Publication Search

Artificial intelligence (AI) is currently a rapidly developing technology in all fields, particularly in finance and the military. This study aims to examine the application of Artificial Intelligence (AI) technology to support financial report analysis and internal control within Indonesian Navy (TNI AL) work units. Along with the development of information technology, AI has the potential to provide innovative solutions to improve efficiency, accuracy, and transparency in state financial management, particularly in a military environment that demands high accountability. The research method used was descriptive qualitative with a case study approach in several work units within the Indonesian Navy. Data were obtained through interviews, observations, and a review of relevant documents and literature. The results indicate that the use of AI, such as machine learning and data analytics, can identify unusual financial transaction patterns, predict potential irregularities, and improve the effectiveness of internal oversight. However, the implementation of this technology still faces challenges, such as limited digital infrastructure, the need for human resource training, and the need for policies that support sustainable digital transformation. This study recommends the gradual and strategic integration of AI as part of the reform of the Indonesian Navy's financial management system.

Management of household waste in Final Disposal Sites (TPA) faces a serious problem, where most of the waste accumulates and is difficult to decompose due to its complex nature. This condition substantially inhibits natural decomposition processes and limits the effectiveness of recycling efforts. Pre-processing operations, such as sorting and crushing, which are still dominated by manual methods, are proven to be inefficient, high-risk, and require large allocations of land resources and manpower. Therefore, automated technological innovation is needed to facilitate the efficient separation of organic components from inorganic materials (packaging). This research was conducted to determine the design and structural strength analysis of a hammer mill type depackaging machine, carried out using Solidworks software. Structural analysis simulation utilizes Finite Element Analysis (FEA) to determine the structural strength of the machine. The specifications of the hammer mill type depackaging machine include a capacity of 3000 kg/hour, a hammer mill input power of 12 KW, and a rotational speed of 2500 rpm with a torque of 34.54 Nm. Meanwhile, the screw conveyor input power is 0.75 KW and the rotational speed is 20 rpm. The FEA simulation analysis results for the hammer mill type depackaging machine showed that the maximum Von Mises stress value recorded is 3,022×10^7   N⁄m^2 , the maximum displacement value measured is very minimal, namely 2,793×10^(-1)  mm, and the Factor of Safety (FOS) obtained is 8.3. This FOS value significantly exceeds the required minimum safety limit (>3), confirming that the machine design has optimal reliability, fatigue resistance, and structural integrity for operation under intensive working conditions at the TPA. The conclusion of this study indicates that the engineering design of this hammer mill type depackaging machine is safe and meets structural technical requirements to proceed to the implementation phase, potentially becoming a sustainable technological solution in improving the efficiency of waste pre-processing.

The rapid growth of open-source software (OSS) in machine learning (ML) has intensified the need for reliable, automated methods to assess project quality, particularly as OSS increasingly underpins critical applications in science, industry, and public infrastructure. This study evaluates the effectiveness of a diverse set of machine learning and deep learning (ML/DL) algorithms for classifying GitHub OSS ML projects as engineered or non-engineered using a SMOTE-enhanced and explainable modeling pipeline. The dataset used in this research includes both numerical and categorical attributes representing documentation, testing, architecture, community engagement, popularity, and repository activity. After handling missing values, standardizing numerical features, encoding categorical variables, and addressing the inherent class imbalance using the Synthetic Minority Oversampling Technique (SMOTE), seven different classifiers—K-Nearest Neighbors (KNN), Decision Tree (DT), Random Forest (RF), XGBoost (XGB), Logistic Regression (LR), Support Vector Machine (SVM), and a Deep Neural Network (DNN)—were trained and evaluated. Results show that LR (84%) and DNN (85%) outperform all other models, indicating that both linear and moderately deep non-linear architectures can effectively capture key quality indicators in OSS ML projects. Additional explainability analysis using SHAP reveals consistent feature importance across models, with documentation quality, unit testing practices, architectural clarity, and repository dynamics emerging as the strongest predictors. These findings demonstrate that automated, explainable ML/DL-based quality assessment is both feasible and effective, offering a practical pathway for improving OSS sustainability, guiding contributor decisions, and enhancing trust in ML-based systems that depend on open-source components.

