Publication Search

Cardiovascular disease is a leading cause of death globally, necessitating effective predictive systems. This research aims to analyze the effectiveness of various machine learning (ML) models—Logistic Regression (LR), Random Forest (RF), Naive Bayes (NB), Support Vector Classifier (SVC), and K-Nearest Neighbors (KNN)—in predicting heart disease using publicly available health data. The study involved pre-processing data, training models, and evaluating them using accuracy, precision, recall, F1-score, and G-Mean metrics. The results show that KNN is the most reliable model, with the highest accuracy of 92%. Significant health features were identified, such as chest pain type and maximum heart rate. The study contributes to improving clinical decision support systems by identifying optimal ML models for heart disease prediction.

The growth of e-commerce in Indonesia has led to the emergence of various online shopping platforms, with Shopee being one of the most popular in Semarang City. User reviews on the Shopee application serve as a valuable data source for analyzing customer satisfaction levels; however, the large volume of data requires a systematic and accurate analytical approach. This study aims to analyze user review sentiments of the Shopee application using three machine learning algorithms: Random Forest, Naïve Bayes, and Support Vector Machine (SVM), as well as comparing the accuracy of these three algorithms. This research utilized 1000 reviews collected through web scraping from the Play Store, which were categorized into three classifications: positive, neutral, and negative sentiments. The analysis process encompassed pre-processing stages, feature extraction using TF-IDF, and classification using Random Forest, Naïve Bayes, and Support Vector Machine algorithms. The results demonstrated that the Random Forest algorithm achieved the highest accuracy at 96.19%, followed by Support Vector Machine with 95.71% accuracy, and Naïve Bayes with 84.76% accuracy. This research highlights the effectiveness of Random Forest and SVM in classifying user review sentiments towards the Shopee application.

The Non-Cash Food Assistance Program (BPNT) is assistance provided by the government to Beneficiary Families (KPM) in the form of non-cash every month. Initially, the Non-Cash Food Assistance (BPNT) program was a replacement program for the Prosperous Rice Program (Rastra) which had several problems. Presidential Regulation of the Republic of Indonesia Number 63 of 2017. This BPNT uses an electronic account mechanism, so it can only be used to buy food from traders or e-warongs that have collaborated with Himbara banks, but now BPNT assistance has changed to being in the form of money that is withdrawn at Bank link. This study aims to identify and analyze the obstacles faced in the implementation of the Non-Cash Food Assistance Program (BPNT) in Barengkok Village, Leuwiliang District, Bogor Regency. This study uses a qualitative approach with in-depth interview and observation methods. Data were collected from various sources, including beneficiaries, program implementers, and other related parties. The analysis was carried out to identify and group the main obstacles that affect the implementation of BPNT. The study identified several major obstacles in the implementation of BPNT, which were grouped into three categories: (1) Technical obstacles, including problems with infrastructure such as internet networks and EDC machines; (2) Administrative obstacles, including inaccuracies in data verification and lack of socialization about BPNT mechanisms; and (3) Socio-Economic obstacles, such as difficult access to e-warongs and low financial literacy among beneficiaries. These obstacles indicate that the implementation of BPNT in Barengkok Village faces various challenges that affect the effectiveness of the program. To improve the results and impact of BPNT, improvements need to be made in technical, administrative, and socio-economic aspects. Recommendations include improving infrastructure, improving administrative coordination, and improving education for the community.

PT XYZ is a company that produces various gases in the form of Oxygen, Nitrogen, and Argon in gas and liquid form. In the production process, the machine runs 24 hours non-stop and will stop production when maintenance is employed once a year. The Air Separation Plant (ASP) machine performance measurements are needed to determine the effectiveness of its production. The reseacrh aims to analyze the factors that affect machine productivity. The method used is quantitative, using the Overall Equipment Effectiveness (OEE) approach. In addition, this study uses interviews to determine the factors that affect engine performance. The results show that the OEE value of the machine is 75%, which is still below the international standard OEE value of 85%. Therefore, it is necessary to optimize engine performance. Based on the analysis using a fishbone diagram, there are five influencing factors: human factors, machines, work methods, environment, and materials. Based on these five factors, the engine factor most influences the low value of engine performance. The predictive maintenance calculations are conducted, especially on expender and cold box machines, every 95 days of machine should use with work efficiency of around 40 hours.

