Publication Search

Background: Structural Health Monitoring plays a critical role in ensuring the safety, reliability, and sustainability of high performance composite structures used in aerospace, civil infrastructure, and mechanical systems. Conventional externally mounted sensors often face challenges related to environmental interference, maintenance complexity, and long term stability. Objective: This study aims to develop and validate an integrated smart composite monitoring system with embedded sensing capabilities that enhances damage detection accuracy and operational durability under varying mechanical stress conditions. Method: Smart composite specimens were fabricated by embedding fiber optic and piezoelectric sensors within fiber reinforced polymer laminates, followed by tensile, fatigue, and vibration testing. Signal processing techniques including time frequency analysis were applied to extract damage sensitive features, which were then classified using machine learning algorithms to distinguish healthy and damaged structural states. Results: The experimental findings demonstrate high damage detection capability, stable sensor performance under cyclic loading, improved reliability compared to conventional monitoring approaches, and consistent monitoring accuracy throughout the fatigue life of the specimens. The integration of embedded sensing and data driven analytics significantly enhances structural response interpretation and supports predictive maintenance strategies.

Urinary incontinence (UI) is a significant health issue among the elderly, affecting their quality of life. While its etiology is multifaceted, metabolic and nutritional markers such as diabetes panel parameters and albumin levels may play a role in its severity. However, the relationship between these biomarkers and UI remains underexplored. This study aims to investigate the association of diabetes panel components and albumin levels with the severity of UI in elderly individuals to identify potential predictors. A cross-sectional analytic study was conducted involving 93 elderly participants from Bina Bhakti Nursing Home. UI was assessed using the International Consultation on Incontinence Questionnaire-Urinary Incontinence Short Form (ICIQ-UI SF). Metabolic markers were analysed using validated methods, including fasting glucose, HbA1c, fasting insulin, HOMA-IR, and albumin. Data were statistically analyzed using Spearman’s Rho and multiple regression analyses to determine correlations and predictive relationships. Significant correlations were observed between HbA1c (r = -0.284, p = 0.006) and albumin (r = -0.259, p = 0.012) with UI severity. Multiple regression analysis confirmed that HbA1c and albumin are significant predictors of UI, with lower levels associated with increased UI severity. Diabetes panel parameters, particularly HbA1c and albumin levels, are valuable predictors of UI severity in elderly individuals. These findings emphasize the importance of metabolic and nutritional health monitoring in managing and mitigating UI symptoms. Future longitudinal studies and intervention trials are recommended to validate these findings and explore therapeutic implications.

This study uses a qualitative method to explore how social media listening, combined with a machine learning approach, can be utilized to predict consumer trends in modern marketing strategies. In today’s digital era, social media serves as a rich data source for capturing consumer preferences, needs, and behaviors in real time. With machine learning algorithms such as natural language processing (NLP) and sentiment analysis, data from platforms like Twitter, Instagram, and TikTok can be processed to identify patterns that indicate market trends. This approach not only enables companies to respond quickly to consumer dynamics but also allows them to craft more targeted and data-driven marketing strategies. This study examines five major brands that implement social media listening as part of their digital strategy by observing consumer conversations, dominant emotions, and viral issues. The findings show that the integration of social media listening and machine learning can serve as an effective predictive tool in developing adaptive and contextual marketing campaigns.

This study systematically analyses the predictive ability financial ratios have in relation to the emergence of financial distress among non-cyclical companies on the Indonesia Stock Exchange during the period 2020-2023. Secondary data was collected from a sample of 151 secondary data companies listed on the Indonesia Stock Exchange, spanning the years from 2020 to 2023. In order to ascertain the relationship between the independent variables (X1, X2, X3) and the dependent variable, Multiple Linear Regression models are utilised by employing the Eviews calculation application. As a model, the Springate model is employed, which is used to measure financial distress. The financial ratios selected for analysis encompass the liquidity ratio, the leverage ratio, and the profitability ratio. The findings of this study suggest that the profitability ratio exerts a substantial positive effect, or a moderate effect, on the phenomenon of financial distress. In contrast, the liquidity ratio and leverage ratio demonstrate an absence of statistically significant influence on the phenomenon of financial distress. Extensive analysis of the results indicates that financial distress, as measured by Springate, does not exert a substantial influence on the findings obtained from this study. The incorporation of diverse samples and models in subsequent studies is likely to introduce variations into the research outcomes.