This study examines the effectiveness of the Early Warning System (EWS) in anticipating and responding to mental health crises in conflict-affected regions of the Middle East through a systematic review of 47 scholarly articles published between 2014 and 2024. The meta-regression findings indicate a significant contribution of EWS implementation to the reduction of post-traumatic stress disorder (PTSD) symptoms with a coefficient of β = -0.67 (p < .001), as well as depressive symptoms with a coefficient of β = -0.59 (p < .001) among populations directly affected by armed conflict. Among 12,456 respondents analysed, 73.8% reported a reduction in anxiety symptoms following the implementation of EWS, with an effect size of d = 0.82 (95% CI [0.76, 0.88]). Digitally based early warning systems demonstrated a significantly higher level of effectiveness (OR = 2.34, 95% CI [1.98, 2.70]) than conventional systems, which are more manual and reactive. Moderator analysis indicated that age (β = -0.31, p < .01) and the duration of exposure to conflict (β = 0.44, p < .001) play important roles in moderating the relationship between EWS interventions and various mental health indicators. These findings expand upon the conclusions of Fu et al. (2020) and Salesi (2023), which previously explored psychosocial interventions in conflict zones, by adding a new dimension—examining digital technology and predictive algorithms within EWS frameworks. The study explicitly demonstrates that integrating machine learning models into EWS can enhance the predictive accuracy of potential mental health crises to 84.6%, representing a novel contribution that has not been comprehensively documented in prior academic literature

This research aims to identify potential hazards and assess the level of fire risk in a textile company located in Sukoharjo Regency using the Hazard Identification, Risk Assessment, and Risk Control (HIRARC) method. The research background is based on the high fire hazard potential in the textile industry due to the use of flammable chemicals, high operating temperatures, and the accumulation of combustible fibers and textile dust. A descriptive research approach was applied through field observations, interviews with workers and the OHS team, and technical document analysis. The results showed that the highest risk levels were found in the dyeing process, electrical panel room, and machine maintenance activities (welding/repair), with risk scores reaching 20 (high category). The main contributing factors included non-standard electrical installations, poor ventilation, and unsafe work behavior. Risk control strategies are recommended through technical, administrative, and behavioral approaches, including smoke detection systems, routine evacuation training, and the reinforcement of safety culture. The implementation of these measures is expected to improve the effectiveness of occupational health and safety management systems and reduce the potential for fire incidents in the textile industry.

Millions of people suffer from malaria, one of the most serious parasitic diseases that threatens human life and causes high rates of morbidity and mortality, particularly in tropical and subtropical regions. Traditional diagnostic methods, such as blood smear examination, which can be performed using a microscope, face many challenges due to the inaccuracy of manual analysis and the reliance on individual skills. Therefore, the use of machine learning or deep learning algorithms to automate malaria detection offers promising solutions to improve accuracy, reduce diagnosis time, and enhance scalability. In this paper, a multi-class convolutional neural network (CNN)-based model is designed to classify cells infected with Plasmodium falciparum (P. falciparum) and Plasmodium vivax (P. vivax) and uninfected cells from blood smears, as most severe cases and deaths are caused by P. falciparum and P. vivax. This is achieved by building and training a CNN from scratch, rather than using transfer learning from pre-trained models. The proposed network was trained and tested on the Kaggle dataset, which consists of 27,558 images of infected and uninfected individuals. These images were divided into 13,779 images of uninfected individuals, 6,890 images of individuals with P. falciparum malaria, and 6,889 images of individuals with P. vivax malaria. The images were preprocessed using several operations, including blurring, denoising, and morphological processing. The proposed model achieved the best evaluation accuracy when compared with other deep learning algorithms, with an accuracy rate of 96.5%, a sensitivity rate of 95%, a specificity rate of 97.6%, and an F1-score rate of 96.5%. These results demonstrate the effectiveness of the proposed model as a tool to assist clinicians in malaria diagnosis, reducing reliance on manual analysis.