Dengue fever (DHF) is an infectious disease caused by the dengue virus and transmitted through the bite of the Aedes aegypti mosquito. This disease is a major health problem in many tropical countries, including Indonesia. Identification and classification of DHF patients is very important to prevent further spread and to provide appropriate medical treatment. In this study, the classification of DHF disease is carried out using the K-Means algorithm, which is one of the methods in machine learning used to classify data based on similarity of features. This study aims to apply the K-Means algorithm in classifying DHF cases based on data on symptoms that appear in patients, such as high fever, joint pain, skin rashes, and others. The data used includes patient medical records that record various clinical and demographic parameters. The K-Means algorithm is used to group the data into clusters that describe the severity category or potential risk of dengue disease. The results showed that the K-Means algorithm can be used to cluster DHF patients well, with the division of groups that can describe the severity of the disease. Evaluation was conducted using metrics such as silhouette and cluster validity to assess the effectiveness of the algorithm in performing classification. This model is expected to help medical personnel in decision-making, provide early warning, and improve rapid response to dengue cases.

This study aims to examine the latest developments in the application of machine learning, software, applications, and websites in language teaching. With the advancement of technology, language learning is increasingly facilitated by the use of digital tools that utilize artificial intelligence (AI) and machine learning to improve the learning experience in an adaptive and interactive manner. The study reviewed a variety of platforms that use this technology, including key features that support personalization, automated feedback, and student performance assessments. In addition, this study discusses the effectiveness of the technology in supporting independent and formal learning in the classroom, including implementation challenges in various educational settings. It was found that although this technology provides a great opportunity in accelerating language learning, there are some limitations, such as limited access in regions with low digital infrastructure, as well as lack of integration with relevant cultural and social contexts in language learning. This study concludes that machine learning-based technology in language teaching has great potential, but further research is needed to optimize its application in various educational contexts.    

Tropical forest fires pose a serious threat to ecosystem sustainability, particularly in Kalimantan, which is prone to seasonal fires. Early detection is key to prevention efforts, but conventional and satellite-based monitoring methods often face limitations, particularly in identifying small-scale hotspots obscured by forest canopies. This study aims to test the effectiveness of integrating drone technology with thermal sensors in tropical forest monitoring as an early fire detection system. The research method uses a field study design with an experimental approach. Drone flights were conducted over tropical forest areas in Kalimantan, systematically capturing thermal imagery according to a predetermined flight path. Thermal image data were analyzed to identify hotspots, then compared with satellite hotspot data (MODIS and VIIRS). Field validation was also conducted through direct temperature measurements using a portable infrared thermometer. Data analysis involved comparing detection results, accuracy testing, and measuring system sensitivity with a confusion matrix. The results showed that drones with thermal sensors were able to detect more hotspots than satellites, with a higher level of accuracy compared to field validation results. For example, in several study areas, drones successfully identified small hotspots that were not detected by satellites. This confirms that drones with thermal sensors have high sensitivity and can be used as early detection tools for tropical forest fires. In conclusion, the integration of drone technology and thermal sensors has proven effective as a monitoring system that complements satellite-based methods. Further development using big data and machine learning, as well as cross-institutional collaboration, is needed for optimal implementation on a large scale.

