Sinkron : jurnal dan penelitian teknik informatika

Design of Real-Time Project Monitoring Dashboard Using Kimball’s Data Warehouse Approach and Google Data Studio

Sat, 12 Jul 2025 00:00:00 +0000

The growth of the construction industry in Indonesia triggers an increasing need for an efficient project management system, especially in presenting project data accurately and in real-time. PT Dream Island Development (PT DID), a specialist MEP contractor company, faces challenges in presenting project reports to executives because the data is still presented in the form of Excel tabulations which require up to three days of processing time and are difficult to interpret quickly. This research aims to design an interactive dashboard-based project data visualization system using Google Data Studio (Looker Studio) to present project information intuitively and responsively. The method used includes a software engineering approach with five main stages: requirements analysis, data warehouse design, ETL process using Pentaho Data Integration, visualization using Google Data Studio, and testing using User Acceptance Test (UAT). Project data from 2022-2024 was modeled using a star schema and displayed in four main dashboards: project cost, project value, project progress, and details per project. The test results showed a high level of user satisfaction with a functionality score of 93.5%, reliability 91.33%, usability 96%, and efficiency 94.66%. These findings indicate that the developed system effectively supports PT DID's needs in project monitoring and data-based decision-making. The system also has the potential to be replicated in other construction companies as an efficient and scalable business intelligence solution.

This research contributes to the growing body of construction informatics by integrating Kimball’s nine-step methodology with modern data visualization tools to enhance project transparency and decision-making.

Bibliometric Mapping and Trend Analysis of Beta Regression Modeling: A Decade of Development (2015–2024)

Sat, 12 Jul 2025 00:00:00 +0000

Beta regression is a statistical model designed to handle dependent variables that assume values within the open interval (0, 1), such as rates, proportions, or percentages. The study aimed to determine the development of beta regression over the last 10 years with a bibliometric approach. The source of the article database used comes from the Scopus website. The tool used for analysis is R software with a bibliometrix package. The results of this study show that there are 293 articles published in the Scopus Journal. Research develops in various research fields. The author with the most articles is Cribari-Neto, F., with the most significant number of documents, i.e., 12. According to the author's country of origin related to the beta regression method, Brazil has the most countries, while Indonesia is in 12th place. Therefore, research on beta regression still has excellent potential to continue to be developed.

Enhancing EEG-Based Stress Detection Using ICA, Relative Difference, and Convolutional Neural Networks

I Made Wahyu Guna Negara, I Made Agus Wirawan, I Made Gede Sunarya — Sat, 12 Jul 2025 00:00:00 +0000

: EEG-based stress detection is crucial for early mental health monitoring, but signal quality is often degraded by artifacts and baseline variability. This study proposes an optimized preprocessing method combining Independent Component Analysis (ICA) for artifact removal and Relative Difference for baseline reduction. Using the SAM-40 EEG dataset, features were extracted with Differential Entropy and structured into a 3D EEG cube to preserve spatial-frequency information. A Convolutional Neural Network (CNN) classified stress levels into low and high categories. The proposed approach achieved 94.44% accuracy, with 100% precision for the high stress class and 81.82% recall. These results highlight the effectiveness of combining ICA and baseline reduction to enhance deep learning-based EEG signal processing for stress detection.

Convolutional Neural Network Algorithm Implementation for Classifying Traditional Wood Carving Motifs of Patra Bali

Sat, 12 Jul 2025 00:00:00 +0000

This research develops an automatic classification system to recognize Balinese Patra carving motifs using deep learning method based on Convolutional Neural Network (CNN). The data used are images of Cina Patra, Mesir Patra, Punggel Patra, and Sari Patra motifs, which have gone through preprocessing stages such as cropping, resizing, and augmentation in the form of flip and rotation to increase data variation. Three pre-trained CNN models were used in testing, namely DenseNet169, InceptionResNetV2, and MobileNetV2. The training process was performed with Adam optimization, batch size 32, and 100 epochs. Model performance evaluation was performed using accuracy and confusion matrix metrics. The results show that all three models were able to achieve 100% accuracy on the test data, with MobileNetV2 recording the lowest loss of 0.75%, followed by DenseNet169 (1.14%) and InceptionResNetV2 (1.18%). Based on the confusion matrix, all motifs were recognized very well, although there was a slight misclassification of the Patra Sari motif by the InceptionResNetV2 model. These findings prove that CNN is effectively used in the recognition of traditional carving motifs and has the potential to support cultural preservation through interactive visual technology.

