Jurnal Politeknik Negeri Batam (PoliBatam)
Not a member yet
3001 research outputs found
Sort by
FINANCIAL HEALTH ASSESSMENT OF PT. PLN (PERSERO) 2019-2022: TOWARDS FINANCIAL SUSTAINABILITY
No full textThis research aims to measure the financial performance of PT. PLN (Persero) in 2019-2022 uses financial ratios in accordance with the regulations of the Ministry of State-owned enterprises (BUMN). The sample for this research is PT PLN (Persero) financial report for four years. The research method used is a case study with an analysis of liquidity, solvency, activity and profitability ratios. The analysis was carried out based on the Decree of the Minister of BUMN No. KEP-100/MBU/2002. The research results show that the liquidity ratio of PT. PLN (Persero) was 95.02%, 64.98%, 58.63% and 82.30%, respectively. The solvency ratio shows debt to assets of 41.37%, 40.85%, 39.15% and 39.48%. Profitability ratios show ROEs of 0.47%, 0.64%, 1.34% and 1.45%. Based on this analysis, PT. PLN (Persero) was categorized as "Less Healthy" during that period. In conclusion, despite some stable financial indicators, several aspects require further attention to ensure continued positive performance. Companies are advised to improve operational efficiency and debt management to strengthen their overall financial position
Implementation and Evaluation of User-Centered Design in an Online New Student Admissions System for Early Childhood Education
Get PDFThe new student admissions process is often conducted conventionally, requiring parents to visit educational institutions in person to submit physical documents. This approach tends to be inefficient, poses risks of document loss or damage, and slows down data analysis. Promotional methods relying on word-of-mouth and social media are also considered less optimal. To enhance efficiency and user experience, a web-based admissions system was developed using a User-Centered Design (UCD) approach. The UCD method was applied to understand the needs and characteristics of key users, including administrators, admissions committee members, school principals, and parents. The development process involved three iterations, covering user needs analysis, user experience-based interface design, testing, and repeated evaluations. The system includes features such as online registration, data management, a payment system, automated notifications, and geolocation to assist parents in estimating school distance. System evaluation using black-box testing and usability testing resulted in a System Usability Scale (SUS) score of 92.125, classified as "Excellent." These findings indicate that the UCD approach effectively produces systems that align with user needs and improve the efficiency of new student admissions.The new student admissions process is often conducted conventionally, requiring parents to visit educational institutions in person to submit physical documents. This approach tends to be inefficient, poses risks of document loss or damage, and slows down data analysis. Promotional methods relying on word-of-mouth and social media are also considered less optimal. To enhance efficiency and user experience, a web-based admissions system was developed using a User-Centered Design (UCD) approach. The UCD method was applied to understand the needs and characteristics of key users, including administrators, admissions committee members, school principals, and parents. The development process involved three iterations, covering user needs analysis, user experience-based interface design, testing, and repeated evaluations. The system includes features such as online registration, data management, a payment system, automated notifications, and geolocation to assist parents in estimating school distance. System evaluation using black-box testing and usability testing resulted in a System Usability Scale (SUS) score of 92.125, classified as "Excellent." These findings indicate that the UCD approach effectively produces systems that align with user needs and improve the efficiency of new student admissions
Detection of Political Hoax News Using Fine-Tuning IndoBERT
Get PDFIndonesia has experienced a surge in the spread of political hoax news, posing a potential threat to democratic and social stability. This study aims to develop a model for detecting political hoax news in the Indonesian language using IndoBERT, a language model optimized for Indonesian text. The dataset was sourced from Kaggle and comprises 20,928 factual news articles and 2,251 hoax news articles from major Indonesian media outlets, including CNN, Kompas, Tempo, and Turnbackhoax. The imbalance between factual and hoax news articles was addressed through undersampling, resulting in 1,302 samples for each class. The research stages include data collection, preprocessing, IndoBERT model training, and model evaluation. Results indicate that fine-tuning IndoBERT can detect political hoax news with an accuracy of 94.1% and an ROC AUC of 0.991, demonstrating high performance in accuracy and generalization capability. This research is expected to contribute to minimizing the spread of political hoax news in Indonesia and enhance media literacy among the public.Indonesia has experienced a surge in the spread of political hoax news, posing a potential threat to democratic and social stability. This study aims to develop a model for detecting political hoax news in the Indonesian language using IndoBERT, a language model optimized for Indonesian text. The dataset was sourced from Kaggle and comprises 20,928 factual news articles and 2,251 hoax news articles from major Indonesian media outlets, including CNN, Kompas, Tempo, and Turnbackhoax. The imbalance between factual and hoax news articles was addressed through undersampling, resulting in 1,302 samples for each class. The research stages include data collection, preprocessing, IndoBERT model training, and model evaluation. Results indicate that fine-tuning IndoBERT can detect political hoax news with an accuracy of 94.1% and an ROC AUC of 0.991, demonstrating high performance in accuracy and generalization capability. This research is expected to contribute to minimizing the spread of political hoax news in Indonesia and enhance media literacy among the public
