ejournal.nusamandiri.ac.id (STMIK Nusa Mandiri)
Not a member yet
1504 research outputs found
Sort by
OPTIMISASI PEMILIHAN FITUR UNTUK PREDIKSI GAGAL JANTUNG: FUSION RANDOM FOREST DAN PARTICLE SWARM OPTIMIZATION
Get PDFHeart failure is a serious, life-threatening cardiovascular disease that increases with age and unhealthy lifestyles. Early prediction is essential to provide timely treatment and reduce mortality. The use of machine learning techniques, especially the Random forest (RF) method, for predicting heart failure has been previously researched, so the problem that occurs is that the RF method does not have maximum results because of irrelevant features. Selection of relevant features is a key step in building an accurate prediction model. Particle Swarm Optimization (PSO) is used to improve feature selection by searching for optimal combinations. The aim of the research is to reduce the mortality rate by improving the RF method with relevant features so as to increase the accuracy of predictions with Fusion RF and PSO. The results show an increase in accuracy of 02.78% to 87.33% with PSO, although the AUC decreased by 0.031%. The advantage of PSO is a significant increase in accuracy, but the disadvantage is a slight decrease in AUC. Future developments could explore how to address AUC degradation without compromising accuracy and transmitting additional relevant features
ANALISIS KEPUASAN PENGGUNA WEBSITE ORLANSOFT MENGGUNAKAN METODE WEBQUAL 4.0
Get PDFOrlansoft website is an ERP (Enterprise Resource Planning) solution that unifies business operations into a single system that integrates and optimizes business processes and provides real-time critical information for all entities and office locations from a single source. PT Multifortuna Sinardelta, in its business processes, uses the Orlansoft website. The quality of the website greatly affects the level of user satisfaction itself. The higher the quality of a website, the more users will access the website. So far, there is no appropriate method and way to measure user quality of the Orlansoft website. This research examines the extent of user satisfaction in using website services. The Webqual 4.0 method has been successfully applied to similar research with website quality measurement and helps to understand the factors that affect user satisfaction, with three measurement categories including usability, information quality and service interaction quality. From the test results, the calculated F value = 11.536 with a significance of 0.0000011. In this study, the calculated F value is 11.536> F table 2.81 and the significance value is 0.0000011 <0.01, thus it can be concluded that variables X1 (usability quality), X2 (information quality), and X3 (service interaction quality) have a significant and positive effect on variable Y (user satisfaction). This is evidenced by the results of the analysis which gives positive results for each variable on the dependent variable
PREDICTIVE MODELING OF BROILER CHICKEN PRODUCTION USING THE NAIVE BAYES CLASSIFICATION ALGORITHM
Get PDFSerious challenges are faced by broiler chicken farmers in Seumirah Village, Nisam Antara Subdistrict, North Aceh Regency, in their efforts to create high-quality and productive chickens. These difficulties not only impact the farmers' income but also result in recurring losses every year. This research aims to design a system using the Naive Bayes Classifier algorithm to assess the capacity and classify production types based on specific criteria such as population, age, depletion, FCR (Feed Conversion Ratio), IP (Index Performance), and BW (Body Weight). The system aims to classify broiler chicken production as either increasing (profitable) or decreasing (unprofitable). In the development of this predictive system, the PHP programming language is employed, with a MySQL database as the data storage medium. The results of this broiler chicken production prediction system have proven effective in providing information in the form of profit or loss reports based on the harvest results for each monthly period. The implementation of this system is expected to assist in optimizing farmers' production management, increasing business profitability, and providing better guidance for future business decisions. The classification results using the Naive Bayes method indicate an accuracy rate of 86,67 and error rate of 13,3%
AN INNOVATIVE LEARNING ENVIRONMENT: G-MOOC 4D TO ENHANCE VISUAL IMPAIRMENTS LEARNING MOTIVATION