Hemodialysis is a medical procedure used to correct blood biochemical abnormalities caused by impaired kidney function, with the aid of a hemodialysis machine. One of the most commonly used accesses in this procedure is the Arteriovenous Fistula (AVF), which is an anastomosis between the artery and vein in the arm or other parts of the body to facilitate the cannulation process. However, during the AVF cannulation procedure, patients often experience pain, which can cause discomfort and anxiety. Cold compresses are one of the non-pharmacological techniques that can be used to alleviate this pain. This study aims to examine the effect of cold compresses on reducing pain during AVF cannulation in hemodialysis patients. This research uses a Quasi-Experimental design with a Pretest-Posttest Control Group Design model, involving 116 hemodialysis patients at RSI Sultan Agung Semarang. Patients were divided into two groups: the intervention group, which received cold compresses, and the control group, which did not receive treatment. Pain intensity was measured before and after cannulation using a visual analog scale (VAS). The results of the study show that the administration of cold compresses significantly reduced pain intensity, with a p-value of 0.000 (< 0.05). In addition, there was a significant difference in effectiveness between the intervention group and the control group, with the same p-value. In conclusion, cold compresses proved to be an effective, simple, safe, and easy-to-apply non-pharmacological intervention to reduce pain in hemodialysis patients during the AVF cannulation procedure. Therefore, the use of cold compresses can be recommended as a method to improve the comfort of hemodialysis patients.

PT. Lotus Indah Textile Industries, a manufacturing company in the open-end yarn spinning sector, faces significant issues related to defective products in its production process. This study aims to identify the level of human error among open-end machine operators and analyze the root causes of these errors. The methods employed include the Human Error Assessment and Reduction Technique (HEART) to calculate the Human Error Probability (HEP), as well as Root Cause Analysis (RCA) with the 5 Whys approach to identify the root problems. Data were collected through observation, interviews, and questionnaires during the period of May to June 2025. The results indicate that the activity of "pushing the full yarn so that it detaches from the holder and moves to the conveyor with the right hand" had the highest HEP value of 0.281996. The main root causes of human error include a lack of focus and accuracy among operators, rushing while working, limited experience, and insufficient training and periodic evaluations of employee effectiveness by the company. The impact of these errors results in defective products such as dirty yarn and rolls that do not meet standards. As an improvement recommendation, the company is advised to conduct periodic evaluations of operator effectiveness after training to enhance productivity and provide feedback, as well as to establish clear procedures for the doffing process of yarn on open-end machines to reduce errors. This study is expected to assist the company in improving operator performance, reducing human error rates, and minimizing defective products.

Human Resource Management (HRM) plays a strategic role in improving organizational competitiveness through proper management of employee placement, training, and performance evaluation. To support the achievement of these goals, a predictive model is needed that can provide an accurate picture of employee performance. This study utilizes a Human Resource Management (HRM) dataset of 1,200 data and applies several classification algorithms to compare their effectiveness, namely J48 or C4.5, Random Forest, Naive Bayes, K-Nearest Neighbor (KNN), Logistic Regression, and Support Vector Machine (SVM). To obtain more optimal results, this study uses resampling techniques and attribute selection methods with a correlation attribute eval approach, so that class distribution can be more balanced and model accuracy increases. From the test results, the Decision Tree J48 algorithm showed the best performance with an accuracy level reaching 95.41%, a kappa value of 0.8925, a mean absolute error (MAE) of 0.0432, a precision of 0.955, a recall of 0.954, and an area under the ROC curve of 0.964. These findings indicate that J48 has excellent predictive capabilities compared to other algorithms. Furthermore, this study also found that the most influential variables in determining employee performance include the percentage of the last salary increase (EmpLast Salary Hike Percent), the level of work environment satisfaction (Emp Environment Satisfaction), the length of time since the last promotion (Years Since Last Promotion), and experience in the current role (Experience Years in Current Role). Overall, the results of the study indicate that the C4.5 algorithm with the application of the resampling technique can be an optimal solution in building an employee performance prediction system. Thus, this model has the potential to be a strong basis for managerial decision-making, particularly in designing HR development strategies and policies to improve organizational performance.

