ejournal.nusamandiri.ac.id (STMIK Nusa Mandiri)
Not a member yet
1504 research outputs found
Sort by
PREDIKSI HARGA PONSEL BERDASARKAN SPESIFIKASINYA MENGGUNAKAN ALGORITMA LINEAR REGRESSION
Get PDFThe rapid advancement of mobile technology tools day by day benefits thousands of smartphone retailers by offering various innovations. This study aims to predict smartphone prices based on their technical features using the linear regression method. The dataset used includes various technical attributes from different smartphone models. The research process involves a data preprocessing stage to clean missing or invalid values and feature transformation to prepare the data for the linear regression process. Subsequently, a linear regression model is developed and tested using cross-validation techniques to evaluate its performance. The metric used to measure the model's prediction accuracy or error is RMSE. The experimental results show an RMSE value of 170.692. The target variable, which is the smartphone price, ranges from the lowest price of 614 to the highest price of 4,361. The RMSE value obtained in this study can be considered fairly good, as it is less than 10% of the actual value or average price. Variables such as RAM, storage size, camera, and processor type significantly influence smartphone prices. However, other factors such as brand and design may also have an impact, albeit to a lesser extent. This study confirms that linear regression can be effectively used to predict smartphone prices based on technical specifications. The findings of this research can assist companies in developing pricing strategies based on smartphone specifications. Additionally, it can help determine which products are suitable for market introduction
PERBANDINGAN MODEL MACHINE LEARNING PADA KLASIFIKASI CURAH HUJAN DI BOGOR
Get PDFAccurate rainfall prediction remains a significant challenge due to the involvement of complex physical processes and its substantial impact on various sectors of society. Rainfall prediction can be performed using classification techniques in Data Mining. Each algorithm employed for rainfall prediction may yield different performance outcomes, depending on factors such as the size of the dataset, the number of missing values, and the meteorological parameters utilized in the study. Selecting the appropriate algorithm for rainfall prediction continues to pose a challenge. This study aims to compare the performance of Naïve Bayes, Decision Tree, and Random Forest in order to identify the best model for classifying rainfall in Bogor Regency. The data utilized in this study includes maximum temperature, minimum temperature, average temperature, average humidity, duration of sunlight exposure, maximum wind speed, average wind speed, maximum wind direction, and rainfall. The dataset spans five years comprising a total 1.825 of data obtained from the Class III Citeko Meteorological Station. The results indicate that Random Forest, when trained with a smaller proportion of data compared to the proportion of test data to be predicted, achieves the best performance, with a precision of 59.1%, recall of 64.3%, and f1-score of 65.5%. This performance is attributed to the ensemble principle employed by Random Forest, which combines multiple weak learner trees to produce a robust learner tree
MEASURING INFORMATION TECHNOLOGY GOVERNANCE USING COBIT 2019 FRAMEWORK AT TOURISM INDUSTRY
Get PDFAlthough PT XYZ has adopted information technology, it has not formally assessed its governance, leading to persistent issues in IT management, human resource capabilities, and alignment with business processes. This study evaluates IT governance at PT XYZ, a company in the travel and tourism industry, where rapid technological advancements have impacted operations. Using the COBIT 2019 framework, the study assessed IT governance through interviews and literature review, focusing on the domains APO04 – Managed Innovation, BAI02 – Managed Requirements Definition, BAI03 – Managed Solution Identification & Build, and BAI05 – Managed Organizational Change. The results indicate that these domains are at level 2, "Largely Achieved," highlighting areas of improvement. This benchmark provides practical recommendations to enhance IT governance and improve integration between IT and business functions. The findings offer PT XYZ actionable steps to strengthen governance practices, improve organizational performance, and better align technology with strategic business goals
PERFORMANCE OF THE DELTA MODULATION SYSTEM WITH VARIOUS DELTA STEP SIZES
