed to improve service efficiency, accelerate diagnostic processes, and enhance disease detection accuracy, particularly through medical imaging and ECG data analysis. Algorithms such as K-Nearest Neighbor (KNN) and Chi-Square have shown effectiveness in heart disease classification. However, despite its benefits, AI implementation presents legal challenges. The absence of specific regulations regarding legal liability in cases of AI-based diagnostic errors creates uncertainty for both medical professionals and patients. Additionally, the lack of national standards, weak patient data protection, and digital literacy gaps present significant obstacles. Adaptive policies, the establishment of dedicated regulations, and collaboration between government, medical practitioners, technology developers, and academics are essential to develop a legal framework that accommodates AI advancements responsibly. With clear legal certainty, AI technology can be optimally utilized to support more inclusive and high-quality healthcare services.

Attendance management is an essential component in educational institutions, companies, and organizations to monitor the presence and punctuality of participants. Traditional attendance systems, such as manual signatures or identification cards, are prone to various issues including human error, time inefficiency, and identity fraud. To address these challenges, this study aims to develop a smart attendance system using facial recognition technology based on Python and the OpenCV library. The system is designed to automatically detect and recognize faces in real time using a webcam or camera module. It employs computer vision techniques to capture facial images, extract unique features, and match them against a stored database of registered participants. Once the face is verified, the system records the attendance along with a timestamp, ensuring data accuracy and security. The development process involved several stages, including image acquisition, preprocessing, feature extraction, and classification. OpenCV was utilized for image processing tasks, while Python provided the programming framework to integrate all components. To enhance recognition accuracy, the system applied techniques such as histogram equalization for lighting normalization and Haar Cascade classifiers for initial face detection. An experimental evaluation was conducted under various conditions, including different lighting environments and facial orientations. The results demonstrated that the system achieved an accuracy rate of 96% under normal lighting conditions, with only a small decrease in performance under dim or uneven lighting. These findings indicate that the system is reliable for practical applications, especially in controlled environments. Conclusion: The Python-based facial recognition attendance system offers a more efficient, secure, and accurate alternative to conventional attendance methods. Future improvements may include the integration of deep learning models to enhance recognition robustness in diverse real-world scenarios.

  Medical records are a critical element in health services at the Mazaya Clinic. Field observations revealed that the clinic does not yet have a medical record folder; Patient documents are only stapled sheets without classification or physical protection. This condition poses risks of document damage, data loss, privacy violations, and operational inefficiency, with search times reaching 12 minutes—far from the standards of the Ministry of Health Regulation No. 24/2022. This study aims to design an integrated medical record folder by optimizing three aspects: (1) anatomical structure, (2) physical material, and (3) content completeness.This research used the Borg & Gall Research and Development (R&D) model through four stages: Define, Design, Development, and Dissemination. The prototype was made using 310 gsm art carton laminated with matte finishing. The design was validated by experts and evaluated through field testing at the clinic. The results showed the folder increased document protection (80% moisture resistance), reduced search time by 75% (from 12 to 3 minutes), and improved data accuracy by reducing input errors by 25%. The study concludes that this folder design is a practical solution for supporting clinical accreditation, patient safety, and cost efficiency. Recommendations include technical training for staff, digital system synchronization, and data backup strategies.

In Indonesia, approximately 70 million people live in malaria-endemic areas, putting them at risk of transmitting the disease to others. Geographic information systems (GIS) are essential tools for mapping and visualizing spatial characteristics, as well as analyzing detailed information. GIS first developed in the late 1950s and has been used in various industries, such as oil and gas, telecommunications, as well as agriculture, forestry, and green open spaces (RTH). This study employed a narrative literature review method, synthesizing previously published information on GIS in green open spaces. The results showed that the classification of aerial imagery using GIS can be divided into two main classes: 'private green spaces' and 'others'. This study focused on finding a significant amount of urban green space in informal settlements, which cover more than 10% of the area. The increase in the number of informal settlements is directly proportional to the increase in private green space. The study also noted that poor communities have access to urban green spaces, which can improve their quality of life. Identification and management of green spaces in informal settlements can strengthen residents' self-confidence and reduce the gap between formal and informal areas in cities.