Electricity has emerged as an essential requirement in modern life. As demand escalates, electricity costs rise, making wastefulness a drain on financial resources. Consequently, forecasting electricity usage can enhance our management of consumption. This study presents an IoT-based monitoring and forecasting system for electricity consumption. The system comprises two NodeMCU micro-controllers, a PZEM-004T sensor for collecting real-time power data, and three relays that regulate the current flow to three distinct electrical appliances. The data gathered is transmitted to a web application utilizing the k-Nearest Neighbor (k-NN) algorithm to forecast future electricity usage based on historical patterns. We evaluated the system's performance using four weeks of electricity consumption data. The results indicated that predictions were most accurate when the user’s daily consumption pattern remained stable, achieving a Mean Absolute Error (MAE) of approximately 1 watt and a Mean Absolute Percentage Error (MAPE) ranging from 1% to 1.7%. Additionally, predictions were notably precise during the early morning hours (3:00 AM to 8:00 AM) when k=6 was employed. This study demonstrates the effectiveness of integrating IoT-based systems with machine learning for real-time energy monitoring and forecasting. Furthermore, it emphasizes the application of data mining techniques within embedded IoT environments, providing valuable insights into the implementation of lightweight machine learning for smart energy systems.

Delivery delays pose a major challenge in the e-commerce industry, often leading to decreased customer satisfaction and negatively impacting business operations. In this study, the XGBoost (Extreme Gradient Boosting) algorithm is applied to predict delivery delays based on a dataset containing 96,476 records. These records include various features relevant to the delivery process, such as shipping distance, carrier performance, and order characteristics. The model achieves a high overall accuracy of 93.24%, indicating strong general performance. In particular, XGBoost demonstrates excellent results in predicting on-time deliveries, achieving a precision of 93% and a recall of 100%. However, the model struggles to correctly identify delayed deliveries. The recall for delayed deliveries is 0%, and the F1-score is extremely low at 0.01. This significant discrepancy reveals a critical limitation in the model's performance — the inability to detect minority class cases (delayed deliveries) due to class imbalance within the dataset. The results highlight the importance of addressing data imbalance in predictive modeling for delivery outcomes. When the dataset is dominated by on-time delivery records, the model tends to be biased toward that class, failing to learn the patterns associated with delays. To improve performance, the study recommends integrating class balancing techniques such as SMOTE (Synthetic Minority Oversampling Technique) to generate synthetic samples of the minority class. Additionally, the use of alternative evaluation metrics beyond accuracy — such as precision, recall, and F1-score for each class — is suggested to provide a more comprehensive understanding of model effectiveness. Overall, the study provides valuable insights into the complexities of predicting delivery delays and outlines practical strategies for enhancing future models in e-commerce logistics analytics.

This study aims to explore students' perceptions of creating digital video projects as a tool for teaching and improving speaking abilities. A descriptive qualitative research design was applied, involving 50 students enrolled in the Intermediate English course during the second semester of the Machine Automotive Study Programme at Politeknik Negeri Jember. Data collection techniques included questionnaires distributed via Google Forms, consisting of multiple-choice and open-ended questions, complemented by semi-structured interviews to gain deeper insights. The focus was on understanding how students perceive the effectiveness of digital video projects in enhancing their speaking skills and overall language learning experience. The findings revealed that most students had a positive attitude toward creating digital video projects, stating that such activities significantly enhanced their confidence, fluency, and pronunciation in English. Many participants emphasized that digital video projects encouraged them to practice speaking repeatedly, which contributed to reducing anxiety and improving their performance. The study also found a clear connection between students' intrinsic motivation to improve their speaking skills and the perceived benefits of completing digital video tasks. Additionally, students highlighted the creative aspect of video-making, which fostered collaboration, critical thinking, and self-expression. The role of the lecturer was identified as crucial in guiding students throughout the project, particularly in overcoming technical and linguistic challenges. The study concludes that integrating digital video projects into speaking lessons not only improves speaking ability but also motivates learners to take active participation in language learning.

