Publication Search

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.

Learning activities can run smoothly if accompanied by the availability of appropriate learning media. Learning in the Machining Technology course requires direct practical activities, for example in understanding the use of lathes. The limitations of students' mastery of knowledge when facing the teaching and learning process that tends to be lecture-oriented, causing students' lack of understanding during practice. Learning media that is less interesting causes failure in delivering material, thereby reducing students' interest in learning. This study aims to examine the effectiveness of Real Time Augmented Reality (RT-AR) Lathe media in the learning process of the Machining Technology course in the D-III Study Program, Department of Mechanical Engineering, Faculty of Engineering, Padang State University (FT-UNP). RT-AR media is designed to present interactive visualizations that describe the lathe work process in real time, so that it is expected to improve students' conceptual understanding and practical skills. The study used a quasi-experimental method with a pre-test and post-test design in two groups: the experimental group using RT-AR media and the control group using conventional learning methods. The results showed that there was a significant increase in the learning outcomes of students in the experimental group compared to the control group. In addition, RT-AR media is also able to increase students' motivation and active participation during the learning process. These findings indicate that RT-AR Lathe media is an effective and relevant learning innovation to be applied in vocational engineering education, especially in mastering lathing material.

This study discusses the application of Internet of Things (IoT) technology in the monitoring and control system of smokehouse machines at PT Serena Harsa Utama. IoT enables the integration of sensors to monitor critical parameters such as temperature and humidity in real-time, thereby enhancing production efficiency and product quality. An experimental method was employed to test the effectiveness of the IoT system, with data collection through integrated sensors. The results indicate that IoT implementation can increase production efficiency by up to 30%, reduce human error, and optimize energy consumption. Despite challenges related to initial investment and operator training, the long-term benefits of IoT adoption, such as improved product quality and reduced downtime, make it a promising solution in the food processing industry. This research emphasizes the importance of adopting IoT technology to enhance competitiveness in the modern industry.

Breast cancer is the most prevalent cancer among women worldwide, requiring early and accurate diagnosis to reduce mortality. This study proposes a hybrid classification pipeline that integrates Hybrid Statistical Feature Selection (HSFS) with unsupervised LSTM-guided feature extraction for breast cancer detection using the Wisconsin Diagnostic Breast Cancer (WDBC) dataset. Initially, 20 features were selected using HSFS based on Mutual Information, Chi-square, and Pearson Correlation. To address class imbalance, the training set was balanced using the Synthetic Minority Over-sampling Technique (SMOTE). Subsequently, an LSTM encoder extracted non-linear latent features from the selected features. A fusion strategy was applied by concatenating the statistical and latent features, followed by re-selection of the top 30 features. The final classification was performed using a Support Vector Machine (SVM) with RBF kernel and evaluated using 5-fold cross-validation and a held-out test set. Experimental results showed that the proposed method achieved an average training accuracy of 98.13%, F1-score of 98.13%, and AUC-ROC of 99.55%. On the held-out test set, the model reached an accuracy of 99.30%, precision of 100%, and F1-score of 99.05%, with an AUC-ROC of 0.9973. The proposed pipeline demonstrates improved generalization and interpretability compared to existing methods such as LightGBM-PSO, DHH-GRU, and ensemble deep networks. These results highlight the effectiveness of combining statistical selection and LSTM-based latent feature encoding in a balanced classification framework.

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.

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.

One of the key processes in the production of APAR cylinders is the welding of cylindrical plates, which is carried out using a Longitudinal Welding Cylinder machine and the CO₂ welding method. However, in practice, operators face several challenges, mainly due to the number of process steps that do not significantly contribute to the quantity or quality of the output, resulting in reduced productivity. This study aims to improve the productivity of the welding process through a series of improvements. The methods used include data analysis and root cause identification through the Overall Equipment Effectiveness (OEE) approach and Lean Six Sigma using the DMAIC stages (Define, Measure, Analyze, Improve, Control). Based on the Define stage, the initial OEE value was 67.49%, which is still far below the world-class standard of 85%. In the Measure stage, Pareto analysis revealed that the largest downtime (2,097 minutes or 40%) was caused by cycle time issues. Further analysis showed that activities such as material setup, additional plate placement, and additional plate cutting (totaling 85 seconds) could still be optimized. During the Improve stage, modifications were made, such as eliminating the additional plate cutting process and adding a stopper to ensure accurate welding alignment. These improvements successfully reduced the cycle time from 180 seconds to 120 seconds, thereby decreasing downtime and increasing the OEE value to 76.12%.