Attendance management is an essential component in educational institutions, companies, and organizations to monitor the presence and punctuality of participants. Traditional attendance systems, such as manual signatures or identification cards, are prone to various issues including human error, time inefficiency, and identity fraud. To address these challenges, this study aims to develop a smart attendance system using facial recognition technology based on Python and the OpenCV library. The system is designed to automatically detect and recognize faces in real time using a webcam or camera module. It employs computer vision techniques to capture facial images, extract unique features, and match them against a stored database of registered participants. Once the face is verified, the system records the attendance along with a timestamp, ensuring data accuracy and security. The development process involved several stages, including image acquisition, preprocessing, feature extraction, and classification. OpenCV was utilized for image processing tasks, while Python provided the programming framework to integrate all components. To enhance recognition accuracy, the system applied techniques such as histogram equalization for lighting normalization and Haar Cascade classifiers for initial face detection. An experimental evaluation was conducted under various conditions, including different lighting environments and facial orientations. The results demonstrated that the system achieved an accuracy rate of 96% under normal lighting conditions, with only a small decrease in performance under dim or uneven lighting. These findings indicate that the system is reliable for practical applications, especially in controlled environments. Conclusion: The Python-based facial recognition attendance system offers a more efficient, secure, and accurate alternative to conventional attendance methods. Future improvements may include the integration of deep learning models to enhance recognition robustness in diverse real-world scenarios.

Pneumonia detection from chest X-ray images is widely used in computer-aided diagnostic systems. However, effective clinical decision support requires not only accurate classification performance but also consideration of unequal error costs, since false negative predictions may lead to more severe consequences than false positives. In addition, prediction probabilities must be well calibrated to support threshold-based medical decisions such as triage and patient escalation. This research investigates asymmetric misclassification costs and probability calibration for binary classification (PNEUMONIA vs. NORMAL) using the Hugging Face dataset hf-vision/chest-xray-pneumonia. The proposed framework utilizes a ResNet-18 architecture integrated with cost-sensitive learning through weighted cross-entropy loss (FN:FP = 5:1), threshold optimization based on validation data to reduce expected cost, and post-hoc temperature scaling for improving probability calibration. Experimental results on the independent test set indicate that the cost-sensitive approach enhances specificity and decreases expected cost compared to the conventional cross-entropy baseline. Furthermore, temperature scaling improves the reliability of probabilistic predictions, as demonstrated by better negative log-likelihood and Brier score values. The study also explores selective prediction strategies to balance prediction coverage and risk reduction, complemented by Grad-CAM visualizations and structured failure-case analysis for qualitative assessment. Overall, the findings demonstrate that incorporating cost-aware decision thresholds and calibrated probability estimates can serve as lightweight yet effective enhancements for chest X-ray classification systems in clinical decision-support applications.

Durability is defined as a measure of a rock's resistance to weathering and disintegration when the rock undergoes weathering processes over a short period of time. The susceptibility of rocks to disintegration is related to their low durability. Rock durability is often measured using the slake durability test. The slake durability test is widely used to assess physical changes resulting from wetting-drying processes (Franklin and Chandra, 1972). Therefore, slake durability testing is conducted to understand the weathering of rocks caused by heat and water, particularly clay stones which are one of the constituent rocks on a slope. The sampling location is around Sanga-sanga and Muara Badak. Sampling was conducted with coordinate points and the Balikpapan and Kampungbaru formations. The claystone samples taken were then brought to the Mineral and Coal Technology Laboratory of the Engineering Faculty of Mulawarman University for Slake Durability tests. In this study, the lowest index value obtained was 45.7% and the highest value was 93%, indicating high to very high durability. The difference in the durability index values of claystone at the research locations indicates the presence of variables that can affect the slake durability index values of the claystone in the Balikpapan and Kampungbaru formations, including grain size and mineral content as well as geological conditions at the research site. Based on the results of the claystone durability tests, the durability index value (Id2) was obtained, indicating that the sandstone at the research location falls into the classification of high to low.

This research aims to examine and describe the implementation of a digital-based Cost of Revenue recording system at PT Alam Mulya as a logistics service company. Amid the rapid development of information technology, digital-based financial recording systems have become a strategic solution for enhancing efficiency, accuracy, and transparency in financial reporting. This study employs a qualitative descriptive approach, utilizing data collection techniques through literature review, direct observation, and interviews with parties involved in the company's financial recording process. The research findings indicate that the use of the Shortcut-AM application can accelerate the real-time recording of direct costs, reduce the risk of recording errors, and facilitate internal monitoring and audits. However, the effectiveness of the system still faces several challenges, such as delays in collecting supporting documents, account classification errors, and discrepancies between account mutation data and internal records. These challenges highlight the importance of cross-divisional coordination, ongoing technical training, and strengthening internal controls to ensure the system operates optimally. Thus, the digital-based recording system not only enhances operational efficiency but also serves as an essential foundation for maintaining the integrity and accountability of the company's financial reports.