ejournal.nusamandiri.ac.id (STMIK Nusa Mandiri)
Not a member yet
1504 research outputs found
Sort by
PERANCANGAN SISTEM SIMPAN PINJAM MENGGUNAKAN OBJECT-ORIENTED SOFTWARE ENGINEERING PADA PT. AUTO PRIMA MAKMUR
Full text linkPT Auto Prima Makmur Jakarta still faces challenges in managing its savings and loan system, which is currently conducted manually. These problems include recording errors, administrative delays, and a lack of transparency, all of which reduce efficiency, accuracy, and the ability to monitor transactions in real time. This situation also increases the risk of data manipulation and loss, slows down member services, and potentially undermines trust in the company’s credibility. To address these issues, this study aims to design a web-based savings and loan information system that can enhance efficiency, accuracy, security, and transparency in managing employee savings and loans. The proposed system is designed to process transactions, reporting, and monitoring quickly and accurately, while minimizing the risk of errors and data duplication. The development method used is Object-Oriented Software Engineering (OOSE), which emphasizes the use case approach with simple notation yet covers all stages of software engineering. This approach enables the design of a structured, flexible software architecture capable of effectively managing system objects. The analysis results indicate that implementing a web-based system can accelerate savings and loan transactions, simplify reporting and monitoring, and improve data security. In addition, real-time data availability will assist management in making faster and more accurate decisions. Therefore, the implementation of this system will not only digitize the company’s business processes but also improve service quality, strengthen competitiveness, and support the company’s sustainability in facing the challenges of the digital er
PERFORMANCE COMPARISON OF CLASSICAL ALGORITHMS AND DEEP NEURAL NETWORKS FOR TUBERCULOSIS PREDICTION
Full text linkThis study compares the performance of several classical machine learning algorithms and deep neural networks for the prediction of tuberculosis in the Democratic Republic of Congo (DRC), using a sample of 1000 cases including clinical and demographic data. The sample is divided into two sets: 80% for training and 20% for testing. The algorithms evaluated include Support Vector Machine (SVM), K-Nearest Neighbors (KNN), Decision Tree, Random Forest and Convolutional Neural Networks (CNN). The results show that the CNN has the best overall performance with an accuracy of 94%, an AUC of the ROC curve of 93%, an accuracy of 90%, an accuracy of 95%, a sensitivity of 88%, an F1-score of 91.3% and a Log Loss of 0.0386. The Random Forest follows closely behind with an accuracy of 92% and an AUC of 86%. The SVM and KNN models also performed strongly, but slightly less well. The Decision Tree obtained acceptable results, but inferior to the other algorithms evaluated. These results indicate that deep neural networks, and in particular the CNN, are superior for predicting tuberculosis compared with conventional machine learning algorithms. This superiority is particularly marked in terms of accuracy, sensitivity and reliability of predictions, as shown by the performance metrics obtained
ASPECT-BASED SENTIMENT ANALYSIS ON TWITTER TWEETS ABOUT THE MERDEKA CURRICULUM USING INDOBERT
Full text linkThe curriculum has changed once again with the introduction of the Merdeka Curriculum to address learning loss in the education sector. Its implementation has elicited various responses, such as support for granting teachers the freedom to innovate, focusing on essential materials, offering diverse learning methods, and fostering student creativity. However, criticism has also arisen, including issues related to teachers’ lack of understanding, parents' concerns, and the increased workload on students due to numerous projects. To improve educational policies, an in-depth analysis of these responses is essential. This study aims to analyze public sentiment toward the Merdeka Curriculum by applying Aspect-Based Sentiment Analysis (ABSA) using data from Twitter. The research focuses on four main aspects: Teaching Modules (MA), Education Reports (RP), the Merdeka Teaching Platform (PMM), and the Strengthening of the Pancasila Student Profile Projects (P5). Data were collected using specific and relevant keywords for each aspect, followed by preprocessing, labeling, and filtering based on sentiment and aspect. The final dataset comprised 2,359 valid tweets. The ABSA model was developed using IndoBERT with fine-tuning, then tested and evaluated. The results showed that the aspect classification model achieved an accuracy of 97%, F1 score of 97%, recall of 97%, and precision of 97%. Meanwhile, the sentiment classification model achieved an accuracy of 85%, F1 score of 85%, recall of 85%, and precision of 85%. This ABSA model is expected to assist in monitoring public responses and provide valuable insights for policy development, particularly within the context of the Merdeka Curriculum
CAUSAL MODELING OF FACTORS IN STUNTING USING THE PETER-CLARK AND GREEDY EQUIVALENCE SEARCH ALGORITHMS