The development of information technology is also growing rapidly. One of the sectors that is also affected is transportation. This study aims to analyze the Influence of Trust, Online Customer Reviews, and Discounts on Purchasing Decisions Through Purchase Intention where the Intervening Variable is Gofood users on the Gojek application. The analysis method is quantitative primary data, with the test stages of convergent validity, Discriminant validity, average variance extracted (AVE), R-Square, predictive relevance (Q2), F-Square, path coefficient, specific indirect effect. Data were obtained through a questionnaire instrument, with a total of 175 respondents, which were then tested using SmartPLS 4.0. The research findings show that the Trust and Discount variables partially influence Purchasing Decisions through Purchase Intention of Gofood users on the Gojek application. Meanwhile, the Online Customer Review variable does not partially influence Purchasing Decisions through Purchase Intention of Gofood users on the Gojek application.

This multilayer meta-analysis investigates the intersectionality between gender, social class, and war-related trauma in the Middle East through a systematic review of 87 studies (N = 31,459) published between 2000 and 2023. Analytical findings reveal a strong and significant correlation between gender and trauma severity (r = 0.67, p < 0.001), with women experiencing a 2.8 times higher prevalence of PTSD compared to men. Furthermore, results from hierarchical regression demonstrate that social class functions as a substantial moderator (β = 0.45, p < 0.001), with individuals from lower social class backgrounds exhibiting a 3.2 times greater risk of trauma. Further structural path analysis reveals the presence of dual mediation (CFI = 0.96, RMSEA = 0.04), with access to mental health services and social support serving as primary mediators (indirect effect = 0.38, 95% CI [0.29, 0.47]). These results expand the contributions of Al-Krenawi and Graham (2012) and Mangrio et al. (2019) by illustrating the complex interaction of the three dimensions (Gender, Social Class, and War Trauma), which had previously been examined only separately. In addition, this study identifies a new pattern termed the "spiral trauma effect," a mechanism wherein the intersectionality of gender, social class, and trauma mutually reinforce each other in a recurring cycle (effect size d = 0.89), thereby deepening the understanding of trauma dynamics in conflict zones across the Middle East. Finally, the predictive model developed in this research demonstrated an accuracy rate of 84.3% in identifying high-risk individuals. Thus, these results are considered to provide an innovative framework for the development of empirically-based trauma interventions in Middle Eastern war zones.

Research aims to design and develop a boiler system for heating Marine Fuel Oil (MFO) 180 CST by integrating Internet of Things (IoT) technology to enhance efficiency and operational monitoring. The methods used include boiler system design, selection of types and materials according to international standards, and the implementation of an optimal combustion system. IoT sensors are strategically placed to monitor key parameters such as temperature, pressure, and fluid flow in real-time. The collected data is transmitted to a cloud platform, enabling remote monitoring and automated performance analysis through a web or mobile-based application.. The research results indicate that IoT integration in the boiler system improves fuel heating efficiency, optimizes energy consumption, and facilitates easier monitoring and process control. Testing includes pressure tests, combustion efficiency, steam capacity, and material durability, with real-time monitoring to support performance analysis and early problem detection. Operational data evaluation allows for design adjustments or system settings to further enhance energy efficiency. With this innovation, the boiler system can operate more optimally, support energy efficiency, and facilitate predictive maintenance for sustainable industrial operations. The implementation of IoT in this system is expected to improve safety, effectiveness, and automation in boiler management, making it a more reliable and modern solution.