Comparative Analysis of LSTM, GRU, and Bi-LSTM Deep Learning Models for Time Series Cryptocurrency Price Forecasting

Sat, 12 Jul 2025 00:00:00 +0000

Cryptocurrency is a highly volatile digital asset that requires accurate predictive methods. This study compares the performance of three deep learning architectures LSTM, GRU, and Bi-LSTM in forecasting the prices of Bitcoin (BTC), Ethereum (ETH), and Binance Coin (BNB) using univariate historical data. Evaluation was conducted through regression metrics (RMSE and MAPE) and classification of price movement into five categories, ranging from very bearish to very bullish, assessed using a confusion matrix. The results show that GRU performed best for BTC (RMSE 974.72, MAPE 1.18%), while Bi-LSTM outperformed others for ETH and BNB (RMSE 43.19 and 6.83; MAPE 1.16% and 1.08%) and achieved the highest classification accuracy (55% and 52%). However, overall classification accuracy remains low, reflecting the complexity of cryptocurrency price patterns. The study is limited by its univariate approach without incorporating external variables. Its contribution lies in combining regression and classification evaluation, and it recommends exploring multivariate and ensemble models in future research.

Meeting Room Booking System with WhatsApp Notification Feature Using Extreme Programming Methods in RS Muhammadiyah Lamongan

Arizona Firdonsyah, Nafisyah Alyana Putri — Sat, 12 Jul 2025 00:00:00 +0000

Meeting room management in hospitals plays an important role in supporting operational efficiency and coordination between departments. At RS Muhammadiyah Lamongan, common issues such as overlapping schedules, delays in booking information, and lack of transparency in the scheduling process are still frequently encountered. This study aims to develop a web-based meeting room booking system using the Extreme Programming (XP) method, integrated with a WhatsApp notification feature. The system is designed to improve transparency, minimize scheduling conflicts, and enhance communication between administrators and users. Requirements gathering was conducted through interviews with the hospital's secretariat, and the system was developed using the Laravel Framework and WhatsApp API. The system testing was carried out using Blackbox Testing and User Acceptance Testing (UAT) with a Likert scale. The test results showed that the system achieved a perfect score of 100 out of 100 points, indicating that all core features functioned as expected without significant technical issues. This system is expected to serve as an effective solution to support a more efficient, real-time, and structured meeting room scheduling process at RS Muhammadiyah Lamongan.

Integrating SMOTE with XGBoost for Robust Classification on Imbalanced Datasets: A Dual-Domain Evaluation

Novriadi Antonius Siagian, Sardo P Sipayung, Alex Rikki, Nasib Marbun — Tue, 15 Jul 2025 00:00:00 +0000

Class imbalance is one of the main challenges in classification problems, as it can reduce the model's ability to accurately identify minority classes and negatively impact the overall reliability of predictions. In response to this problem, this study proposes an integrated approach combining SMOTE and XGBoost to improve classification performance on imbalanced data. This approach aims to evaluate the impact of oversampling techniques on prediction accuracy and model sensitivity to class distribution. The evaluation was conducted using two public datasets representing different domains and different amounts of data, namely Spambase and Diabetes, to assess the effectiveness and generalization of the applied approach. The experimental results show that this integrated model consistently outperforms traditional comparison algorithms, with an F1 score of 0.94 and ROC-AUC of 0.98 on the Spambase dataset and ROC-AUC of 0.83 on the Diabetes dataset, with a good balance between precision and recall. The 10-fold cross-validation technique was applied to ensure objective performance estimates free from random data splitting bias. Additionally, this study highlights the importance of selecting appropriate evaluation metrics in the context of imbalanced data, as single accuracy often provides a misleading performance picture. This study makes a significant contribution by providing a benchmark for comparing the effectiveness of SMOTE-XGBoost integration using two different datasets, accompanied by rigorous cross-validation. These findings reinforce the position of integrating data preprocessing strategies and ensemble learning as a competitive and adaptive solution for addressing class imbalance challenges in data-driven classification systems.