This study examines the impact of imperfect targeting on market segmentation and digital advertising strategies through a qualitative literature review. In the rapidly evolving digital era, consumer targeting accuracy has become a major challenge, especially with increasing data privacy regulations such as the GDPR. The study reveals that inaccurate targeting can reduce advertising effectiveness and intensify competition among companies to capture high-value consumers. Additionally, technological and regulatory barriers often hinder the achievement of optimal results in data-driven marketing strategies. However, technological innovations such as artificial intelligence (AI) and machine learning have the potential to improve targeting accuracy, thereby enhancing the outcomes of advertising campaigns. This research also highlights the need for balancing targeting efficiency with compliance to privacy regulations, as well as adopting more adaptive, value-based marketing approaches to foster long-term consumer relationships. These findings offer crucial insights for companies in devising advertising strategies within the dynamic and complex digital landscape.

Currently, technological advances are very rapid and sophisticated. It is not surprising that this progress is utilized by many sectors, both private and government. The government must use technology to develop more sophisticated and inventive government systems. One of them is a unique finger impression-based attendance method that is used to discipline employees in carrying out their duties. The purpose of this research is to find out how effective the use of unique finger impressions is to discipline employees at the Malang Regency Transportation Service, how effective the use of unique finger impressions is to increase employee discipline, and the steps taken to improve employee discipline. This study is based on an inductive approach combined with a descriptive approach. Data collection methods include interviews, observation, and documentation. According to Tangkilisan (2005: 141), there are four ways to evaluate effectiveness: target achievement, adaptability, job satisfaction, and responsibility. By using unique finger impressions, employee discipline and organizational performance improve. However, there are several challenges, one of which is that employees continue to come for unique finger impressions rather than performance, which hinders them from completing tasks on time. One of the efforts made by the Malang Regency Transportation Service is to carry out direct supervision from the leadership and apply disciplinary penalties objectively and according to procedures. The author suggests improving or updating unique fingerprint scanning machine technology, especially the sensitivity of the scanner in reading fingerprints, and adding one unit of unique fingerprint scanning machine

According to academic data, student math ability tests at MTSS PAB 5 Klambir Lima yield mixed results. There are students who understand math well, but there are also those who have difficulty understanding the mathematical concepts themselves. Math teachers at this school have difficulty designing lessons that can meet the needs of students with different levels of understanding. So, it is necessary to group student data to produce educational decision-making and improve learning effectiveness, such as through data mining. Data mining is a semi-automated process that uses machine learning techniques, mathematics, statistics, and artificial intelligence to identify and organize information contained in large databases. The process of finding information can be done by determining the decision rule based based on the level of student understanding in mathematics lessons using the Decision Tree Algorithm C4.5 method. The use of the Decision Tree algorithm C4.5 aims to make it easier to determine decision rules based on gender, Predicate, teacher teaching methods, student learning interest, and level of understanding. Based on the results of the study, it was found that if the teacher's teaching method is good, the predicate value is B, the student's learning interest is less interested, and the gender is male, then the student's level of understanding in mathematics lessons is not understood.

Effective financial management is crucial for business success, especially amid the Industry 5.0 revolution, which has transformed production, management, and human-machine interactions. This era has introduced advanced technologies such as artificial intelligence (AI), the Internet of Things (IoT), robotics, and additive manufacturing into production environments, leading to significant changes in accounting practices. In Indonesia, SMEs, traditionally reliant on manual record-keeping, are encouraged to adopt digital applications to remain current. Consequently, various financial management applications have emerged, including BukuWarung, designed to streamline transaction recording and enhance financial management efficiency. This research aims to assess the effectiveness of BukuWarung as a financial management tool for SMEs. Utilizing a qualitative and descriptive approach, the study involved SMEs at SWK Lidah Wetan that use BukuWarung. Primary data were gathered through observation, interviews, and field documentation. Findings reveal that BukuWarung significantly aids SME financial management, particularly in billing, bookkeeping, cashier operations, inventory management, and transaction scheduling. Future research should explore the utilization of specific features within BukuWarung and their effects on SME financial management.