Get PDFThe proliferation of visual impairment among school-age children in Indonesia has prompted the need for specialized online learning solutions. The G-MOOC 4D platform, a novel Learning Management System (LMS), is designed to address this need by leveraging gamification and artificial intelligence to enhance accessibility for visually impaired users. This study reports on the development and testing of two AI models within the G-MOOC 4D framework: a facial recognition model for secure user authentication and a voice command model for interactive learning. User Acceptance Testing (UAT), conducted with expert users, namely teachers at a special needs school, showed high approval rates for the platform's features. The results show that all metrics, accuracy, precision, and recall reach their optimal values at a distance of 40 cm for face detection. The respective metric scores at that distance, precision: 100%, accuracy: 98%, and recall: 97%. Additionally, the voice command functionality tested achieved a 100% recognition rate, reflecting the platform’s potential to significantly ease the learning process for visually impaired students. The findings underscore the importance of integrating assistive technologies into educational platforms to ensure all students have equal access to learning opportunities
THE ROLE OF INFORMATION SYSTEMS IN ADVANCING SMART VILLAGES: A RURAL TOURISM CASE STUDY
Get PDFRecent studies highlight the need for a deeper understanding of the ways in which information systems, local government policy and community involvement affect the development of rural tourism. By using Structural Equation Modelling and Partial Least Squares (SEM-PLS), the current study aims to analyze the role of information systems, local government policy and local community engagement in rural tourism development. Using data from 69 participants in Watesjaya village, Bogor regency, the study analyzes multiple relationships among latent constructs. The data, encompassing variables such as system quality, information quality, local government policy, local community engagement, destination branding, and rural tourism development, undergoes meticulous reliability and validity assessments. Results from the SEM-PLS analysis unveil significant relationships and insights. Local community engagement emerges as a pivotal factor, positively influencing tourist satisfaction (0.499) and moderately affecting destination branding (0.239). However, local government policy exhibits a less pronounced positive impact on tourist satisfaction (0.069847) and a notable negative influence on destination branding (-0.300460), underscoring the need for policy realignment. Information quality paradoxically influences tourist satisfaction negatively (-0.185) and destination branding (-0.158), highlighting areas for strategic improvement. Meanwhile, information system quality positively affects tourist satisfaction (0.055) and significantly contributes to rural tourism development (0.783). This study provides a better understanding of stakeholders about rural tourism development by focusing on information system quality, information quality, local government policies, and local community engagement The study indicates that information system quality and local community engagement can be valuable indicators for boosting rural tourism development and improving tourist satisfaction
ENHANCING MOBILE CRYPTOCURRENCY WALLETS: A COMPREHENSIVE ANALYSIS OF USER EXPERIENCE, SECURITY, AND FEATURE DEVELOPMENT
Get PDFThe surge in cryptocurrency usage has increased reliance on cryptocurrency wallet applications. However, the usability, security, and feature richness of crypto wallets require significant enhancements. This research aims to identify critical factors that should guide the future design of mobile cryptocurrency wallets. The first step was to collect user reviews on several popular crypto wallets as the dataset. A total of 5,466 mobile wallet-related reviews from mobile application stores were filtered and analyzed. A machine-learning approach was used to cluster the user reviews. The analysis shows that customer issues are divided into four main themes: domain-specific challenges, security and privacy concerns, misconceptions, and trust issues. A software process assessment was also conducted to examine the current state of crypto wallets in terms of security, usability, and feature richness. Around 21 crypto wallet platforms were explored and assessed. Based on the thematic analysis and software process assessment, feature recommendations are proposed to address these shortcomings and enhance the credibility of mobile cryptocurrency wallets
DETEKSI RUPIAH EMISI 2022 UNTUK DISABILITAS NETRA MENGGUNAKAN YOLOV5M DENGAN OUTPUT SUARA