Smart Diagnosis of Coffee Diseases via Web-Based Expert System

Wed, 23 Jul 2025 00:00:00 +0000

Indonesia’s coffee industry faces persistent threats from plant diseases and pests, which significantly impact crop yield and farmer livelihoods. Many smallholder farmers lack access to timely expert guidance, leading to delays in diagnosis and ineffective treatments. This study proposes a web-based expert system designed to assist farmers in diagnosing coffee plant diseases and pests based on observed symptoms. The system integrates a Bayesian Network (BN) to model the probabilistic relationships between symptoms and diseases. It employs a Breadth-First Search (BFS) algorithm to optimize the exploration of symptom-disease associations. Developed using Node.js, Next.js, and MySQL, the system enables users to input their symptoms and receive probabilistic diagnoses along with treatment suggestions. Validation results show over 85% accuracy compared to expert assessments, highlighting the system's reliability and scalability. This research demonstrates that combining probabilistic reasoning and structured graph traversal provides an effective diagnostic tool, especially for underserved rural communities. Furthermore, the system serves as a foundation for future development of intelligent agricultural support tools, with potential integration of real-time environmental data, mobile platforms, and adaptive learning models to enhance decision-making in precision farming.

Customer Segmentation Using RFM and K-Means Clustering to Support CRM in Retail Industry

Yohanni Syahra, Abdul Fadlil, Herman Yuliansyah — Wed, 23 Jul 2025 00:00:00 +0000

In today’s highly competitive retail landscape, businesses face increasing challenges in retaining customer loyalty and achieving sustainable growth. A common issue, particularly among small and medium-sized enterprises (SMEs), is the absence of a structured method for identifying and categorizing customers based on their value and behavior. This study addresses the challenge by implementing a data-driven customer segmentation approach using Recency, Frequency, and Monetary (RFM) analysis combined with the K-Means clustering algorithm. The research utilized 2,353 transaction records from 369 unique customers collected over three years from a local retail business. After preprocessing and normalizing the RFM values using Min-Max scaling, the Elbow Method was applied to determine the optimal number of clusters, resulting in four distinct customer segments. Cluster 3, labeled “Loyal Customers,” consisted of customers with high purchase frequency and very high spending; Cluster 1 (“Potential Loyalists”) included those with moderate activity; Cluster 0 represented “At-Risk Customers,” and Cluster 2 comprised “One-Time Buyers.” This segmentation framework supports the development of targeted Customer Relationship Management (CRM) strategies, such as loyalty programs and re-engagement campaigns. However, the approach also has limitations, including potential data bias due to the use of static transaction records and the challenge of interpreting clusters without qualitative customer feedback. Despite these constraints, the study demonstrates the practical utility of combining RFM analysis with clustering techniques to extract actionable insights in environments with limited technical infrastructure.

Hyperparameter Optimization with MobileNet Architecture and VGG Architecture for Urban Traffic Density Classification Using Bali Camera Image Data

I Putu Arsana Suputra, I Gede Aris Gunadi, I Made Gede Sunarya — Fri, 25 Jul 2025 00:00:00 +0000

