Publication Search

Brake discs are one of the motorcycle spare parts that function to connect and reduce speed when the motorbike is moving, although very simple, this spare part is part of the braking system and has a very important role, without braking it will endanger the driver and other road users. To determine the hardness of the motorcycle brake disc on two original brake discs and variation brake discs on the Yamaha Vision sport motorbike by conducting Rockwell hardness tests on the original and variation brake discs with 10 test variable points. The results obtained for the average value at the level of hardness on the original disc sample are 55.1 HRC and the average value on the variation disc sample is 44.6 HRC, and the conversion hardness value from the Rockwell test. For Brinell testing and tensile testing from the results of Rockwell hardness testing, the average Brinell and tensile test values ​​were converted from the test site with the average Brinell conversion results for the original disc being 575 HBS, while the average variation disc value was 417.1 HBS, the conversion tensile test value with the results on the original disc was 1626 N/mm² and the variation disc was 1427 N/mm² with 10 variable point Rockwell testing and the conversion value of the Brinell hardness test and the original disc tensile test value was still greater than the variation disc tensile test value.

The instability of the climate is becoming increasingly prominent across Southeast Asia, creating uncertainty in agricultural systems that are highly dependent on seasonal weather patterns. Indonesia, where rice remains the primary staple food, is particularly vulnerable to the effects of rising temperatures and rainfall deficits. This study applies the Seasonal Autoregressive Integrated Moving Average (SARIMA) model to predict rice production while incorporating indicators of extreme climate anomalies. Using publicly available datasets, including FAOSTAT production statistics, NOAA rainfall and temperature anomalies, and climate indices from the World Bank, this model was developed following the Box-Jenkins procedure. Among the configurations tested, the SARIMA model (1,1,1)(0,1,1)₁₂ showed the strongest performance, reflected in a MAPE of 4.62% and low RMSE values. The model indicates that significant El Niño events can reduce annual rice production by 3–7%, while wetter La Niña conditions may support production recovery. These findings highlight the importance of integrating climate-sensitive data into agricultural forecasting. The model presented here could support early warning systems, adaptive farming strategies, and long-term food security planning in Indonesia.

The attendance recording system at PLN ULP Tanjungbalai still relies on manual, paper-based methods, resulting in delays in data recap, reduced efficiency, and a high potential for recording errors. This condition affects the accuracy of employee attendance information, which is essential for administrative activities and managerial decision-making. Based on these issues, this practical work aims to design and develop a web-based e-attendance application as a solution to enhance efficiency, processing speed, and the accuracy of attendance recapitulation. The system was developed using PHP as the programming language and MySQL as the database management system, following several stages including requirement analysis, system design using UML, and implementation of a web-based user interface. The application provides essential features such as user login, daily attendance recording, employee data management, attendance notes (permission, sickness, etc.), and automatic attendance report generation. The system is designed for two types of users—Admin and Employees—each with specific access rights. The implementation results indicate that the e-attendance application significantly improves the efficiency of attendance administration at PLN ULP Tanjungbalai. Data collection and recapitulation become faster, more structured, and less prone to errors, while also enabling administrators to monitor employee attendance in real time. Therefore, this web-based e-attendance application serves as an effective solution to support operational activities and enhance the quality of employee attendance management.

Flower disease detection is a common challenge in modern agriculture. Various factors, such as changes in leaf color, shape, petal structure, and environmental conditions, make it difficult to achieve high accuracy with conventional models. Transfer learning is an effective solution to improve model performance in image detection, especially when available data is limited. This study used several pre-trained models, namely VGG16, ResNet50, and EfficientNet-B0, to detect three types of flower diseases: black spot on roses, white powdery mildew, and leaf rust. The process included data processing, increasing the data volume, model training, and result verification. The results showed that the EfficientNet-B0 model provided the highest accuracy of 97.2%, significantly better than the CNN model created from scratch with an accuracy of 85.1%. This study proves that the transfer learning method is very effective in improving the accuracy of flower disease detection. These results confirm that transfer learning is effective for detecting plant diseases with higher accuracy, especially when the dataset is limited.