Full text linkStunting is one of the nutritional problems that can hinder the growth and development process in toddlers. Untreated stunting can lead to fatal outcomes. Previous research on the factors that exist in the incidence of stunting mostly used multivariate analysis. Previous research on stunting factors has primarily used multivariate or correlation analyses. However, this study uniquely focuses on establishing causal relationships between these factors, a crucial step in improving early diagnosis for stunting prevention and treatment. The data used in this research was 83 data on stunting incidents and consisted of eight parameters. The purpose of this study is to model the causal relationship between factors that represent the incidence of stunting. This study uses two simple causal approaches, namely the Peter-Clark (PC) algorithm to obtain the initial concept of a graph model of the relationship between variables and the Greedy Equivalence Search (GES) algorithm to refine the model by obtaining the direction of the causal relationship. There are six bi-directed relationships that have been found, namely from food variables to support; maternal knowledge with sanitation; Height/Age and Weight/Age with Child Nutrition; height/age with weight/age and stunting. In addition, both algorithms in this study have successfully obtained a causal model, by comparing performance using directional and causal densities that the GES algorithm was able to identify a relationship of 0.66 compared to the PC algorithm
IMPLEMENTASI YOLOV5 UNTUK DETEKSI KARTU DEBIT: STUDI KASUS PADA KLASIFIKASI BRITAMA DAN SIMPEDES
Full text linkThis study aims to develop an object detection model based on YOLOv5 to classify debit card types. With the advancement of financial technology, the need for automated systems to identify debit cards has become essential to enhance transaction efficiency and security. The research methodology involves five main stages: dataset collection, data preprocessing through labeling and resizing to 640 x 640, dataset augmentation, YOLOv5 model training, and model evaluation. The dataset used consists of three categories of debit cards, with a total of 300 images. The results demonstrate that the YOLOv5 model achieves excellent performance with a mean average precision (mAP) of 92.7% and an object loss value of 0.08. The high mAP value indicates the model’s capability to accurately recognize objects, while the low object loss value reflects minimal detection errors during testing. In conclusion, YOLOv5 has proven to be reliable for application in debit card detection systems. This study provides significant contributions to the development of automation systems in the financial sector, particularly in improving the efficiency and accuracy of identification processes. It is hoped that this research will serve as a foundation for further studies with broader datasets, the application of more advanced augmentation techniques, and the utilization of more sophisticated hardware to enhance model performance
PERANCANGAN SISTEM INFORMASI WEBSITE PROFILE SEKOLAH SEBAGAI SARANA PROMOSI
Full text linkThe development of information technology encourages educational institutions to utilize digital media in supporting promotional activities and information dissemination. This research aims to design a website-based school profile information system that functions as a promotional medium and increases the dissemination of information and expands the reach of school promotion to the community, especially prospective students and parents. This information system is designed to increase transparency, accessibility, and effectiveness in conveying school information to the public. This information system presents information about school profiles, school activities, school facilities, and school contacts in an interactive and structured manner. The Waterfall method is used in system development, which consists of the stages of requirements analysis, design, implementation, testing, and maintenance. In the needs analysis stage, the main information required is identified through interviews and surveys. Then, the interface design was made with attention to the aspects of user-friendliness and responsiveness for various devices. The implementation phase uses the codeigniter framework to build a dynamic and easy-to-manage system. Testing is carried out using the blackbox testing method to ensure that the system functionality runs according to specifications. The results of the study show that this website-based school profile information system is able to present information effectively, increase school visibility, and facilitate interaction with prospective students and parents. This system can also provide added value in building the school's image in the digital era
WORD2VEC OPTIMALIZATION USING TRANSFER LEARNING IN INDONESIAN LANGUAGE FOR HIGHER EDUCATION
Full text linkNatural language processing (NLP) in Indonesian faces challenges due to limited linguistic resources, particularly in developing optimal word embedding models. This study optimizes the Word2Vec model for Indonesian in higher education contexts by leveraging transfer learning and lexicon expansion. Using a dataset of 4,463 higher education related tweets consisting of positive and negative sentiment categories, the proposed NewWord2Vec model combined with a Support Vector Machine (SVM) classifier achieved a 4% improvement in word detection accuracy compared to the standard Word2Vec. This enhancement demonstrates better performance in capturing linguistic nuances and sentiment orientation in Indonesian text. However, the model’s applicability remains limited to higher education terminology, and potential biases from transfer learning must be addressed. Future research should expand the dataset to diverse domains and refine the transfer learning process to better capture contextual variations in Indonesian. These findings contribute to advancing NLP applications in Indonesian, particularly for automated assessment systems, recommendation tools, and academic decision-making processe