Enhancing Website Security Using Vulnerability Assessment and Penetration Testing (VAPT) Based on OWASP Top Ten
Get PDFWebsite security is one of the main concerns in the digital era, given the increasing potential for cyber threats. This research aims to improve website security by using the Vulnerability Assessment and Penetration Testing (VAPT) method that refers to the OWASP Top Ten standard. The applied method includes four main stages: information gathering, vulnerability scanning, exploitation, and reporting. The results showed that there were several successfully exploited vulnerabilities, such as Clickjacking, Improper HTTP to HTTPS Redirection, Directory Listing, and Sensitive Information Disclosure, which were classified based on the OWASP Top Ten. The severity of the vulnerabilities was analyzed using Common Vulnerabilities and Exposures (CVE), Common Weakness Enumeration (CWE), and Common Vulnerability Scoring System (CVSS). The analysis results show that some vulnerabilities have high severity after considering the factual conditions of the system. This research provides specific remediation recommendations to address these vulnerabilities, such as the implementation of security headers, deletion of sensitive configuration files, and dependency updates. With this approach, the research is expected to contribute to improving website security and provide effective mitigation guidelines.Website security is one of the main concerns in the digital era, given the increasing potential for cyber threats. This research aims to improve website security by using the Vulnerability Assessment and Penetration Testing (VAPT) method that refers to the OWASP Top Ten standard. The applied method includes four main stages: information gathering, vulnerability scanning, exploitation, and reporting. The results showed that there were several successfully exploited vulnerabilities, such as Clickjacking, Improper HTTP to HTTPS Redirection, Directory Listing, and Sensitive Information Disclosure, which were classified based on the OWASP Top Ten. The severity of the vulnerabilities was analyzed using Common Vulnerabilities and Exposures (CVE), Common Weakness Enumeration (CWE), and Common Vulnerability Scoring System (CVSS). The analysis results show that some vulnerabilities have high severity after considering the factual conditions of the system. This research provides specific remediation recommendations to address these vulnerabilities, such as the implementation of security headers, deletion of sensitive configuration files, and dependency updates. With this approach, the research is expected to contribute to improving website security and provide effective mitigation guidelines
Comparison of Machine Learning Methods for Menstrual Cycle Analysis and Prediction
Get PDFThis study compares three machine learning methods—Long Short-Term Memory (LSTM), Convolutional Neural Network (CNN), and Decision Tree—for analyzing and predicting menstrual cycles. The dataset consists of 1,665 samples with 80 attributes encompassing information related to menstrual health. These methods were evaluated using accuracy, Mean Absolute Percentage Error (MAPE), and Root Mean Square Error (RMSE) metrics. The results show that LSTM achieved the highest accuracy (91.3%), followed by CNN (88.9%) and Decision Tree (85.2%). LSTM excelled in capturing complex temporal patterns in menstrual cycle data, while CNN effectively identified key patterns, and Decision Tree offered interpretability despite lower performance. This study concludes that LSTM is the most effective model for menstrual cycle prediction. The findings highlight the potential for improved accuracy in reproductive health tracking, with future research opportunities to incorporate additional variables such as hormonal history and lifestyle factors, as well as a focus on data privacy
Improving Attack Detection in IoV with Class Balancing and Feature Selection
Get PDFThe Internet of Vehicles (IoV) represents a specialized application of the Internet of Things (IoT), enabling vehicles to communicate with their surrounding infrastructure to enhance transportation safety and efficiency. However, IoV systems are susceptible to various cyberattacks, including Denial of Service (DoS) and spoofing attacks, which necessitate effective and efficient detection mechanisms. This study investigates the enhancement of detection efficiency for DoS and spoofing attacks in IoV by employing Ensemble Learning methods combined with feature selection techniques. The selected feature selection methods include Information Gain Ratio, Chi-Square (X²), and Fast Correlation-Based Filter (FCBF). The CICIoV2024 dataset, utilized in this study, was balanced using the Random Under Sampling technique to address data imbalance issues. The ensemble algorithms evaluated in this research comprise Random Forest, Gradient Boosting, and XGBoost. Results indicate that all three algorithms achieved high accuracy and F1 scores, reaching 0.985. Moreover, the application of feature selection significantly reduced computational time without compromising detection performance. These findings are expected to contribute to the advancement of IoV security systems in the future
Effect of Virtual Sample Generation in Predicting Corrosion Inhibition Efficiency on Pyridazine