Communication is a fundamental human need for conveying information and ideas. However, individuals who are deaf and mute face difficulties in communicating with the broader community that does not understand sign language. This study aims to design and implement a real-time static sign language translator into speech using five flex sensors, an MPU6050 sensor, a Raspberry Pi Pico, an ADS1115 ADC module, and a DFPlayer Mini module as the audio output medium. Testing results show that the device successfully recognizes finger movements and hand orientation. The system is capable of playing audio output corresponding to recognized gestures, with the shortest latency recorded at 1.1 seconds and the longest at 2.8 seconds, achieving a detection accuracy rate of 75% based on 60 tests across 12 sign words. This device supports the translation of 12 simple sign words. The implementation demonstrates potential as an assistive communication tool, although further development is needed to improve accuracy, expand vocabulary, and conduct trials directly with deaf or mute users.

The use of information technology through website development has become a crucial need for MSMEs, including traditional food businesses like Siomay Batagor Bogarasa. This study aims to develop a business profile website using the Odoo-based ERP website module to strengthen brand identity and facilitate information delivery to customers. The development process follows the Software Development Life Cycle (SDLC) stages, including planning, requirement analysis, design, implementation, and testing. The developed website consists of several pages such as Home, About Us, Menu, and Contact Us, presenting information about the business history, product catalog and pricing, sales locations, and contact channels. Testing results indicate that most features function well, with responsive display, smooth navigation, active contact form, and effective social media integration. One issue was found in the Google Maps display, which has not yet accurately shown the business location. Overall, the website provides practical benefits in terms of promotion, communication, and enhancing the professionalism of the business.

The development of information technology has encouraged various organizations, including cooperatives, to digitize their service systems. The Credit Cooperative (Kopdit) CU Mera Ndi Ate is one of the cooperatives that still uses a manual system in managing savings and loans, which causes the service process to be slow, inaccurate, and has a high risk of recording errors. This study aims to design and build a web-based savings and loans system that can be used by members of Kopdit CU Mera Ndi Ate. This system allows members to conduct transactions online, view transaction history, and monitor savings or loan balances. The research methods used are observation, interviews, and literature studies. The system development process uses a waterfall model with stages of analysis, design, implementation, and testing. The result of this study is a prototype of a web-based savings and loans information system that has main features such as member registration, transaction recording, financial data management, and automatic financial report generation. With the implementation of this system, it is hoped that the cooperative can improve work efficiency, speed up services, and provide easy access to information to all members.

The rapid development of the sea transportation industry produces a massive and complex volume of transaction data, requiring strategic management to support managerial decision-making. This research aims to implement the Executive Information System on SeaPass in order to evaluate the performance of ship ticket sales. The research method uses data visualization with a two-level drill-down mechanism, which allows the presentation of information hierarchically from general summaries to specific details. The methodological stages include needs analysis, user interface (UI) design using Figma, front-end implementation with HTML, CSS, and JavaScript, database integration, and system testing through Black Box Testing. The results showed that the SIE implementation successfully integrated operational data, including schedules, ships, and manifests, into an interactive dashboard. The two-level drill-down feature provides the ability for executives to identify operational anomalies and market fluctuations in real-time. In conclusion, the system significantly enhances executive data analysis capabilities, transforming complex transaction data into accurate strategic information, thereby supporting more precise business decision-making and adaptive to the dynamics of the marine transportation market.