In today’s global economy, accurately predicting foreign exchange rates or estimating their trends correctly is crucial for informed investment decisions. Despite the success of standalone models like ARIMA and deep learning models like LSTM, challenges persist in capturing both linear and nonlinear dynamics in highly volatile exchange rate environments. Motivated by the limitations of these individual models and the need for more robust forecasting tools, this study proposes a hybrid ARIMA-LSTM model that integrates ARIMA’s strength in modeling linear trends with LSTM’s capability to capture nonlinear dependencies, using historical USD/NGN exchange rate data from the Central Bank of Nigeria (CBN) spanning 2001 to 2024. The research hypothesis posits that the hybrid ARIMA-LSTM model will significantly outperform standalone models in forecasting accuracy. By comparing these models against state-of-the-art approaches, the study highlights the advantages of hybridizing statistical and deep learning methods. The findings demonstrate that the hybrid model achieved the lowest Root Mean Squared Error (RMSE) of 2.216 and the highest R² of 0.998, indicating superior forecasting performance. This study fills a critical research gap by demonstrating the effectiveness of hybrid deep learning in financial time series forecasting, providing valuable insights for investors, policymakers, and financial analysts. Future research will extend this work by incorporating the latest dataset and evaluating model robustness during the recent surge in the Naira/Dollar exchange rate from 2023 to 2024.

Knee osteoarthritis is a global health issue with increasing prevalence, particularly among the elderly population. This condition is characterized by primary symptoms such as joint pain, stiffness, and reduced physical function, which significantly limit the patient's daily activities. One promising non-pharmacological approach to managing knee osteoarthritis is Home-Based Resistance Training (HBRT). HBRT combines the effectiveness of resistance training with the convenience of being performed at home and is increasingly supported by advancements in telerehabilitation technology. This study is a systematic review conducted based on the PRISMA-P guidelines, with literature searches from PubMed, Scopus, Semantic Scholar, Google Scholar, and Cochrane databases. The included articles were English-language publications from 2019 to 2024 that evaluated the effectiveness of HBRT in patients with knee osteoarthritis. The findings indicate that HBRT is significantly effective in reducing joint pain, with a decrease in WOMAC scores ranging from 24.78% to 29.64% (p < 0.001), and improving physical function by 21.54% to 30.2%. These improvements meet the Minimum Clinically Important Difference (MCID) criteria, indicating clinically significant benefits. Furthermore, the effectiveness of HBRT is comparable to machine-based training, particularly in patients with high baseline severity. With standardized exercise protocols and adequate technological support, HBRT can be considered a feasible and effective intervention strategy in the rehabilitation of knee osteoarthritis patients, especially in the digital era and in contexts where access to conventional healthcare facilities is limited.

Google Translate is an artificial intelligence-based translation service developed by Google. Since its introduction in 2006, this service has continued to create with the application of Neural Machine Translation (NMT) technology, which improves the accuracy and fluency of translation compared to previous methods. This study aims to determine the effectiveness and limitations of Google Translate in translating Batak into Indonesian. The research method used is descriptive qualitative with a comparative approach of Google Translate translation results and manual translations by professional translators. The study results show that Google Translate can translate basic words and simple sentences quite well. However, there are several limitations, such as a lack of understanding of the cultural context, idioms, and dialect variations in the Batak language. In addition, the translation is also influenced by the limitations of the database and vocabulary enrichment in this service. Thus, although Google Translate can be a tool in translation, users still need to do manual verification to ensure accuracy, especially in fields that require high precision such as law, academics, and professional communication.

This study explores the application of machine learning algorithms, specifically Linear Regression and Decision Tree Regressor, for predicting student academic performance using academic grade data from Kaggle. The analyzed factors include attendance, assignment grades, midterm exam grades, and final exam grades. The research methodology encompasses data collection, preprocessing, model development, training, and validation. This study contributes to the field of educational data analytics by demonstrating how machine learning can provide actionable insights into students' learning patterns and academic outcomes. The findings emphasize the effectiveness of Linear Regression for linearly distributed data and Decision Tree Regressor for capturing complex, non-linear relationships. The implications of this research suggest that machine learning models can assist educators in identifying key factors influencing student performance, enabling targeted interventions to enhance learning outcomes. Future research should explore larger, more diverse datasets and incorporate ensemble methods, such as Random Forest or Gradient Boosting, to improve model generalization and prediction accuracy. Additionally, integrating socio-economic and psychological factors could provide a more holistic perspective on academic achievement.