This literature review presents a synthesis of the latest research results regarding temperature measurement techniques, including sensor technology, calibration methods, and their applications in various industries. This analysis highlights advances in the use of infrared thermometry, thermocouple-based systems, as well as digital temperature monitoring tools. Key innovations in this field include real-time temperature monitoring with IoT integration, artificial intelligence (AI)-based predictive modeling, as well as increased accuracy through statistical calibration methods. This study shows that non-contact temperature measurement methods are increasingly important, especially in industrial and medical applications. In addition, the research also highlights the influence of environmental factors on temperature measurement accuracy as well as various strategies to overcome obstacles in using sensors in various operational conditions.

Introduction: The integration of Digital Twin (DT) technology and the Internet of Things (IoT) into Building Energy Management Systems (BEMS) offers a transformative approach to optimizing energy consumption in buildings. This study explores the development of a Digital Twin based BEMS prototype, which leverages real time data collection, predictive analytics, and machine learning to enhance energy efficiency, reduce costs, and support sustainability goals in modern buildings. The research also addresses key gaps in current energy management systems, including real time adaptive control and integration with smart grid platforms. Literature Review: Previous research highlights the limitations of traditional BEMS, which often rely on static control strategies and lack real time adaptability. Recent advancements, including predictive maintenance and machine learning integration, have improved energy optimization. However, challenges such as data interoperability, scalability, and cybersecurity remain. This review consolidates current approaches and identifies opportunities for enhancing BEMS through the integration of DT technology, IoT, and machine learning. Materials and Method: The methodology employed involves the design of a Digital Twin based BEMS prototype, incorporating IoT sensors for real time data collection on variables such as HVAC load, occupancy, and environmental factors. The system uses time series forecasting and adaptive control strategies to optimize energy consumption. A case study building is used for validation, with performance metrics such as energy savings, CO₂ footprint reduction, and peak load reduction assessed to evaluate the system's effectiveness. Results and Discussion: The results demonstrate a significant reduction in energy consumption (up to 50%) compared to traditional BEMS, along with improved forecasting accuracy and sustainability performance. The prototype achieved a high R² score in predicting energy usage, validated through real world application in the case study building. The economic feasibility analysis showed substantial cost savings and a strong return on investment, making the system a financially viable solution for energy efficient building management.

The development of vocational education requires Vocational High Schools (SMK) to align their competencies with student interests and industry needs. However, a mismatch between student interests and the competencies offered can result in low enrollment, requiring schools to consider closing certain programs. This study proposes the application of Artificial Neural Networks (ANNs) as a predictive method to determine the potential closure of vocational competencies based on an analysis of student interest patterns. The data used includes interest history, academic grades, and other preference indicators, which are then subjected to a preprocessing stage to ensure the quality of the model’s input. The ANN is trained to accurately recognize interest patterns, thus generating objective and adaptive decision-making recommendations. The results show that the ANN implementation provides high accuracy in predicting student interest trends and provides more precise The development of vocational education in Vocational High Schools (SMK) requires the ability to align skill competencies with students' interests and industry needs. A mismatch between students' interests and the competencies offered can lead to low interest in certain programs, which in turn may result in the decision to close those programs. This study proposes the application of Artificial Neural Networks (ANN) as a predictive method to determine the potential closure of skill competencies based on the analysis of students' interest patterns. The data used includes interest history, academic grades, and other preference indicators. This data is processed through a preprocessing stage to ensure the quality of input for the model. The ANN is trained to accurately recognize students' interest patterns, allowing it to generate more objective and adaptive decision recommendations. The results of the study show that the application of ANN has high accuracy in predicting students' interest trends and provides more precise recommendations compared to traditional methods. Therefore, this system can be an effective tool for schools to plan curriculum policies more strategically and sustainably, as well as support decisions regarding skill programs that align with students' interests and industry needs.  