The rapid development of digital streaming platforms such as Netflix has generated a large volume of content data with diverse characteristics, thereby requiring effective analytical methods to understand emerging patterns and trends. This study aims to classify Netflix content into two main categories, namely movies and television shows, and to analyze genre trends and content characteristics using a data mining approach with the Naive Bayes algorithm. The dataset used in this study is the Netflix Shows dataset, consisting of 8,809 content entries, with the primary features analyzed including genre, rating, and country of production. The research process begins with data exploration and preprocessing stages, including data cleaning, handling missing values, and transforming categorical features to enable effective model construction. Subsequently, the dataset is divided into training and testing sets to objectively and systematically build and evaluate the Naive Bayes classification model. Model performance is evaluated using accuracy, precision, recall, and F1-score metrics to assess the model’s ability to accurately distinguish between Netflix content types. The experimental results demonstrate that the Naive Bayes algorithm is able to classify Netflix content into Movie and TV Show categories with accuracy, precision, recall, and F1-score values of 100%, respectively. The confusion matrix indicates that no misclassification occurred, suggesting that genre, rating, and country of production features provide a very clear separation between content classes. These findings indicate that the Naive Bayes algorithm can achieve exceptionally high classification performance with optimal evaluation results. The results further reveal distinct differences in characteristics between movies and television shows based on genre and production attributes. Therefore, this study is expected to contribute to the development of content recommendation systems and strategic content management within the streaming industry.

Flower disease detection is a significant challenge in modern agriculture, particularly with factors such as changes in leaf color, petal shape and structure, and environmental conditions affecting the accuracy of conventional models. These factors make it difficult to achieve optimal results using traditional methods. Transfer learning is an effective solution to improve image detection performance, especially when data is limited. This study used several pre-trained models, namely VGG16, ResNet50, and EfficientNet-B0, to detect three types of flower diseases: black spot on roses, white powdery mildew, and leaf rust. The research process included data processing, increasing the data volume using augmentation techniques, model training, and evaluation of the results. Experimental results showed that the EfficientNet-B0 model produced the highest accuracy of 97.2%, significantly better than the CNN model built from scratch with an accuracy of 85.1%. This study demonstrates that transfer learning is highly effective in improving the accuracy of flower disease detection, making it a more reliable alternative to methods that do not utilize pre-trained models, especially for agricultural applications that require high levels of accuracy in disease detection.

The scarcity of real-world data in Air-Conditioning (AC) fault diagnosis necessitates the use of synthetic data; however, rule-based synthetic datasets often suffer from a significant sim-to-real domain gap. To address this, we propose a Model-Data Coevolution (MDC) framework that employs a Simulated Annealing (SA) controller to optimize augmentation parameters. We introduce a novel technique, Stochastic Feature Decoupling (SFD), which applies independent noise to raw and derived features, contrasting it with traditional Logically-Consistent Augmentation (LCA). Empirical results show that SFD significantly outperforms LCA, achieving a weighted F1-score of 0.93 and increasing NORMAL class recall to 82%. We demonstrate that by breaking deterministic feature links, SFD acts as a robust regularizer, utilizing "physically impossible" data to enhance generalization in complex real-world environments.

Diabetes Mellitus is a chronic disease that requires early detection to prevent serious complications. This study aims to implement the Artificial Neural Network (ANN) algorithm with the Backpropagation method to predict the risk of diabetes. The dataset used is the Pima Indians Diabetes Dataset, consisting of 768 medical records with 8 feature attributes. This study employs the Multi-Layer Perceptron method with an architecture of 8 input neurons, two hidden layers, and 1 output neuron. Model evaluation is conducted using a Confusion Matrix to measure accuracy levels. The test results show that the model is capable of predicting diabetes diagnosis with an accuracy rate of 76.62%. Based on these results, it can be concluded that the Backpropagation algorithm is effective as an alternative method for early detection of diabetes, although further development is needed to improve the model's sensitivity to positive cases.  