Developments in the world of manufacturing industry are increasing, very tight industrial competition is encouraging industry to increase production effectiveness. PT. PAN Brothers is a manufacturing industry located in Boyolali, Central Java. PT. PAN Brothers produces clothing types such as jackets, coats, ski jackets, down jackets, tracksuits, travel pants and so on. During the production process, sewing machines have problems, namely machine damage. This research aims to analyze the effectiveness of sewing machine performance using the Overall Equipment Effectiveness (OEE) method and provide suggestions for improving the results of the Failure Mode and Effect Analysis (FMEA) method. The measurement uses the OEE method with three main components, namely availability rate, performance rate and quality rate to identify types of losses based on the six big losses. The average OEE value of 60% is still below world class standards with factors influencing the low OEE value. namely the performance rate, while the losses that affect the effectiveness value of the performance rate are Idling and minor stoppages losses with a value of 42%. By carrying out root cause analysis using a fishbone diagram, the root causes of low performance values ​​influenced by Idling and minor stoppage losses are known, namely machine factors, human factors, methods, materials and the environment. After identifying the problem and measuring the Risk Priority Number (RPN), suggestions for improvement were obtained including providing training to operators, to implement a preventive maintenance system, adding employees in the line balancing section and adding equipment to support machine repair facilities.      

The use of computers in the development of Electronic Chart Display and Information System (ECDIS) teaching materials can be used to assist lecturers in learning activities on vocational campuses as well as other materials in the Computer Base Training (CBT) laboratory at the Indonesian Maritime Polytechnic. The CBT laboratory provides learning materials on ship machinery systems and multiple choice questions for learning evaluation. The purpose of this study was to determine the level of effectiveness of the use of ECDIS material learning media software when used computer-based. The method used in this study is a qualitative method by looking at the final grades of students. This software consists of 42 slides of ECDIS material theory, 1 slide of ECDIS material video tutorial, 1 slide of ECDIS material practice, 20 slides of multiple choice evaluation questions, and 1 slide of final grades made using Visual Basic software. The results of the test showed that all cadets who attended the lecture were successful in using the software until the final grade was obtained.

This research aims to find out how much market service levies contribute to the local income of the city of Kupang, the level of effectiveness as well as the obstacles and efforts in the process of collecting market levies. This research is descriptive qualitative, namely analyzing and describing or illustrating various conditions and situations, various data collected in the form of interview results regarding the problems studied at PD. Kupang City Market. Data collection techniques were carried out using observation, interviews and documentation. The results of the research show that the level of contribution to the receipt of market service levies is classified as very low, the level of effectiveness of the receipt of market service levies is classified as less effective. Obstacles in receiving levies are traders who are in arrears and unpredictable weather. Efforts to increase market levy receipts are by providing outreach, sanctions to traders who are in arrears, selling stalls/kiosks that are still empty and making payments using EDC machines.  

Skin diseases are highly prevalent and transmissible. It has been one of the major health problems that most people face. The diseases are dangerous to the skin and tend to spread over time. A patient can be cured of these skin diseases if they are detected on time and treated early. However, it is difficult to identify these diseases and provide the right medications. This study's research objectives involve developing an ensemble machine learning based model for classifying Erythemato-Squamous Diseases (ESD). The ensemble techniques combine five different classifiers, Naïve Bayes, Support Vector Classifier, Decision Tree, Random Forest, and Gradient Boosting, by merging their predictions and utilizing them as input features for a meta-classifier during training. We tested and validated the ensemble model using the dataset from the University of California, Irvine (UCI) repository to assess its effectiveness. The Individual classifiers achieved different accuracies: Naïve Bayes (85.41%), Support Vector Machine (98.61%), Random Forest (97.91%), Decision Tree (95.13%), Gradient Boosting (95.83%). The stacking method yielded a higher accuracy of 99.30% and a precision of 1.00, recall of 0.96, F1 score of 0.97, and specificity of 1.00 compared to the base models. The study confirms the effectiveness of ensemble learning techniques in classifying ESD.