This study aims to analyze the effectiveness of preventive maintenance on the Simplex machine at PT. XYZ by applying the Overall Equipment Effectiveness (OEE) method and identifying the primary causes of production losses through the Six Big Losses framework. Preventive maintenance is an important strategy to ensure machine reliability, reduce downtime, and improve production efficiency. OEE is a widely recognized performance measurement tool consisting of three key indicators: Availability, Performance, and Quality. These indicators collectively reflect the overall effectiveness of equipment in supporting the production process. The results of this study indicate that the OEE value of the Simplex machine is 79%, which remains below the world-class benchmark of 85% as recommended by the Japan Institute of Plant Maintenance (JIPM). This finding suggests that the machine’s performance has not yet reached the optimal standard and requires improvement efforts. Further analysis using the Six Big Losses approach reveals that the most significant contributors to reduced machine effectiveness are equipment failure and idling or minor stoppages. These two categories account for the majority of productivity losses, thereby affecting both machine utilization and production output. To further explore the underlying issues, a root cause analysis was conducted using a fishbone diagram, which enabled the identification of several critical factors related to human resources, methods, machines, materials, environment, and measurement systems. Based on this analysis, improvement proposals were developed through the 5W+1H method, providing a systematic strategy to enhance preventive maintenance practices. The recommended actions include scheduling more frequent inspections, improving operator training, upgrading spare parts management, and implementing stricter monitoring of machine performance. In conclusion, this study highlights the importance of continuous preventive maintenance to optimize machine productivity and reduce unplanned downtime. By adopting the proposed improvement strategies, PT. XYZ can increase the effectiveness of its Simplex machine, moving

The continuous operation of airlock machines in wheat milling facilities plays a critical role in the material handling system, especially in the transfer of grain from ships to silo storage. At PT XYZ, the airlock machine has been identified as the equipment with the highest frequency of downtime over a three-month observation period, leading to significant disruptions in production flow and increased corrective maintenance costs. This study aims to analyze the failure modes of the airlock machine using the Failure Mode and Effect Analysis (FMEA) method and to develop preventive maintenance recommendations based on the highest Risk Priority Number (RPN) values. The research adopts a quantitative descriptive approach, involving field observations, interviews with maintenance personnel, historical breakdown analysis, and machine technical documentation review. The FMEA results indicate that the seal, gear, and bearing are the most critical components, with RPN values of 224, 210, and 192, respectively. These components are prioritized for preventive actions such as regular seal replacement, scheduled lubrication, gear inspections, and motor monitoring. Simulation of the proposed maintenance strategy demonstrates a 66.7% reduction in downtime, from 18 hours to 6 hours per month, and a 43.7% reduction in total maintenance costs, from Rp 9,034,500 to Rp 5,087,500 monthly. These results validate the effectiveness of the FMEA method in identifying risk-prone components and optimizing maintenance planning. It is recommended that PT XYZ institutionalize periodic FMEA updates and establish a cross-functional analysis team to continuously monitor and improve equipment reliability.

The electronic medical record (EMR) is an important step in supporting the digitization of health services, with the aim of improving the effectiveness, efficiency and accuracy of the management of patient medical data in hospitals. This study aims to determine the readiness of the implementation of RME in BUDIASIH Hospital Trenggalek by using the Fishbone Diagram method as an analytical tool in identifying the factors that influence.This study uses a descriptive method with a qualitative approach to explore the implementation process in depth. The Data was obtained through in-depth interviews and direct observation to 20 informants who actively use the RME system in the implementation of daily tasks.The results showed that the readiness of RME implementation in Budi Asih Hospital was influenced by five main factors, namely man (Human Resources), matherial (tools), machine (data), method (methods), and money (budget). Health workers and administrative staff have been able to operate RME well, accompanied by regular training and workshops to improve understanding related to System updates. Equipment and support systems are available and functioning properly, along with scheduled maintenance to keep the system running stably. Data management has been done accurately and timely, supported by periodic audits to maintain the quality and validity of the data. The hospital also has a clear Standard Operating Procedure (SOP) I n the implementation of RME and has allocated a budget to support the sustainability of this system. Overall, Budi Asih Trenggalek Hospital has shown good readiness in the implementation of RME and is ready to develop this system to support the improvement of the quality of health services in the future.This study recommends increased maintenance of software and hardware as well as regular training of human resources to support the sustainability of the RME system.  