Traffic congestion in urban areas is a critical issue, particularly in densely populated regions such as Bali. This study addresses the challenge by implementing a Convolutional Neural Network (CNN) method to classify traffic density levels based on images captured by road surveillance cameras. The primary focus of this research is hyperparameter optimization to enhance the model's performance in classifying traffic conditions. Various combinations of hyperparameters—such as the number of neurons in the dense layer, dropout rate, learning rate, batch size, and number of epochs—were tested on two popular CNN architectures: MobileNet and VGG16. MobileNet offers lightweight computing, while VGG16 provides strong feature extraction capabilities, albeit with higher computational resource demands. Quantitative results show that after hyperparameter tuning, the MobileNet architecture achieved an accuracy of 96.94% and an F1 score of 0.969, while the VGG16 architecture achieved an accuracy of 97.22% and an F1 score of 0.972 in traffic density classification. These findings confirm that hyperparameter optimization can significantly improve classification accuracy. The scientific contribution of this research lies in the structured approach to CNN hyperparameter optimization and the demonstration that this process directly impacts the enhancement of model performance in traffic image classification tasks. This study offers valuable insights for the development of intelligent traffic management systems, especially in urban areas with limited resources.

Comparative Performance Analysis of Decision Tree And SVM Algorithms in Detecting Multiple System Atrophy Based on Clinical Features

Fri, 25 Jul 2025 00:00:00 +0000

Multiple System Atrophy (MSA) is a progressive neurodegenerative disorder that presents significant challenges in early and accurate diagnosis. Advances in machine learning algorithms offer promising solutions for improving diagnostic support in medical fields, particularly in complex disorders such as MSA. This study compares the performance of two widely used classification algorithms Decision Tree (DT) and Support Vector Machine (SVM) in detecting MSA using clinical datasets consisting of 300 patient records. Supervised learning techniques with cross-validation were employed, and key performance metrics including accuracy, precision, recall, and F1-score were evaluated. SVM achieved an accuracy of 88.1% and F1-score of 87.1%, outperforming Decision Tree, which recorded 85.4% accuracy and an F1-score of 83.9%. The novelty of this study lies in its direct comparative benchmark using standardized clinical features for MSA detection, offering practical insights into model selection for neurodegenerative disease screening. The SVM model’s superior performance indicates its suitability for reliable early detection of MSA from clinical data. This research contributes to the development of machine learning-based decision support tools in neurology.

Comparative Performance of Yolov8 and Ssd-mobilenet Algorithms for Road Damage Detection in Mobile Applications

Arie Satia Dharma, Chantika Nadya Serebella Pardosi, Zan Peter Silaen — Sun, 27 Jul 2025 00:00:00 +0000

Road damage is a serious issue that can impede traffic and increase the risk of accidents in any area. Fast and accurate detection and classification of road damage are crucial for efficient maintenance and repair. Considering the ease of access, the implementation of this detection can be done using a mobile application. This study aims to compare the performance of two object detection algorithms, YOLOv8 and SSD-MobileNet, in detecting and classifying road damage in mobile application. Evaluation is conducted using accuracy, speed, and memory utilization, and classification of road damage into six categories namely block cracks, alligator cracks, transverse cracks, edge cracks, patches, and potholes using a confusion matrix. The results show that YOLOv8 has an overall accuracy of 86.4%, a speed of 0.5 ms, and consumes 0.41 GB of RAM. SSD-MobileNet shows an overall accuracy of 91.1%, speed 0.7 ms, and consumes 0.14 GB of RAM. The comparison indicates that YOLOv8 excels in detection speed, while SSD-MobileNet is more higher accuracy and efficient in memory. This study is limited to a performance measurement approach for YOLOv8 and SSD-MobileNet algorithms in a mobile-based road defect detection context. Its contribution lies in the trade-off between accuracy, speed, and the memory required to implement the models in limited devices. In future research is recommended to explore model with pruning to reduce memory usage.

