ejournal.nusamandiri.ac.id (STMIK Nusa Mandiri)
Not a member yet
1504 research outputs found
Sort by
PROTOTYPE PARKING SENSOR ON A SHIP AT THE DOCK USING SENSOR BASED ON ARDUINO UNO R3
Get PDFThe main issue that needs to be addressed in this research is to enhance the safety and efficiency of the vessel berthing process by reducing the risk of collisions with the dock. With the advancement of technology in the maritime industry, there is still a reliance on various parties such as tugboats, ship crew, and dock authorities to ensure safe vessel berthing. Therefore, it is necessary to design a modern technology-based parking sensor system to provide assistance in the vessel berthing process. By using a parking sensor system based on the Arduino Uno R3 and ultrasonic sensors JSN-SR04T and AJ-SR04M, this research aims to address the risk of collisions with the dock, which can result in serious damage to the vessel, dock, and the surrounding environment. This parking sensor system is designed to reduce this risk by providing early warnings to the users. Furthermore, the research aims to reduce dependence on human factors and minimize human errors. Lastly, the research also aims to improve the efficiency of the vessel berthing process. By designing and implementing this prototype, the research aims to provide a technological solution to address the above-mentioned issues, enhance safety, and optimize the vessel berthing process around Motor Vessel BIN NO.2 EKS. SANYO MARU NO.8
UNVEILING GENDER FROM INDONESIAN NAMES USING RANDOM FOREST AND LOGISTIC REGRESSION ALGORITHMS
Get PDFGender detection can be done in many ways, some of these ways by using image identification such as the process of image identification based on faces or image shapes, on the other hand image identification and detection can also be done based on text or written data. The usefulness of gender identification can be used in various aspects of life, ranging from greetings such as ladies and gentlemen, which will certainly make the person concerned feel more appreciated by the accuracy of the pronunciation of the name. This gender identification and detection process can be done by making class predictions on predetermined gender label classes. Of course, each name in various languages has different characteristics in identifying and representing each gender, as well as Indonesian names that have diversity and unique levels of variation. The purpose of this study is to test the results of the algorithm in classification based on class labels. The application of this detection uses two algorithms, namely Random Forest and Logistic Regression. Both of these algorithms can predict classes with perfect accuracy in 6 experimental data, then the results of 526 experimental data resulted in a final accuracy of 0.94 for logistic regression and 0.93 for random forest. The advantage with a thin difference in this case is in the Logistic Regression algorithm
MULTILEVEL MODAL VALUE ANALYSIS FOR INTERPRETING CATEGORICAL K-MEDOIDS CLUSTERS DATA
Get PDFConsumer segmentation plays a crucial role for business owners in developing their enterprises. K-Medoid is commonly used for segmentation functions due to its low computational complexity. However, K-Medoid has limitations, such as the variability in cluster sizes across different iterations and the challenge of determining the optimal number of clusters. The Davies-Bouldin Index (DBI) is a metric used to evaluate the number of clusters by calculating the ratio between the within-cluster distance and the between-cluster distance. Most segmentation studies typically stop at the formation of clusters without further interpretation, particularly when dealing with categorical data. This study aims to modify the use of K-Medoid and propose a method for interpreting clusters with categorical data. The research began with questionnaire design and the data collecting from 100 respondents, which was normalized in the second stage. Clustering used K-Medoid with variations K values from K=2 to K=10, with each K value tested 10 times. The clustering results were evaluated using the DBI to select the optimal clusters. Data interpretation conducted using modal values, calculated as the ratio of the number of times a specific attribute variable was selected by respondents to the total number of data points in the cluster. Utilization and hierarchical visualization of modal values proposed in this study offer insights into the dominant variables within an attribute and also depict the relationships between attributes based on the ranking of modal values. These advantages facilitate business analysts in labeling clusters for developing consumer-driven business strategies
OUTSOURCED EMPLOYEE RECRUITMENT DECISION SUPPORT SYSTEM WITH FUZZY TOPSIS INTEGRATED REST API METHOD