This study presents a high-accuracy real-time soft failure detection framework for large-scale fiber-to-the-home(FTTH) optical access network using a hybrid ensemble of Isolation Forest and One-Class Support Vector Machine (OCVSM). The proposed model was trainde and validated on a real-word multivariate performance dataset comprising more than 1.8 million samples collected at 5-minute intervals from 50 Optical Line Terminal (OLTs) and over 3,000 Optical Network Terminals (ONTs) across a five-month periode(June-October 2025). Ground-truth validation was performed using 111 confirmed network incidents in October 2025 affecting 12,990 customer. The hybrid ensemble achieved Precision 0.940, Recall 0.982, with an average detection delay of only 7.8 minutes-representing an 87.7% reduction compared to conventional manual response (63.5 minutes). The framework significantly outperforms traditional threesholding and recent ML-based methods while demonstrating practical deployability in live operational enviroments.

This research aims to design and implement a village MSME website as a centralized digital promotional medium to overcome the limitations of conventional marketing and expand the market reach of local products more effectively and sustainably. The system was developed using the waterfall method, encompassing requirements analysis, design, implementation, testing, and maintenance. The system was developed using the PHP programming language and the CodeIgniter framework based on the Model-View-Controller (MVC) architecture to ensure a structured, efficient, and maintainable development process. The implementation resulted in a responsive and user-friendly website equipped with key features such as an informative product catalog, village MSME profiles, and a content management system via an admin dashboard that allows MSMEs to update data independently and flexibly. Functional testing demonstrated that all features functioned well and reliably according to user needs. Therefore, this village MSME website can be concluded as an effective digital solution for increasing the visibility of local products, strengthening MSME competitiveness, and supporting village economic growth through sustainable and integrated online promotion.

Queueing systems play an important role in evaluating service performance, especially in small-scale businesses such as barbershops, where fluctuating customer arrival patterns and limited service capacity often lead to long waiting times. This study aims to analyze the performance of barbershop services using the M/M/1 queueing model and an analytical approach based on experimentally tested arrival (λ) and service (μ) rates. The model was selected because it represents a single-server system with Poisson arrivals and exponentially distributed service times, closely matching real barbershop operational characteristics. Using assumed realistic parameters, the analysis shows that when λ = 12 customers per hour and μ = 6 customers per hour, the system becomes unstable with a utilization rate (ρ) exceeding 1, indicating continuous queue growth. Further simulations with increased service rates demonstrate significant improvements: at μ = 15, the system achieves ρ = 0.8 with an average waiting time of 16 minutes, while at μ = 13, the system remains stable but experiences a long waiting time of approximately 55 minutes. These findings emphasize that barbershop performance is highly sensitive to service speed and that even small increases in μ can produce substantial improvements in queue stability and customer waiting times. The study concludes that barbershops must ensure adequate service capacity—either through optimizing service duration, improving worker efficiency, or adding servers—to maintain service quality and enhance customer satisfaction.

A wall follower robot is a type of autonomous robot that is designed to move by following a wall at a certain distance. This research aims to design and build a Wall follower robot equipped with a Fuzzy-PID control system to improve navigation performance. The robot uses five HC-SR04 ultrasonic sensors to detect the distance to the wall and the surrounding obstacles. The data from the sensor is then processed by a Fuzzy-PID algorithm that combines the advantages of conventional PID control with fuzzy logic, resulting in a more adaptive response to environmental conditions. The test results showed that the robot with Fuzzy-PID control was able to maintain the stability of the distance to the wall more consistently compared to the pure PID control. In addition, the system exhibits better adaptability to complex environmental conditions, such as sharp turns, uneven wall surfaces, and the presence of resistance variations. The application of Fuzzy-PID control has been shown to improve the stability, response speed, and accuracy of the robot's navigation. These findings are expected to contribute to the development of robotic navigation systems for a wide range of practical applications, including automated cleaning robots, environmental exploration, and industrial systems that require reliable autonomous mobility.