Get PDFDelta Modulation Systems are widely used in Analog-to-Digital Converter (ADC) systems. This research aims to determine the optimal delta step size that can be achieved in a Delta Modulation system, as the system's performance is highly influenced by the delta step size. The method used involves simulations with MATLAB to identify the optimal delta step value. The performance of a Delta Modulation system is greatly influenced by the Delta step size. The optimal value in this study was achieved at a Delta step size of 0.4 with the smallest error, namely MSE = 0.1186. If the Delta step size is smaller or larger than this optimal value, the MSE increases. When the frequency of the input signal increases, the Delta step size needs to be increased to follow the changes in the input signal. Otherwise, the MSE will also increase, a phenomenon known as Slope-overload Distortion. Granular Noise occurs when the input signal changes very slowly or is almost constant, while the step size is too large, resulting in a high MSE. To overcome this problem, a dynamic Delta step size is needed, adjusted to the frequency changes of the input signal. Such a system with a dynamic Delta step size is known as Adaptive Delta Modulation
FEATURE SELECTION COMPARATIVE PERFORMANCE FOR UNSUPERVISED LEARNING ON CATEGORICAL DATASET
Get PDFIn the era of big data, Knowledge Discovery in Databases (KDD) is vital for extracting insights from extensive datasets. This study investigates feature selection for clustering categorical data in an unsupervised learning context. Given that an insufficient number of features can impede the extraction of meaningful patterns, we evaluate two techniques—Chi-Square and Mutual Information—to refine a dataset derived from questionnaires on college library visitor characteristics. The original dataset, containing 24 items, was preprocessed and partitioned into five subsets: one via Chi-Square and four via Mutual Information using different dependency thresholds (a low-mid-high scheme and dynamic quartile thresholds: Q1toMax, Q2toMax, and Q3toMax). K-Means clustering was applied across nine variations of K (ranging from 2 to 10), with clustering performance assessed using the silhouette score and Davies-Bouldin Index (DBI). Results reveal that while the Mutual Information approach with a Q3toMax threshold achieves an optimal silhouette score at K=7, it retains only 4 features—insufficient for comprehensive analysis based on domain requirements. Conversely, the Chi-Square method retains 18 features and yields the best DBI at K=9, better capturing the intrinsic characteristics of the data. These findings underscore the importance of aligning feature selection techniques with both clustering quality and domain knowledge, and highlight the need for further research on optimal dependency threshold determination in Mutual Information
ANALYSIS OF THE CANTEEN INFORMATION SYSTEM AT AN-NAWAWI ISLAMIC BOARDING SCHOOL USING PIECES
Get PDFThe canteen at An-Nawawi Modern Islamic Boarding School Bogor plays a crucial role in supporting students' daily activities; however, its current information system is not optimally integrated to handle the growing student population and operational complexity. This study aims to analyze the problems within the canteen's information system to identify priority areas for improvement. The methodology employs a quantitative analysis using the PIECES framework, which evaluates six variables: Performance, Information, Economy, Control, Efficiency, and Service. Data was collected by distributing a questionnaire to respondents via Google Forms. The research findings show that among the six variables, the Control variable obtained the lowest average score (563.4), indicating a significant weakness in the supervision and data security aspects of the current system. Therefore, it is concluded that the main priority for future development should be focused on strengthening the control aspects to create a more secure, reliable, and well-managed canteen information system
RE-DESIGNING JAKLINGKO APPS UI/UX USING AGILE REQUIREMENT ENGINEERING APPROACH
Get PDFPublic transportation has become a staple in a lot of countries, including Indonesia. As the largest city in Indonesia, is trying to accommodate the dense traffic in Jakarta by implementing various types of public transportation, one of which is the Bus Rapid Transit (BRT). BRT has its own application called Jaklingko, which the commuter uses to gain information about the BRT. Unfortunately, this application has bad reviews in the app store. This research tried to redesign the UI/UX of this application using prototyping and the System Usability Scale (SUS) as tools for agile requirement engineering tools. In Agile requirements usually conducted the same as traditional which is using interview or observation. But, using this method proved to be time consuming. Therefore this research tried to incorporate prototyping and SUS into the requirements gathering process. After the requirements are collected, the next phase is redesigning the application based on the gathered requirements. From the research conducted, the main pain point of the responses is how much information is given in the apps. This research also found that prototyping and SUS could be used to gather requirements, but they will depend heavily on the test case being used. Therefore, it is not suitable for stand alone gathering tools but good as a confirmation too