This study aims to address the challenges and propose solutions for the Optimization of Blockchain-Based Cybersecurity Systems to Enhance Resilience Against Ransomware Attacks using a Systematic Literature Review (SLR) approach. Blockchain is increasingly recognized as a transformative technology in cybersecurity due to its decentralized structure, transparency, and robustness in securing data. Despite these advantages, its widespread adoption is hindered by several challenges, including scalability, interoperability, high energy consumption, and limited access to representative ransomware datasets. This research highlights that integrating blockchain with advanced technologies such as data analytics, machine learning, and Explainable AI (XAI) can significantly enhance its effectiveness in combating ransomware.The findings reveal that Graph Convolutional Neural Networks (GCN) enable real-time detection of ransomware patterns in network traffic with an accuracy of up to 95%. Furthermore, Layer-2 solutions like the Lightning Network and sharding effectively alleviate the load on main blockchains, thereby increasing transaction throughput. Efficient consensus mechanisms, including Proof of Stake (PoS) and Delegated Proof of Stake (DPoS), address energy consumption issues, making blockchain more adaptable to IoT and resource-constrained environments. These approaches have proven successful in enabling early detection, mitigation, and prevention of ransomware in IoT systems, cloud infrastructures, and smart grid networks. The implications of this study underscore the potential of blockchain as a critical component of proactive and adaptive cybersecurity systems. However, overcoming existing challenges requires further development of hybrid frameworks that integrate blockchain with data analytics and machine learning technologies. In addition, efforts should focus on standardizing global security protocols to enhance interoperability and creating robust, diverse ransomware datasets to support more accurate detection systems. Future research should also explore methods to minimize latency and improve blockchain efficiency in real-time cybersecurity applications.

This research aims to understand the impact of the integration between artificial intelligence (AI) technologies and cyber security on administrative decisions in three aspects: (1) decision-making speed, (2) decision accuracy, and (3) decision effectiveness. A sample of 150 employees was drawn, and a survey was used to gather the required information. Data analysis was conducted using the statistical program SPSS 25, employing various statistical methods such as mean, standard deviation, correlation coefficient, and simple linear regression. The research concluded with several findings, the most important being: The integration of AI technologies and cyber security leads to improved speed, accuracy, and effectiveness of administrative decisions, The researcher recommended that institutions adopt AI technologies to enhance their cyber security systems, particularly in areas like machine learning and big data analysis.

This study conducts an exploratory data analysis combined with machine learning techniques to identify early signs of student depression. We investigated various factors affecting mental health among students, including sleep duration, dietary patterns, history of suicidal thoughts, family history of mental illness, and their relationships with depression across age groups and academic pressure. The study also examined the influence of gender on academic stress levels. Three machine learning models such as Random Forest, Support Vector Machine (SVM), and K-Nearest Neighbors (KNN) were utilized to predict depression. The performance of these models was evaluated, achieving accuracy rates of 84.97% for Random Forest, 84.85% for SVM, and 81.16% for KNN. The findings highlight the effectiveness of these models in predicting student depression and underscore the importance of targeted mental health interventions based on key factors influencing mental health among students.

Optical Character Recognition (OCR) systems often struggle to extract text accurately from images captured at various distances, particularly under challenging conditions such as blurriness, noise, or poor lighting. These issues are common in real-world scenarios and limit the effectiveness of existing OCR technologies. This study addresses these challenges by applying Gaussian blur after the grayscale conversion. This method reduces noise for the image's clarity without sacrificing the original algorithm's key features. Results revealed that the enhanced OCR algorithm significantly outperformed existing methods in terms of accuracy and confidence levels. It demonstrated the ability to read signages with higher precision, even in difficult conditions such as intricate designs, poor lighting, and long distances. This advancement enables more reliable text recognition and translation, offering practical applications for public signage translation, cross-cultural communication, and improved accessibility in multilingual environments.