This study analyzes the impact of artificial intelligence on youth digital political engagement through a Structural Equation Modeling approach. The development of algorithmic technology has changed the way young people access, assess, and react to political information, requiring an empirical understanding of its mechanisms of influence. This study explores how digital literacy, trust in AI, and perceived usefulness shape online political participation. Data was obtained from an online questionnaire targeting individuals aged 17-30 who are active with AI, then analyzed using the SEM-PLS 4 method. The main findings reveal that digital literacy and trust in AI have a strong influence on perceived usefulness, which acts as a key mediator in encouraging such participation. This indicates that the impact of AI is not direct, but rather occurs through cognitive processes that guide young people in assessing the benefits of technology. The implications of this research emphasize the importance of strengthening digital literacy, algorithm transparency, and responsible AI implementation to strengthen inclusive youth political participation in the digital environment.

Traffic congestion is a persistent challenge in urban areas in Indonesia, where increasing vehicle density creates the need for intelligent traffic monitoring systems. This study aims to develop a real-time vehicle parking system using the YOLOv8 object detection model to provide efficient traffic analysis from live CCTV broadcasts and recorded videos. This study uses a quantitative experimental approach with the implementation of the YOLOv8m model using the Ultralytics library in Python, tested on data collected from CCTV cameras A TCS Dishub Medan and additional footage from mobile devices. Vehicles are detected and counted in two directions up (Up) and down (Down) using virtual detection lines on the video frame. The system performance is evaluated by automatic detection counting with manually recorded ground truth data. The results show that on live CCTV broadcasts, the YOLOv8m model achieves an average precision of 98.96%, a recall of 96.59%, and an F1 score of 97.74% for upstream traffic, while for downstream traffic it achieves 100% precision, 95.64% recall, and an F1 score of 97.730/0. On the other hand, on high-quality recorded videos, all performance metrics achieve 100%, indicating perfect detection accuracy. These findings confirm the effectiveness of YOLOv8 in real-time traffic monitoring, but also indicate that video quality and stream stability affect detection performance. In conclusion, the developed system shows strong potential to support smart city traffic management solutions. Future research should focus on performance optimization under low-resolution live streaming conditions to improve accuracy in practical applications.

This study discusses the introduction of digital signature patterns using the Backpropagation method on Artificial Neural Network (JST) to identify a person's characteristics and potential. The increasing use of digital identities demands a verification system that is more secure, accurate, and adaptive to the variations of each individual's signature. The main problem faced in the signature recognition system is the low level of accuracy when the visual features of the signature have similarities between users, both in terms of shape, size, and stroke pressure. In addition, variations of signatures made by the same individual are also a challenge in the identification process. As a solution, this study implements Principal Component Analysis (PCA) to extract important features from the signature image before the training process using JST. PCA is used to reduce the data dimension so that the learning process becomes more efficient and optimal. A total of 80 signature images were used in this study, consisting of 60 training data and 20 test data. The results showed that the system was able to achieve an accuracy level of 92.5%. These findings prove that the combination of PCA and JST methods is effective in recognizing digital signature patterns and has the potential to be applied to digital security-based biometric identification systems.

Vocational education requires a practice-based learning process supported by complete facilities so that students can master work competencies optimally. However, the condition of the Motorcycle Engineering workshop at Noemuti State Vocational High School shows that the completeness of the disc brake system practice facilities does not meet the ideal ratio standards, which affects the effectiveness of learning. This incompleteness has an impact on the low achievement of students' practical learning outcomes that have not reached the KKM. This study aims to describe the level of completeness of workshop facilities and the results of the disc brake system practice learning, and to determine whether there is a relationship between the two. The research approach uses a quantitative correlational method with a total sampling of 26 students. Data were obtained through observation, questionnaires, and documentation, then analyzed using descriptive statistics, normality tests, linearity tests, Pearson correlations, and coefficients of determination using SPSS 27. The results showed that the average completeness of workshop facilities was 42.27 and the results of practical learning were 42.81, both of which were in the good category. The Pearson correlation test produced a value of r = 0.960 with a significance of 0.000 (<0.05), indicating a very strong and significant relationship. The coefficient of determination (R² = 0.92) shows that 92% of the variation in practical learning outcomes is influenced by the completeness of workshop facilities. The more complete the workshop facilities, the higher the students' practical learning outcomes.