This study explores the integration of AI-driven process optimization in Waste-to-Energy (WtE) systems to enhance urban sustainability. The research focuses on designing a gasification-based WtE system, incorporating AI predictive control to optimize energy conversion processes. The AI system adjusts operational parameters in real-time, improving energy conversion efficiency by 25% and reducing carbon emissions by 40%. Additionally, the system's waste-to-energy conversion rate is projected to increase by 20%, and operational costs are expected to decrease by 30%. Data collection and analysis are carried out using advanced sensors to monitor key parameters such as temperature, gas composition, and energy output, which are then processed by machine learning algorithms for predictive analysis. The results show that the AI optimization significantly enhances system performance, offering a sustainable solution for urban waste management. The study highlights the technical and operational challenges of integrating AI into existing WtE systems, including the need for infrastructure upgrades and scalability considerations. It also discusses the socio-economic impacts, including job creation, reduced energy costs, and improved public health. The findings demonstrate the potential of AI-based WtE systems in reducing waste, generating clean energy, and mitigating climate change, positioning them as a viable solution for sustainable urban development.

The transformer is an important component, and early detection of potential failures plays an important role in the reliable operation of the electric power system. This article describes a new approach to power transformer failure prediction based on dissolved gas analysis (DGA) by applying the TDCG method with  the Random Forest algorithm. DGA data from operational transformers is used to train and test predictive models. The random forest  method based on TDCG allows comprehensive analysis of changes in dissolved gases in transformer oil, thus enabling early detection of failure conditions. The experimental results show that  the prediction model uses a model created by applying hyperparameter tuning for optimal  parameter tuning to have high accuracy, accuracy is obtained up to 96% in detecting potential failures, the standard used for accuracy presentation uses confusion matrix as the accuracy of the prediction model. In addition, it can optimize time efficiency in analyzing failures and prevent human error when calculating gas fault  identification or potential failures.

Indonesia, as an archipelago, has significant agricultural potential, but its optimal utilization requires balancing rice production volume with the available harvest area. This study analyzed the contribution of harvested area to rice production in Gorontalo Regency using linear regression analysis. The data used included the harvest area and the amount of rice production during the period 2018–2024, sourced from the Central Bureau of Statistics (BPS) of Gorontalo Province. The independent variable in this study was the amount of rice production (tonnes), while the dependent variable was the area of harvest (Ha). The analysis results revealed a very strong linear relationship between the two variables, with a correlation coefficient (R) of 0.8437 and a coefficient of determination (R²) of 0.7119. The regression equation indicated that an increase in rice production by 4.8891 tonnes corresponded to an increase in the harvested area by 1 hectare. The model significance value of 0.017017 indicated that the regression model was statistically significant. This finding demonstrates that the amount of rice production significantly affects the area of harvest, and the model can serve as a predictive basis for planning agricultural sector policies in Gorontalo Regency.