Get PDFPT Dina Mika Muda Mandiri is a logistics and transportation company that is facing challenges in recruiting outsourced employees to meet the company's standards with complex assessment criteria. In overcoming this problem, the research developed a decision support system that is integrated with Rest API and the Fuzzy Technique for Order Preference by Similarity to Ideal Solution (TOPSIS) method. The system aims to improve the efficiency and accuracy of candidate selection by evaluating criteria such as interviews, knowledge, testing, curriculum vitae (CV), processing time, and salary. Two case studies were conducted involving 36 applicants for a website upgrade project and 24 applicants for an outsourced goods transit system. The results demonstrate that the decision support system integrated with Fuzzy TOPSIS significantly enhanced the selection process, improving accuracy by 91% for the website upgrade project and 97% for the goods transit system when compared to traditional human resource development (HRD) decision criteria. This demonstrates the system's effectiveness in aligning with HRD standards, making the recruitment process more effective, accurate and efficient. Future research should explore methods to refine the weighting of criteria and integrate expert opinions or more sophisticated machine learning algorithms to support more objective decision support systems in outsourcing employee recruitment
OPTIMIZING MSME PRODUCT AUTHENTICITY VERIFICATION IN DECENTRALIZED MARKETS USING BLOCKCHAIN
Get PDFBlockchain technology offers a solution for ensuring product authenticity in decentralized digital marketplaces. However, Micro, Small, and Medium Enterprises (MSMEs) face barriers such as limited infrastructure, high costs, and data interoperability challenges. This study develops a hybrid blockchain-based application architecture tailored to MSME needs, integrating on-chain and off-chain storage. Critical security data, such as product hashes, is stored on-chain, while non-sensitive data, like product descriptions, is managed off-chain using a cloud-based MySQL database. This design reduces storage costs and computational load while maintaining data integrity. Ethereum smart contracts manage product registration and verification, linked to QR code-based authentication for end-users. A realistic simulation environment using server-based infrastructure and cloud databases evaluated system performance, including transaction throughput, latency, resource utilization, and scalability. The results show significant improvements compared to conventional centralized methods, achieving a transaction throughput of 391 TPS for 1 million transactions while maintaining low latency and resource efficiency. This research addresses a theoretical gap by optimizing blockchain for small-scale decentralized markets, tackling resource limitations and interoperability issues unique to MSMEs. Practically, it provides a scalable and cost-effective solution for product authenticity verification, enhancing consumer trust and reducing counterfeiting in MSME digital markets. While real-world testing remains a limitation, the findings underline the system’s potential to support sustainable MSME digital marketplaces and build consumer confidence
BEYOND ALGORITHMS: AN INTEGRATED APPROACH TO FAKE NEWS DETECTION USING MACHINE LEARNING TECHNIQUES
Get PDFThe internet has become a major source of information, but it also facilitates the rapid spread of fake news, which can significantly influence public opinion and social decisions. While various techniques have been developed for detecting fake news, many studies focus on individual algorithms, which often result in suboptimal performance. This study addresses this gap by comparing machine learning models, including Support Vector Classification (SVC), XGBoost, and a Stacking Ensemble that combines both SVC and XGBoost, to determine the most effective approach for fake news detection. Text preprocessing was performed using IndoBERT, which provides context-aware and semantically rich text representations specifically for the Indonesian language. The evaluation results demonstrate that the Stacking Ensemble outperforms the individual models, achieving an accuracy of 82%, compared to 79% for XGBoost and 78% for SVC. This superior performance is attributed to the complementary strengths of the base models: SVC excels in handling high-dimensional data, while XGBoost effectively manages imbalanced datasets and captures complex feature interactions. The use of IndoBERT further enhances model performance by improving text representation through contextual embeddings. These findings highlight the effectiveness of ensemble learning in enhancing predictive performance and robustness for fake news detection, demonstrating the potential of combining different machine learning techniques with advanced preprocessing methods to achieve more reliable results
DIGITALLY FILE EXTRACTION OPTIMISED WITH GPT-4O BASED MOBILE APPLICATION FOR RELEVANT EXERCISE PROBLEM GENERATION
Get PDFThis research studies the creation of an AI-driven question extraction system using the GPT-4o model to improve the accessibility and variety of practice questions for students. The study tackles the difficulties in sourcing relevant practice materials and aims to transform educational technology by integrating mobile learning. A mobile application was built with Dart and Flutter, designed to extract questions from PDF files. The system is capable of generating both multiple-choice and essay questions across different difficulty levels. The quality and relevance of the generated questions were assessed using ROUGE metrics. The results indicated strong performance for multiple-choice questions, especially in single-answer and true/false formats. However, the system encountered difficulties in producing complex essay questions, highlighting the need for further improvements in understanding intricate contextual relationships. Key findings reveal effective generation of multiple-choice questions with high precision and recall; inconsistent performance in essay question generation, with simpler questions yielding better results; and ROUGE-1 metrics surpassing ROUGE-2 and ROUGE-L, indicating a stronger ability to generate straightforward questions. The research concludes that while the developed system shows potential in enhancing educational resources, additional research is necessary to refine complex question generation. Recommendations include broadening the training dataset and creating specialized models for question generation tasks to enhance the effectiveness of AI-assisted learning tools