Fraud in digital transactions has become a serious issue threatening the security and integrity of the fintech and e-commerce sectors. To address this problem, machine learning technology has emerged as an effective solution for automatically detecting anomalies and fraudulent transactions. This study aims to analyze the application of machine learning algorithms, specifically Support Vector Machine (SVM), Random Forest, and Ensemble Learning, in detecting fraud in digital transactions. The research adopts a quantitative approach with experimentation, testing the effectiveness of the three algorithms using a digital transaction dataset consisting of both fraudulent and non-fraudulent transactions. The results show that the Random Forest algorithm performs the best in terms of accuracy and recall, followed by Ensemble Learning, which enhances fraud detection performance by combining multiple prediction models. Meanwhile, SVM demonstrates satisfactory performance but is prone to overfitting issues when handling large and complex datasets. The study also finds that the problem of imbalanced data can affect model accuracy, and data balancing techniques such as oversampling are required to improve fraud detection performance. Overall, the findings suggest that machine learning, particularly Random Forest and Ensemble Learning algorithms, can be relied upon to improve fraud detection in digital transactions. However, challenges such as model interpretability and the need for periodic algorithm updates still need to be addressed to enhance the effectiveness of fraud prevention systems in countering the ever-evolving nature of fraud.

Diabetes is one of the diseases that poses a significant global health challenge, with a considerable impact on quality of life and mortality rates. This study examines the use of the Support Vector Machine (SVM) algorithm for diabetes classification through a literature review. SVM was chosen due to its ability to handle imbalanced and complex data. The aim of this study is to assess the effectiveness of SVM compared to other machine learning methods in detecting diabetes. The results of the literature review indicate that SVM achieves higher accuracy than other methods such as Naïve Bayes and Decision Tree, with some studies showing accuracy above 90%. This study is expected to provide deeper insights into the development of machine learning-based diagnostic systems for diabetes.

This study presents a Quantum Machine Learning (QML) architecture for perfectly classifying the Iris flower dataset. The research addresses improving classification accuracy using quantum models in machine-learning tasks. The objective is to demonstrate the effectiveness of QML approaches, specifically the Variational Quantum Circuit (VQC), Quantum Neural Network (QNN), and Quantum Support Vector Machine (QSVM), in achieving high performance on the Iris dataset. The proposed methods result in perfect classification, with all models attaining accuracy, precision, recall, and an F1-score of 1.00. The main finding is that the QML architecture successfully achieves flawless classification, contributing significantly to the field. These results underscore the potential of QML in solving complex classification problems and highlight its promise for future applications across various domains. The study concludes that QML techniques can offer transformative solutions in machine learning tasks, particularly those leveraging VQC, QNN, and QSVM.

PT XYZ) is a company which focuses on integrated aquaculture. Operating since 1987, PT XYZ has a fish and shrimp feed factory, fish and shrimp breeding and rearing as well as marine fish food processing and cold storage for local and global markets. At PT XYZ, especially the Quality Control division, there are still ineffective analysis activities, namely piece length analysis. An effort to increase productivity is by designing an automatic cut length analysis machine with the aim of maximizing efficiency and effectiveness. Therefore, the objective function of this research was carried out to design and increase productivity and reduce inefficient activities. From this, it is necessary to design and optimize activities to have a positive impact on the company. This research uses Blender software and the Multimedia Development Life Cycle (MDLC) method which includes concept, design, material collecting, assembly, testing and distribution. The results of this research show that this machine design is very effective and practical for the company and allows the company to improve maximum performance

The integration of Artificial Intelligence (AI) in personalized and adaptive learning environments has revolutionized the education sector by offering customized learning experiences tailored to individual student needs. This study explores the role of AI in enhancing adaptive learning through data-driven insights, intelligent tutoring systems, and real-time feedback mechanisms. By employing machine learning algorithms and natural language processing, AI-driven platforms can analyze student performance, predict learning patterns, and deliver personalized content. The study highlights the effectiveness of AI in addressing diverse learning styles, improving engagement, and optimizing educational outcomes. Furthermore, it discusses the implications of AI in fostering inclusive education and lifelong learning. The findings suggest that AI-powered learning environments significantly enhance student-centered education, promoting efficiency and accessibility.