Every company is obliged to carry out efficiency strategies in every business process in order to continue to exist in today's increasingly fierce competition. This research aims to determine the magnitude of the OEE value and the dominant factors from the six big losses analysis which is used as a proposal for improvements to the cutting machine at PT ABC. The method used is Availability Ratio, Performance Ratio and Rate of Product Quality as basic elements of Overall Equipment Effectiveness and Six Big Losses and analyzed using a fishbone diagram. Calculation results for the period September 2023 to February 2024 obtained an OEE value of 82.58% with the largest contributor to losses being the idling and minor stoppages and Reduce Speed ​​factors. To overcome this, it is necessary to increase skills in identifying and repairing machines, implementing clear standard operating procedures, operator skills in conveying information about machine damage, as well as standard material for parts used by machines.    

This study presents an advanced structural health monitoring (SHM) system for steel bridges based on wireless sensor networks (WSN) integrated with machine learning algorithms. The proposed system monitors and predicts structural integrity under various load conditions. The research focuses on developing a machine learning model capable of real-time anomaly detection, allowing for early warnings of potential failures. Experimental results from both simulation and field tests demonstrate the system’s effectiveness in prolonging bridge lifespan while reducing maintenance costs.

The rapid growth of big data has significantly increased the demand for efficient and scalable data processing methods, particularly within cloud computing environments. This study aims to evaluate the effectiveness of distributed computing frameworks, specifically Apache Hadoop and Apache Spark, in optimizing big data processing. A qualitative approach using a Systematic Literature Review (SLR) method is employed to analyze existing studies related to distributed systems, cloud computing architectures, and performance optimization techniques. The analysis focuses on key performance indicators, including processing speed, resource utilization, and scalability, as well as the suitability of each framework for different data processing scenarios. The findings indicate that Apache Hadoop is highly effective for batch processing and storage-intensive tasks due to its disk-based architecture, while Apache Spark demonstrates superior performance in real-time and iterative processing through its in-memory computing capabilities. Additionally, system configuration factors such as cluster size, memory allocation, and network bandwidth are identified as critical elements influencing overall performance. The study also highlights emerging trends, including the adoption of hybrid cloud environments, the integration of artificial intelligence and machine learning, and the utilization of edge computing to enhance real-time data processing. In conclusion, distributed computing frameworks play a vital role in improving the efficiency and scalability of big data processing in cloud environments. The selection of an appropriate framework, combined with optimized system configuration, can significantly enhance operational performance and support data-driven decision-making.

This article investigates recent innovations in industrial engineering and mechanical systems, emphasizing how technological advancements impact manufacturing efficiency, sustainability, and cost-effectiveness. Through a review of current technologies, such as additive manufacturing, automation, and smart materials, the study assesses the key challenges industries face and forecasts emerging trends in mechanical engineering and industrial innovation. The article also discusses the potential for artificial intelligence and machine learning to revolutionize industry standards and drive forward engineering solutions.

Cloud-based resource allocation and VM/container orchestration play a crucial role in ensuring performance, scalability, and energy efficiency in modern distributed computing environments. This study investigates the effectiveness of centralized and decentralized scheduling models combined with heuristic and optimization-based allocation strategies in container-based cloud infrastructures. A quantitative experimental approach was employed to evaluate system performance under varying workload intensities. Key evaluation metrics included response time, throughput, resource utilization, SLA violation rate, and energy consumption. The experimental results indicate that centralized scheduling mechanisms experience scalability limitations and increased latency under high workload conditions. Although optimization-based allocation improves performance within centralized architectures, coordination bottlenecks remain significant. In contrast, decentralized scheduling models demonstrate superior adaptability, reduced response time, and improved throughput due to distributed decision-making and reduced control overhead. The integration of intelligent optimization techniques further enhances resource utilization and energy efficiency, achieving the lowest SLA violation rates and highest system stability. Overall, the findings confirm that combining decentralized scheduling with optimization-driven resource allocation provides a more scalable and sustainable orchestration strategy for modern cloud environments. This approach is particularly suitable for dynamic, large-scale, and latency-sensitive applications in container-based and edge-integrated cloud systems.