COMPARATIVE ANALYSIS OF CLASSIFICATION ALGORITHMS IN HANDLING IMBALANCED DATA WITH SMOTE OVERSAMPLING APPROACH
Get PDFMost machine learning algorithms tend to yield optimal results when trained on datasets with balanced class proportions. However, their performance usually declines when applied to data with significant class imbalance. To address this issue, this study utilizes the Synthetic Minority Oversampling Technique (SMOTE) to improve class distribution before model training. Several classification algorithms were employed, including Decision Tree, K-Nearest Neighbors, Logistic Regression, Support Vector Machine, and Random Forest. Experimental results reveal that the Random Forest model produced the highest accuracy (95.70%) and the best F1-score, demonstrating a well-balanced trade-off between precision and recall. In contrast, the Logistic Regression algorithm achieved the highest recall (74.20%), indicating better sensitivity in identifying positive instances despite a lower F1-score. These outcomes highlight the importance of choosing appropriate classification methods based on the specific evaluation goals whether prioritizing accuracy, recall, or overall model balance
EDUKASI KESEHATAN DASAR PANGGUL DAN LATIHAN KEGEL BAGI IBU HAMIL: PROGRAM KEMITRAAN MASYARAKAT
Get PDFCesarean delivery is associated with complications in pregnant women, including pelvic floor disorders. Kegel exercises can help maintain pelvic floor health and support normal delivery. This community service activity aimed to provide education on pelvic floor health and Kegel exercises to empower pregnant women at Pucang Sewu Public Health Center, Surabaya, in 2024. The program was conducted in three stages: preparation, implementation, and evaluation. Preparation involved coordination, planning, and developing a physical activity book for pregnant women. The implementation phase included education sessions and Kegel exercise training using a two-way communication method. Evaluation was conducted through pretest–posttest and observation of participants’ practice skills. The activity was attended by 27 pregnant women and 10 healthcare workers. The results showed increased knowledge and skills among participants after the training, indicated by higher posttest scores and active participation during practice. More than half of the participants had never exercised regularly before. This program effectively improved participants’ understanding and ability to perform Kegel exercises. The health center is expected to continue providing education to encourage pregnant women to practice Kegel exercises independently at home
EDUKASI KEAMANAN PANGAN JAJANAN ANAK SEKOLAH DENGAN POLA SAH MENGGUNAKAN MODEL BIOPSIKOSIAL
Get PDFMany school children still have limited knowledge about the safety of snack foods, causing them to choose snacks based on taste without considering the ingredients. To facilitate nutrition education for school children, instructional media in the form of PowerPoint slides were used. The snakes and ladders game method is highly suitable for school-aged students because it is interactive and enjoyable. The aim of this community service activity was to provide education on PJAS (school snacks) safety using the SAH approach (Fresh, Safe, and Hygienic) with the Biopsychosocial model. The method applied was lectures supported by PowerPoint slides. Based on the results of questionnaires regarding students' knowledge about PJAS safety, pre-test and post-test scores were obtained. Data were collected through questionnaires and analyzed using the Wilcoxon Signed Rank Test. The analysis showed an increase in students' knowledge about snack food safety after the intervention. Statistical analysis using the Wilcoxon Signed Rank Test resulted in p = 0.000 (p < 0.05), indicating a significant improvement in students' knowledge and attitudes between pre-test and post-test. Thus, PJAS food safety education using the Biopsychosocial model approach was proven effective in improving students' knowledge and attitudes regarding snack food safety