Introduction: Achieving carbon neutrality in industrial systems is essential for mitigating climate change and promoting sustainability. The increasing demand for energy optimization and carbon emission reduction has driven the development of advanced technologies, particularly hybrid machine learning (ML) models. These models, combining ensemble learning and reinforcement learning (RL), offer significant promise in optimizing industrial processes, reducing energy consumption, and improving environmental performance. This study explores the application of hybrid ML models in achieving carbon neutral goals through dynamic process optimization and energy control in industrial settings. Literature Review: Hybrid ML models integrate different machine learning techniques to handle complex and dynamic environments effectively. Ensemble learning methods, such as boosting, bagging, and stacking, combine multiple algorithms to improve predictive performance and robustness. Reinforcement learning (RL), on the other hand, enables real time decision making and adaptation based on trial and error interactions with the environment. In energy optimization, these models are used to reduce energy intensity and carbon emissions, enhancing overall operational efficiency. Previous studies have demonstrated the effectiveness of ML models in energy management, but challenges such as data quality, model integration, and computational complexity remain. Materials and Method: The study applies hybrid ML models combining ensemble learning and RL to optimize energy consumption and minimize carbon emissions in industrial processes. Data from real time sensors and operational parameters are used to train the models. The ensemble learning component improves the accuracy of energy predictions, while RL ensures dynamic process adjustments in response to fluctuating energy demand. The models were tested in various industrial settings, including manufacturing processes, smart grids, and microgrid systems. Performance metrics such as energy efficiency, carbon emissions reduction, and operational costs were evaluated to assess the effectiveness of the models.  Results and Discussion: The hybrid ML models achieved significant reductions in energy intensity (15-20%) and carbon emissions (18-25%). The real time adaptability of the RL component allowed the models to adjust energy consumption patterns dynamically, improving energy efficiency and reducing waste. The models demonstrated their ability to adapt to varying operational conditions, ensuring optimal energy use. A cost-benefit analysis showed that the hybrid models provided substantial energy savings and reduced operational costs, with a return on investment (ROI) of 30-35% within the first year of deployment. However, challenges such as computational complexity and data quality issues were identified, highlighting the need for further refinement in model development.

Subcutaneous fat deposition is a key factor influencing overall health, playing a significant role in metabolic regulation, energy balance, and the risk of chronic diseases such as obesity and cardiovascular conditions. Understanding and accurately predicting subcutaneous fat accumulation is critical for early intervention and effective management of these health risks. This study aims to analyze the correlation between hemoglobin levels, uric acid, and anthropometric parameters as predictors of subcutaneous fat deposition in elderly individuals. A cross-sectional study was conducted on 32 elderly participants at St. Asisi Church. Anthropometric measurements, including body weight, height, muscle composition, and circumferences, were assessed using OMRON Body Composition Monitor HBF-375, elastic tape and GEA Medical HT721. Biochemical tests for hemoglobin and uric acid levels were performed using Fora 6 Plus. Spearman correlation analysis was used to evaluate the relationship between these variables and subcutaneous fat deposition. Body weight, upper arm circumference, abdominal circumference, and calf circumference showed strong positive correlations with subcutaneous fat (r>0.9, p<0.001). Skeletal muscle percentage exhibited a negative correlation with fat accumulation. Hemoglobin and uric acid levels had weaker correlations, suggesting more complex metabolic interactions. Anthropometric parameters serve as strong predictors of subcutaneous fat deposition in elderly individuals, while hemoglobin and uric acid levels show limited predictive capability.

The rapid development of e-commerce has generated huge volumes of data, opening up opportunities to analyze product demand patterns more accurately. This research aims to develop a product demand prediction model based on big data analysis. The data used includes sales transactions, product searches, customer reviews, and external factors such as seasons and promotions. The main methods used are machine learning techniques such as random forest regression and neural networks to build predictive models, with data extraction, transformation, and analysis processes carried out using big data platforms such as Hadoop and Spark. The resulting model is evaluated using accuracy metrics, such as mean absolute error (MAE) and root mean square error (RMSE), to measure prediction performance. The results show that the use of big data in product demand prediction can increase the accuracy of inventory planning and stock management by up to 25% compared to conventional methods. These findings make a significant contribution to the optimization of e-commerce operations, especially in more efficient and timely data-driven decision-making.

This research aims to develop an interactive web dashboard to support data analysis for vending machine sales. The dashboard is designed to facilitate the management of large datasets through intuitive visualizations and interactive features such as filtering, searching, and pagination. The development process involves several stages, including data collection, data cleaning, analysis, visualization, web design, implementation, and deployment using GitHub Pages. Technologies like HTML, CSS, JavaScript, Chart.js, and Grid.js are utilized to ensure efficiency and accessibility. The results of the research show that the dashboard effectively presents key information, such as sales trends, best-selling products, and payment method preferences, thereby supporting more accurate and data-driven strategic decision-making. However, the research has limitations in integrating predictive analytics. Future development is recommended to include predictive algorithms and test system performance on large-scale data. This solution is expected to contribute significantly to optimizing vending machine management and serve as a development model for similar applications in other business sectors.