Get PDFPeople with visual disabilities have difficulty recognizing rupiah denominations using blind codes due to differences in paper size for each denomination, wrinkled paper, and variations in blind codes for different emission years.. The proposed method uses the YOLOv5m algorithm as well as Google Text to Speech (GTTS) as voice output. The aim of the research is to find a model with the best precision value from YOLOv5m in detecting the 2022 emission rupiah and integrate it into GTTS to produce nominal rupiah sounds. The model was trained with the main image dataset, namely 700 images of rupiah emissions in 2022 taken at an angle of 1200. Next, the model was tested to recognize seven nominal amounts, namely IDR 1,000, IDR 2,000, IDR 5,000, IDR 10,000, IDR 20,000, IDR 50,000, and IDR 100,000. The test results show that the best YOLOv5m model is the one that has been trained using the main dataset (700 images) and supplemented with a multi-class image dataset (250 images) and background images (30 images). This model has a precision value of 82% when testing in real time. This research succeeded in applying the YOLOv5 algorithm which is integrated with Google Text to Speech to detect the image of 2022 emission rupiah banknotes
PENERAPAN HYPERPARAMETER MACHINE LEARNING DALAM PREDIKSI GAGAL PINJAM
Get PDFLoans or credit are one of the key factors in advancing the economy. One of them is encouraging business expansion which will have a direct impact on a country's economic growth. Banks and other financing institutions must be able to evaluate the borrower's ability to pay their debts based on the inherent risks to reduce the possibility of default. To this end, machine learning (ML) has emerged as a revolutionary tool in using advanced prediction methods to examine historical data based on customer behavior. This research investigates the application of ML in predicting loan outcomes by optimizing parameters in the Machine Learning algorithm. The ML algorithms examined in this research are Logistic Regression (LR), K-Nearest Neighbor (KNN), Random Forest (RF), Decision Tree (DT), and XGBoost (XGB). Meanwhile, the technique used in hyperparameter tuning is Grid Search Cross Validation (CV). The results show that the algorithm's performance is more optimal than before, it can be seen that the LR algorithm experienced an increase in accuracy of 5%, KNN by 4%, RF by 3%, DT by 3%, and XGB by 2%. By including a default dataset based on customer behavior and optimized algorithm parameters, apart from being able to answer the alignment in previous literature in providing a deeper understanding of loan estimation, this research can also provide an understanding that hyperparameter techniques are worth trying to improve the performance of ML algorithms. So, it will be easier for financing institutions to determine the right loan scenario
PENDAMPINGAN LITERASI KEUANGAN DAN PEMASARAN MENJADI ENTREPRENEUR MARITIM PADA NELAYAN TANGKAP TANJUNG SEBAUK TANJUNGPINANG
Get PDFThis Community Service activity focuses on optimizing catches and financial management, including: socialization of seafood processing, digital marketing training, and financial management literacy assistance with the aim of improving the economic welfare of capture fishermen in Tanjung Sebauk, Tanjungpinang,. Through this approach, it is expected to increase the income of fishermen and encourage the economic independence of coastal communities. The method used is a socialization program and direct assistance to capture fishermen, focusing on the use of social media as a marketing platform and the application of simple financial management principles. Data were obtained through observation, interviews, and documentation of activities. The results of this activity show an increase in fishermen's income after participating in the program, which is due to the expansion of market reach and better financial management. In conclusion, this mentoring program proved effective in empowering capture fishermen and encouraging them to become maritime entrepreneurs. However, support from all parties is needed to ensure the sustainability of the program and changes in fishermen's behavior in the long run
ANALISIS PENGARUH KUALITAS PRODUK TERHADAP KEPUASAN PELANGGAN MENGGUNAKAN METODE REGRESI LINIER
Get PDFThis research was conducted to explore and evaluate whether product quality affects customer satisfaction at the Mixue branch in Margonda. The study participants were customers who purchased ice cream or drinks at the Mixue Margonda branch. The sample consisted of 50 respondents selected through an online questionnaire distribution. The approach used was quantitative, and SPSS version 26 was used for data analysis. The validity and reliability of the research instruments were tested. Data analysis employed simple linear correlation and regression with product quality (x) and customer satisfaction (y) variables. The correlation results demonstrated a significant positive relationship between product quality and customer satisfaction. Simple linear regression showed the equation y = 3.341 + 0.746x, and partially, the product quality variable had a relevant impact on customer satisfaction. This research confirms that product quality significantly impacts customer satisfaction at the Mixue outlet, highlighting the importance of improving product quality to enhance customer satisfaction