SISTEM DETEKSI GEMPA BERBASIS IOT DENGAN VISUALISASI REAL-TIME DAN NOTIFIKASI CERDAS
Get PDFIndonesia, as a region with high seismic activity, requires a fast, accurate, and reliable disaster mitigation system. However, most existing earthquake detection systems still focus primarily on data collection without automatic notifications, which delays response times in emergency situations. This study develops an Internet of Things (IoT)-based early earthquake detection system that integrates a gyroscope sensor, the ThingSpeak cloud platform, and an Android application to provide real-time information to users. The system detects orientation changes along the X, Y, and Z axes, calculates vibration magnitude through a calibrated algorithm, and sends automatic notifications via WhatsApp to mitigation officers. Testing was conducted through simulations using Wokwi to validate the algorithm and physical implementation in real-world conditions, demonstrating that the system achieves high accuracy in detecting seismic activity, with an average accelerometer magnitude of 3.35 and a gyroscope magnitude of 4.19. Data visualization on ThingSpeak, along with graphical displays in the Android application, enables intuitive and real-time earthquake monitoring. The integration of smart notifications via WhatsApp ensures a fast response from mitigation officers, making it an effective and applicable solution for earthquake risk mitigation
FOREST FIRE LOCATION AND TIME RECOGNITION IN SOCIAL MEDIA TEXT USING XLM-ROBERTA
Get PDFForest fires have become a serious global threat, significantly impacting ecosystems, communities, and economies. Although remote sensing technology shows potential, limitations such as time delays, limited sensor coverage, and low resolution reduce its effectiveness for real-time forest fire detection. Additionally, social media can serve as a multimodal sensor, presenting multilingual text data with rapid and global coverage. However, it may encounter challenges in obtaining location and time information on forest fires due to limitations in datasets and model generalization. This study aims to develop a multilingual named entity recognition (NER) model to identify location and time entities of forest fires in social media texts such as tweets. Utilizing a transfer learning approach with the XLM-RoBERTa architecture, fine-tuning was performed using the general-purpose Nergrit corpus dataset containing 19 entities, which were relabeled into 3 main entities to detect location, date, and time entities from tweets. This approach significantly improves the model's ability to generalize to disaster domains across multiple languages and noisy social media texts. With a fine-tuning accuracy of 98.58% and a maximum validation accuracy of 96.50%, the model offers a novel capability for disaster management agencies to detect forest fires in a scalable, globally inclusive manner, enhancing disaster response and mitigation efforts
PENGEMBANGAN KAPASITAS SUMBER DAYA MANUSIA KOPERASI SYARIAH BERBASIS MASJID DI KOTA BANDUNG
Get PDFMosque-based sharia cooperatives are increasing in number in Bandung City. The problem faced by mosque-based sharia cooperatives is the limited capacity of human resources to prepare integrated and up-to-date sharia cooperative financial reporting. Many managers of sharia cooperatives do not have the skills to prepare financial reports based on sharia accounting standards needed to meet job demands. In addition, the lack of training programs is an obstacle to the ability of cooperative managers because training programs require costs for human resource development so that managers can meet the expected standards. Managers also have difficulty adapting to the development of accounting application technology, which can reduce the competitiveness of cooperatives in the business environment. This community service aims to provide management with knowledge about preparing financial reports that comply with standards and how to implement financial accounting for sharia cooperatives in the city of Bandung. The software used is Accurate. Accurate was developed with the aim of continuing to provide ease of financial recording with PSAK standards for various types of businesses from MSMEs to large companies. This activity was carried out by a group of lecturers from the Bachelor of Accounting study program at Widyatama University in collaboration with the economics sector of the Bandung City MUI and the mosque cooperative center. The implementation method is carried out in four stages, namely preparation, training, evaluation and reporting, and mentoring. The administrators of sharia cooperatives feel they have gained direct knowledge of the subject matter so they are able to prepare sharia cooperative financial reports based on sharia accounting standards