Smart Contract Architecture for a Blockchain-Driven Multi Criteria DSS in Forest Fire Monitoring and Response

Fajar Yusuf Nur Cahyo, Djarot Hindarto — Sun, 27 Jul 2025 00:00:00 +0000

The current centralized system is vulnerable to data manipulation due to the absence of independent verification mechanisms, thereby compromising the reliability of information. In addition, the inconsistency of formats and data silos across agencies exacerbates information fragmentation. Delays in data distribution hamper rapid response in emergency situations, while uneven communication infrastructure—especially in remote areas—reduces real-time monitoring capabilities. Lack of coordination among stakeholders—such as BNPB, forestry agencies, local communities, and the private sector—adds to the complexity of disaster management and often leads to overlapping tasks. The decision-making process is further complicated by competing criteria, such as priority areas, resource availability, dynamic weather conditions, and limited IoT sensor coverage. Additionally, high operational costs for system maintenance and limited audit trails make it difficult to track data history and ensure accountability. Therefore, the Multi-Criteria Decision Making (MCDM) method is necessary to handle uncertainty, combine different geospatial factors in an organized way, and make sure the decision-making process is reliable and clear. This research fills the technological gap by introducing a decentralized audit trail while facilitating cross-sector collaboration in fire mitigation decision-making and minimizing the risk of evidence-based data errors.

Customer Loyalty Classification Using KNN and Decision Tree for Sales Strategy Development

Mukhlisin, Handoyo Widi Nugroho — Sat, 02 Aug 2025 00:00:00 +0000

Customer loyalty is a crucial element in maintaining business continuity in today’s competitive digital era. This study aims to classify customer loyalty levels based on sales and transaction behavior data using two supervised machine learning algorithms: K-Nearest Neighbor (KNN) and Decision Tree. The models were developed and evaluated using Python in the Google Colaboratory environment, utilizing a dataset of 250 customer records. The research process included data preprocessing, feature selection, normalization, data splitting, model building, and evaluation using accuracy, precision, recall, and F1-score metrics. Evaluation results showed that the Decision Tree algorithm delivered the best performance with 99.20% accuracy, 99.50% precision, 99.50% recall, and a 99.50% F1-score. Meanwhile, the KNN algorithm achieved 91.60% accuracy, 91.63% precision, 98.50% recall, and a 94.91% F1-score. These findings indicate that the Decision Tree model is more effective for classifying customer loyalty and can be implemented as a decision support tool for data-driven Customer Relationship Management (CRM) strategies.

Food Recipe Recommendation System with Content-Based Filtering and Collaborative Filtering Methods

Ni Putu Triska Widiantari, I Made Agus Dwi Suarjaya, Ni Kadek Dwi Rusjayanthi — Tue, 05 Aug 2025 00:00:00 +0000

Cooking your own food at home is a good step toward reducing fast food consumption. Fast food increases the risk of dangerous diseases. The diversity of recipe information available on the internet makes it difficult to choose recipes that match user preferences. Mobile technology can help with this by recommending recipes that better suit users' eating habits. This makes the transition to a healthier diet easier. Therefore, in this study, a recommendation system was developed that can recommend recipes based on the preferences of Android users. Two main recommendation methods are used in this study: content-based filtering and collaborative filtering. Using cosine similarity, a content-based recommendation system identifies the proximity between a recipe for food and its related context. The history of user comments on recipes serves as implicit feedback for the collaborative recommendation algorithm. This eliminates the need for explicit evaluations, such as ratings. This recommendation system generates recommendations in the form of the top ten food recipes with an evaluation matrix, referred to as NDCG@k and Hit-Ratio@k. The tests revealed that a content-based filtering technique may produce helpful recommendations, with the highest similarity score of 0.41 for the entry "chocolate cake that you can easily make at home." Meanwhile, in the collaborative filtering method using the Neural Collaborative Filtering (NCF) approach, the system shows consistent performance improvements, with the MAP@10 value increasing from 0.705 to 0.767 and the NDCG@10 from 0.78 to 0.83 after 10 training epochs.