Get PDFThe purpose of this research is to study how the application of virtual sample generation using the linear interpolation and gaussian noise augmentation method impacts the improvement of prediction model performance in the case of corrosion inhibition efficiency using pyridazine. Random Forest Regressor, Gradient Boosting Regressor, and Bagging Regressor are the models used. The coefficient of determination (R2) values for each model are -0.06, 0.05, and 0.12 on the initial data; the RMSE values are 34.80, 32.90, and 31.65, respectively. After the use of virtual sample development, the R2 values significantly increased to 0.99, 0.96, and 0.99, while the RMSE values significantly decreased to 1.59, 2.88, and 1.25. The research results show that the linear interpolation method can enrich the dataset without altering the data distribution pattern, this method significantly improves the model\u27s accuracy. This performance improvement demonstrates the ability of virtual sample generation to overcome the limitations of the original data; ultimately, this results in a more accurate and reliable predictive model. In the field of material efficiency prediction especially for material technology applications and corrosion control this research helps develop data augmentation methods for similar cases.The purpose of this research is to study how the application of virtual sample generation using the linear interpolation and gaussian noise augmentation method impacts the improvement of prediction model performance in the case of corrosion inhibition efficiency using pyridazine. Random Forest Regressor, Gradient Boosting Regressor, and Bagging Regressor are the models used. The coefficient of determination (R2) values for each model are -0.06, 0.05, and 0.12 on the initial data; the RMSE values are 34.80, 32.90, and 31.65, respectively. After the use of virtual sample development, the R2 values significantly increased to 0.99, 0.96, and 0.99, while the RMSE values significantly decreased to 1.59, 2.88, and 1.25. The research results show that the linear interpolation method can enrich the dataset without altering the data distribution pattern, this method significantly improves the model\u27s accuracy. This performance improvement demonstrates the ability of virtual sample generation to overcome the limitations of the original data; ultimately, this results in a more accurate and reliable predictive model. In the field of material efficiency prediction especially for material technology applications and corrosion control this research helps develop data augmentation methods for similar cases
Heavy Equipment Rental Information System Development using the Prototyping Method
Get PDFA private company engaged in heavy equipment rental services, established on June 19, 2012, in Pekanbaru. In the current business process, customers who wish to rent heavy equipment or seek information about it can only do so during office hours, making the rental process less efficient. Record-keeping is still done using Excel, which increases the risk of data loss. Therefore, a solution has been proposed to develop a web-based information system to access and manage the process easily. The information system was developed using the prototyping method. The choice of the prototyping method is made to speed up development time, ease system completion, and avoid discrepancies between developers and users. The information system is then tested through Black Box testing and usability testing. From the Black Box testing results, it was found that the system\u27s functionality for all users has been successfully implemented and operates as expected. Meanwhile, the usability testing results showed an average score of 89%, indicating that users strongly agree with the system\u27s usability. This research helps to facilitate customers and administrators in the heavy equipment rental process by providing quick and easy access to information on prices, schedules, and equipment types, while also improving data recording to reduce the risk of data loss and facilitate administrative tasks
Liquidity vs. Sustainability Dilemma: Do Loan Ratios Hinder Social Transparency in Banks of Emerging Asia-Pacific?
Get PDFThe aim of this study is to analyze the fundamental dilemma in banking concerning the trade-off between liquidity management and sustainability commitments, with a focus on the banking sector in emerging Asia-Pacific economies. The findings reveal that banks with higher Total Loans to Total Deposits (TLTD) ratios tend to exhibit stronger Social Disclosure Scores (SDS), driven by stricter regulatory oversight. In contrast, banks with higher Total Loans to Total Assets (TLTA) ratios demonstrate weaker sustainability disclosures, prioritizing financial performance over ESG commitments. This study highlights the crucial role of regulatory pressure in encouraging banks to improve ESG transparency, even when short-term financial gains are prioritized. The findings underscore the need for policymakers to develop regulatory frameworks that not only enforce sustainability disclosures for high-risk banks but also incentivize asset-heavy institutions to integrate ESG principles into their core financial strategies, ensuring a balanced approach to sustainability and financial stability
Identification Food Nutrition and Weight Prediction using Image Processing
No full textObesity is a global issue with rising prevalence each year, driven partly by excess nutrient and calorie intake. Identifying nutrient content in food is vital to prevent obesity. This research employs image processing, specifically the YOLO (You Only Look Once) algorithm, to classify and identify fruits and vegetables quickly and accurately. YOLO is advantageous for its speed and ability to classify multiple objects simultaneously. The goal is to develop a system that recognizes, classifies, and predicts the weight of fruits and vegetables, providing nutritional and calorie information. Tests showed that the system accurately detects produce under various lighting conditions—achieving 100% accuracy with additional ring light (600–650 lux) and 99.2% without extra lighting. Beyond object detection, the system predicts weight with an average error of 5.6% when illuminated. This technology has the potential to aid users in monitoring nutritional intake by providing reliable identification and calorie data, contributing to obesity prevention efforts