MONITORING ELDERLY HEART RATE BASED ON OXIMETER SENSORS
Full text linkHeart rate check is an important step in preventing heart attacks that is often not realized by the elderly. However, independent heart rate checks by the elderly have not utilized technology, especially Android. This study design a heart rate detector using the Max30102 Oximeter Sensor integrated with Android device from the elderly aged 60 to 75 years and displays the results of the heart rate per minute (BPM) along with normal or abnormal status on the Android application. The prototype method involves the stages of development, testing, and evaluation of the tool. The results of the study showed that this heart rate detector was able to provide data on heart rate per minute (BPM) that was accurate and easily accessible to the elderly, so that the elderly could check their health independently. The test results indicate a detection accuracy of 97% with a standard deviation of 1.19 BPM, which is higher compared to studies using the Max30100. Thus, this tool is expected to help increase the independence of the elderly in monitoring heart health and reduce the risk of heart attack through routine monitorin
YOLO MODEL DETECTION OF STUDENT NEATNESS BASED ON DEEP LEARNING: A SYSTEMTIC LITERATURE REVIEW
Full text linkMaintaining proper student neatness (uniform compliance, grooming standards, and posture) is essential for fostering disciplined learning environments. While traditional monitoring methods are labor-intensive and subjective, computer vision-based solutions leveraging You Only Look Once (YOLO) architectures offer promising alternatives. The objective of this study is to evaluate YOLO optimization techniques for student neatness detection, identify key challenges, and propose relevant future research directions. This systematic review evaluates 28 recent studies (2021-2024) to analyze optimization techniques for YOLO models in student neatness detection applications. Key findings demonstrate that attention-enhanced variants (e.g., YOLOv10-MSAM) achieve 87.0% [email protected], while pruning and quantization methods enable real-time processing (50-130 FPS) on edge devices like Jetson Orin. The analysis reveals three critical challenges: (1) occlusion handling in crowded classrooms (10-15% false negatives), (2) lighting/background variability, and (3) ethical concerns regarding facial recognition. Emerging solutions include hybrid vision-language models for explainable detection and federated learning for privacy preservation. The review proposes a taxonomy of optimization approaches categorizing architectural modifications (attention mechanisms, lightweight backbones), data augmentation strategies (GAN-based synthesis), and deployment techniques (TensorRT acceleration). Future research directions emphasize multi-modal sensor fusion and domain adaptation for cross-institutional generalization. This work provides educators and AI developers with evidence-based guidelines for implementing automated neatness monitoring systems while addressing practical constraints in educational settings
PKM PENDAMPINGAN DIGITALISASI SEKOLAH SMPIT AJIMUTU GLOBAL INSANI TAMBUN UTARA-BEKASI BERBASIS ARTIFICIAL INTELLIGENCE
Full text linkDigital transformation in education is inevitable; however, many schools such as SMPIT Ajimutu Global Insani still face challenges in adopting technology. The main issue lies in the manual learning evaluation process, which leads to teacher time inefficiency and limited question variation, ultimately affecting learning quality. This community service program aims to bridge the digital gap by implementing an Artificial Intelligence (AI)-based solution. The novelty of this initiative lies in the use of the Question Maker Application (QUMAA)—an innovative tool that automates question generation and includes a question difficulty analysis feature, offering a comprehensive approach to digitizing school evaluation systems. The program was carried out through a participatory method consisting of five stages: needs assessment, application development, intensive training and mentoring for teachers, implementation and evaluation, as well as monitoring and sustainability planning. The results showed that the learning evaluation process was successfully digitized, with teachers’ ability to understand and use AI increasing by more than 50%, and question preparation time reduced by up to 50%. This program not only facilitated technology transfer but also empowered teachers and strengthened the school institution. The implementation of the AI-based QUMAA proved effective in improving efficiency and quality in learning evaluation. Furthermore, this model can be replicated in other schools as a concrete contribution to achieving the SDGs in education, emphasizing the need for ongoing support and funding to sustain digital innovation in the education sector