Keywords: Recommendation systems; content-based filtering; neural collaborative filtering; cosine similarity; implicit feedback

Hybrid Genetic Algorithm for Dynamic Portfolio Optimization Problems

Sarah Ayatun Nufus, Sutarman, Elvina Herawati — Sun, 10 Aug 2025 00:00:00 +0000

Dynamic portfolio optimization is a complex problem due to continuous changes in market conditions, demanding algorithms capable of effective adaptation. Genetic Algorithms (GA) are often used for optimization problems but may face limitations in convergence speed and solution precision. This research aims to develop and evaluate a Hybrid Genetic Algorithm (HGA) that integrates GA with the Hill Climbing local search method, and to compare its performance against standard GA in solving dynamic portfolio optimization problems with the objective of maximizing the Sharpe Ratio. A series of simulation-based experiments were conducted by varying key algorithmic and dynamic environment parameters. Simulation results indicate that HGA generally has significant potential to improve performance compared to standard GA. Consistently, HGA successfully achieved superior solution quality, both in terms of Offline Performance Solution Quality and Overall Best Fitness. Regarding robustness to dynamic changes, HGA also demonstrated a smaller impact from performance degradation and a more promising recovery capability after market environment changes. Although HGA's superiority in convergence speed is not always absolute and the implementation of Hill Climbing adds to the computational time per generation, the improvement in solution quality and robustness offered in many configurations can be considered a worthwhile trade-off, especially for complex dynamic portfolio optimization problems. These findings support the hypo that hybridizing GA with local search can provide a positive contribution, noting that careful parameter tuning is crucial for maximizing HGA's potential.

Creditworthiness Classification Utilizing AHP-SVM Based on 5C Criteria

Sun, 10 Aug 2025 00:00:00 +0000

Credit risk occurs when borrowers fail to meet loan repayment obligations, posing significant challenges to the financial stability of lending institutions. Accurate classification of creditworthiness is essential to mitigate such risks. This study proposes a hybrid approach that integrates the Analytical Hierarchy Process (AHP) and Support Vector Machine (SVM) to evaluate borrower eligibility based on the 5C model: Character, Capacity, Capital, Collateral, and Condition. The AHP method is used to assign weights to credit attributes based on expert judgment, while SVM performs the classification. Three experiments were conducted to compare the effectiveness of different feature selection strategies: (1) expert-defined 5C attributes, (2) AHP weighting conducted by experts, and (3) AHP weighting conducted by non-experts. Experimental results show that the 5C-SVM model achieved the highest performance with 96% accuracy, followed by AHP-SVM (expert) with 95% and AHP-SVM (non-expert) with 93%. The findings indicate that expert involvement in the feature selection process significantly improves model performance. This study demonstrates the effectiveness of combining domain knowledge with machine learning in building intelligent decision support systems for credit risk analysis. The proposed approach offers practical value for financial institutions seeking more objective, accurate, and consistent credit evaluation processes. Furthermore, it opens new opportunities for integrating expert-based reasoning with automated analytics in financial decision-making.

Lightweight YOLO Models for Real-Time Multi-Vehicle Detection

Imam Ashari, Iis Setiawan Mangku Negara, Arif Setia Sandi A — Sun, 10 Aug 2025 00:00:00 +0000

This study presents a comparative evaluation of three lightweight YOLO architectures: YOLOv5n, YOLOv8n, and YOLOv11n, for multi-class vehicle detection using CCTV imagery captured under dense traffic conditions in Semarang, Indonesia. The models were tested on their ability to detect four types of vehicles, including motorcycle, car, bus, and truck. To enhance generalization across different lighting conditions, image qualities, and environmental noise, six data augmentation techniques were applied during training. These included Blur, Brightness Adjustment, Color Jitter, Noise Injection, Scaling, and Zoom In. Among these, the Blur technique yielded the most significant improvement in detection accuracy. YOLOv8n with Blur augmentation achieved the best performance with a precision of 0.875, recall of 0.655, mAP@0.5 of 0.756, and mAP@0.5:0.95 of 0.467. Class-wise analysis showed that buses and trucks were easier to detect due to their larger size and distinct features, while motorcycles were the most difficult due to their smaller dimensions and visual similarity to other objects. Training curves demonstrated consistent decreases in loss values and progressive improvements in evaluation metrics across 60 epochs. These findings emphasize the importance of selecting appropriate model architecture and augmentation strategies to improve object detection performance, particularly in real-time and resource-limited applications. YOLOv8n with Blur augmentation proved to be the most effective configuration in this study.