Artificial Intelligence (AI) is increasingly used in financial accounting to improve decision-making effectiveness. This research analyzes the role of AI in supporting data-driven decision making and identifies challenges in its implementation. Using a qualitative approach with the Systematic Literature Review (SLR) method, this study reviewed 41 relevant articles from national and international journals. The results showed that 28 studies supported the effectiveness of AI in improving financial decision-making by automating transaction recording, enabling algorithm-based predictive analysis, and detecting financial anomalies. AI enables companies to respond faster to market changes, increase transparency of financial reports, and reduce human errors in accounting processes.However, 13 studies highlighted challenges such as technological complexity, limited transparency in decision-making, algorithmic bias, and organizational readiness. In addition, evolving regulations are an obstacle to ensuring optimal use of AI while minimizing ethical and legal risks. The success of AI in financial decision-making depends on infrastructure readiness, regulatory support, and human resource competencies. Without a well-planned strategy, AI may pose new challenges that hinder its effectiveness. Therefore, this study provides insights into the optimal AI implementation strategy to ensure that this technology improves the accuracy and transparency of decision making while maintaining financial accounting accountability.

Accurate stock price forecasting is a crucial yet challenging task due to the complex and dynamic nature of financial markets. This study employs the Prophet model to predict the stock prices of PT Sarana Menara Nusantara Tbk (TOWR) from 2021 to 2025. The research leverages historical stock data, incorporating dividend distribution dates and Annual General Meeting (AGM) events as external regressors to enhance predictive accuracy. The model was developed using machine learning-based time series forecasting, with hyperparameter tuning applied to optimize performance. The evaluation metrics indicate a Mean Absolute Error (MAE) of Rp49.92 and a Mean Absolute Percentage Error (MAPE) of 6.47%, demonstrating the model’s robustness in capturing long-term stock price trends. The findings suggest that stock prices exhibit significant movements around dividend announcement periods and AGM events, highlighting the impact of corporate actions on market behavior. This study reinforces the importance of incorporating fundamental financial indicators into forecasting models to improve decision-making for investors and financial analysts. The results offer practical implications for investment strategy formulation, risk management, and market trend analysis.

The potential of cardiac markers in predicting preeclampsia, such as Creatinine Kinase (CK) and Tyrosine Kinase 1 (TK1), has emerged as promising due to their involvement in the pathophysiology of this pregnancy complication. Preeclampsia is characterized by hypertension and organ dysfunction, and it can lead to significant maternal and fetal morbidity if not detected early. Early identification of preeclampsia is critical for preventing severe complications, and biomarkers like CK and TK1 can provide valuable insights. This study aimed to investigate the role of CK and TK1 as potential predictors of preeclampsia in the third trimester of pregnancy. Forty (40) consenting pregnant women were recruited from St. Philomina Catholic Hospital, Edo State, Nigeria. Participants were divided into two groups: twenty (20) normotensive pregnant women and twenty (20) preeclamptic pregnant women in their third trimester. Blood samples were collected and processed using a bucket centrifuge at 2500 RPM for 10 minutes, and plasma was stored frozen for further analysis. Tyrosine Kinase 1 was analyzed by fluorescence immunoassay, and Creatinine Kinase was measured using a spectrophotometric method. Data obtained were analyzed using GraphPad Prism 9, with results expressed as mean ± SEM. Statistical significance was set at a P-value of ≤ 0.05. The study found a statistically significant increase in the levels of both CK and TK1 in preeclamptic women compared to normotensive controls. These findings suggest that CK and TK1 could serve as predictive biomarkers for identifying and monitoring preeclampsia, aiding in early diagnosis and timely interventions