This study explores the development and application of a digital twin-driven cybersecurity risk assessment model for Industrial Internet of Things (IIoT) networks. The increasing complexity and interconnectivity of IIoT systems have expanded the attack surface, making them vulnerable to a wide range of cyber threats. The digital twin model addresses this challenge by creating real-time virtual replicas of physical systems, which can simulate and predict network vulnerabilities and attack vectors. The model uses machine learning algorithms and real-time data to simulate cyberattacks, including Distributed Denial of Service (DDoS), malware, and data breaches. By providing continuous monitoring and dynamic risk predictions, the digital twin model enhances the resilience of IIoT networks compared to traditional cybersecurity frameworks. The findings indicate that the model's ability to predict potential cyber threats and simulate various attack scenarios provides a more proactive and accurate approach to cybersecurity in IIoT environments. Additionally, the study highlights key mitigation strategies, including adaptive security mechanisms, real-time anomaly detection, and the use of lightweight encryption for resource-constrained devices. Despite its effectiveness, challenges such as computational requirements, integration with legacy systems, and scalability were identified. This research underscores the strategic importance of digital twin models in securing IIoT systems and advancing Manufacturing 4.0 ecosystems. Future research should focus on enhancing model accuracy, expanding its application to diverse industrial sectors, and improving interoperability with legacy systems to further strengthen the security posture of IIoT networks.

Along with the increasing threat of cybercrime, which is predicted to cause losses of up to US$10.5 trillion by 2025 , penetration testing (pentest) has become a crucial strategy for identifying security vulnerabilities. However, the manual pentest process is often time-consuming. This research aims to analyze the role, effectiveness, and challenges of Generative AI (GenAI), specifically GPT-4.1, in accelerating and optimizing the penetration testing process. This research method uses a qualitative approach with a case study on the "PumpkinFestival" VulnHub machine , where GPT-4.1 is integrated into the Kali Linux environment through the ShellGPT tool. The results show that GPT-4.1 can significantly accelerate all stages of the pentest, from reconnaissance to exploitation. GenAI proved effective in analyzing scan results, composing specific payloads, and creating decryption scripts quickly and accurately , while also filling a research gap by evaluating a newer AI model compared to previous studies. The implication is that the integration of GenAI in cybersecurity has great potential to increase the efficiency and effectiveness of security teams in facing increasingly complex threats.

Digitalization of transaction documents is a process of transferring transaction document media using a scanner. Digitalization of transaction documents is one of the supports for the efficiency of petty cash vouching procedures that have been implemented from 2025. The purpose of this research is to evaluate that implementation of transaction document digitization and assess the extent to which digitization is able to support the effectiveness of the petty cash vouching process. This research uses a descriptive qualitative method to obtain in-depth information about how the implementation of the digitization of petty cash transaction evidence. Interviews were conducted with 3 FAT (Finance, Accounting, Tax) staff. human resources, funds, machine tools, work methods, and document conditions are factors that support the implementation of digitization of transaction documents. In addition, in its implementation, there are still some obstacles that occur such as the absence of fixed procedures in digitizing proof of transactions, lack of human resources for the implementation of digitizing transaction documents, dependence on scanner devices, and systems that have not been integrated.

The development of digital printing technology requires machines with high reliability and efficiency. The AccurioPress 6100 is a widely used digital printing machine that offers a speed of up to 100 pages per minute. However, the machine’s Overall Equipment Effectiveness (OEE) at PT. OctoPrint only ranged from 45% to 53%, which is below the industry standard of 85%. This study identifies the gap in machine efficiency and proposes solutions based on OEE analysis involving Availability, Performance, and Quality indicators. The study adopts a descriptive quantitative method, collecting data through direct observation and interviews over a 14-week period. Preventive maintenance strategies were implemented to improve machine performance. The results showed an increase in OEE to 60–63%, supported by improvements in Mean Time To Failure (MTTF) and reductions in Mean Time To Repair (MTTR).

This research aims to evaluate the impact of communication technology on customer satisfaction through the implementation of digital marketing strategies at CV Sinar Anugrah Machinery. Using a quantitative approach, data were collected from 112 customers using the proportionate stratified random sampling method to obtain a balanced representation. The analysis was conducted using the Partial Least Squares (PLS) approach with the SmartPLS software. The research results reveal that communication technology directly contributes positively to customer satisfaction and affects the effectiveness of digital marketing strategies. In addition, digital strategies have proven capable of increasing consumer satisfaction levels. This conclusion shows that the integration of communication technology in digital marketing can strengthen relationships with customers and increase loyalty. From a practical standpoint, companies are advised to continue leveraging the latest technology and strengthening their digital strategies to create superior customer experiences and maintain competitiveness in the ever-evolving market.