MLP Model Optimization for Heart Attack Risk Prediction: A Systematic Literature Review

Heru Supriyanto, Taqwa Hariguna, Azhari Shouni Barkah — Sun, 10 Aug 2025 00:00:00 +0000

Heart disease remains a leading cause of global mortality, making the development of accurate predictive models a clinical priority. While Multilayer Perceptron (MLP) models offer significant potential, their application is hindered by challenges in optimization, data imbalance, and interpretability. This systematic literature review aims to address these issues by synthesizing current research on MLP model optimization for heart disease prediction, focusing on strategies for handling class imbalance and achieving model transparency with SHapley Additive exPlanations (SHAP). Following PRISMA guidelines, a structured search of major scientific databases resulted in the in-depth analysis of 30 peer-reviewed studies. The findings indicate that MLP optimization is increasingly sophisticated, employing automated hyperparameter tuning and novel architectures. For class imbalance, the Synthetic Minority Over-sampling Technique (SMOTE) is the predominant data-level solution, though a trend towards advanced algorithm-level techniques is emerging. The application of SHAP has successfully validated models by confirming the importance of known clinical risk factors like age and chest pain type, while also demonstrating potential for new discovery. This review concludes by providing a comprehensive roadmap for researchers, highlighting a critical need for comparative studies on imbalance techniques, deeper applications of explainable AI for local-level analysis, and a stronger focus on validation using large-scale, real-world clinical data to develop truly robust and trustworthy predictive systems.

Indonesian Public Sentiment Toward Electric Vehicles: Analysis of Social Media Data

Sat, 16 Aug 2025 00:00:00 +0000

The development of electric vehicles (EVs) in Indonesia has progressed significantly, supported by government subsidies for Battery-Based Electric Motor Vehicles. These subsidies have sparked mixed public reactions that some support them due to environmental benefits and pollution reduction, while others oppose them for various reasons. Social media platform X serves as a valuable source for gauging public opinion, though analyzing such data manually can be complex. To address this, sentiment analysis, particularly using the Support Vector Machine (SVM) method, offers an efficient solution. This study analyzes 23,031 Indonesian-language tweets from social media platform X, collected between October 2023 and July 2024, using SVM for sentiment classification. The best-performing model, with parameter C = 0.5 and without stemming, achieved an accuracy of 84.98%. The findings suggest that Indonesians generally view electric vehicles positively, with more favorable sentiments than negative ones. This study offers implications across methodological, industrial, and policy domains. Word cloud analysis further supports this, highlighting public support in areas such as pricing, infrastructure, and environmental impact. However, the study also identifies key concerns, including issues around subsidies, taxes, vehicle durability, battery types, and import regulations. Overall, the research provides meaningful insights into the diverse perspectives of Indonesian citizens regarding EVs, helping to inform future policy and development strategies.

Mathematical Modeling of the Vehicle Routing Problem with Relaxed Time Windows and Delay Penalties

Rosa Fitrie, Saib Suwilo, Herman Mawengkang — Sat, 16 Aug 2025 00:00:00 +0000

The Vehicle Routing Problem with Relaxed Time Windows (VRP-RTW) is an extension of the classic Vehicle Routing Problem (VRP) that incorporates flexibility in service time windows. In VRP-RTW, vehicles are allowed to arrive later than the specified time window. However, a violation will be imposed for exceeding the specified time limit. in the form of fines or similar penalties. This research aims to design a mathematical model for VRP-RTW to minimize total travel costs and delay penalties, while ensuring that all customers are served within the capacity limits of the available vehicles. This research uses literature review methods and mathematical formulation approaches to describe the logistics distribution problem. The developed model considers several constraints, such as vehicle capacity, route balance, and service time limitations. The results of this research are expected to contribute to more efficient and flexible logistics distribution decision-making and serve as a basis for the development of vehicle route optimization models that can be applied in real-world scenarios.