ejournal.nusamandiri.ac.id (STMIK Nusa Mandiri)
Not a member yet
1504 research outputs found
Sort by
OPTIMIZING DECISION TREE PERFORMANCE WITH RECURSIVE FEATURE ELIMINATION FOR HIGH-DIMENSIONAL MUSHROOM CLASSIFICATION
Full text linkClassifying mushroom species presents a significant challenge within biological data analysis because of the wide variety of species and their distinct attributes. This research investigates the effectiveness of the Decision Tree classifier for mushroom categorization by comparing two splitting criteria, the Gini Index and Entropy. Additionally, the study employs the Recursive Feature Elimination (RFE) method for dimensionality reduction to enhance model efficiency and performance. The dataset was collected, cleaned, and analyzed exploratorily before feature selection was conducted using RFE. The Decision Tree model was trained and evaluated using accuracy, precision, recall, and F1-score metrics. The results showed that applying RFE improved computational efficiency without compromising model accuracy. The Gini criterion provided more stable results across all metrics, while Entropy demonstrated higher precision in certain cases. Model optimization through parameter tuning produced the best parameter combination at max_depth = 5, min_samples_leaf = 5, and min_samples_split = 10. This study concludes that integrating RFE with the Decision Tree can significantly enhance the performance of high-dimensional dataset classification. The findings are expected to serve as a reference for developing efficient and accurate biological data classification model
LOGISTICS SERVICE INFORMATION SYSTEM AUDIT USING COBIT 5 FRAMEWORK
Full text linkKBN Prima Logistik is a subsidiary affiliated with PT. Kawasan Berikat Nusantara which operates in the field of logistics services. In carrying out its business processes, it has implemented an Information System in the form of using desktop-based supporting business applications (Client Server). Some of the current problems are that the applications used are not functioning optimally, IT Governance procedures are not well defined by standards, there is no IT Division in the Organizational Structure that is responsible for IT management and there is a shortage of competent human resources in the IT field. Therefore, it is necessary to measure the Maturity Level and Capability Level of IT governance. So, research was carried out using the COBIT 5 framework as an Information System Audit model. The research method goes through the stages of problem identification, literature study, and domain determination which focuses on the DSS and MEA domains. The data collection method was through interviews and distributing questionnaires filled in by 20 respondents. The research results show that the Maturity Level value in the DSS and MEA domains shows an average value of 1.94 or 194%. Capability Level is still at Level 2 (Managed Process) from the expected Target Level 3 (Established Process). This indicates that although the IT processes has been run and implemented regularly with planning and monitoring according to business process objectives, but the management is not yet optimal and not well standardized. The results of the gap assessment show that the average gap value is 1.06
LITERATURE REVIEW: ADVANTAGES AND DISADVANTAGES OF BLACK BOX AND WHITE BOX TESTING METHODS
Full text linkSoftware testing methods play a crucial role in ensuring the quality, security, and performance of applications. The two main approaches often used are black box and white box testing. This article presents a comprehensive literature review of the characteristics, advantages and disadvantages of both testing methods with the aim of providing in-depth insights for practitioners and researchers in the field of software engineering. The research method used is Systematic Literature Review (SLR), which is a technique of collecting information through the process of searching for literature based on research questions, filtering search results, evaluating, and analyzing relevant research from various academic database sources to gain a comprehensive understanding. Through the analysis of various literature studies, the results of this research are the characteristics of each testing method that is more effectively used in best practice to achieve efficient testing with the coverage of literature review sources in the range of 2020 to 2024. The review of these characteristics is based on seven criteria, namely: test focus, test base, tester's point of view, test case design, program error identification method, program code knowledge, and test effectiveness. In addition, this article presents a comparison of the two methods so that the differences in testing methods can be clearly recognised in terms of how they are implemented. Based on the results of review literature, both methods are better used together in order to ensure that the functional and internal code structure of the software is functioning properly
PASSWORD STRENGTH STUDY USING THE ZXCVBN ALGORITHM AND BRUTE-FORCE TIME ESTIMATION TO STRENGTHEN CYBERSECURITY
Full text linkThis research analyzes password strength based on its length and complexity using brute force attack simulations. The study begins with collecting password data from various sources to ensure sufficient variation in complexity levels. Next, the passwords are evaluated using the Zxcvbn algorithm, which provides a strength score as well as information about the time required to crack them. The same passwords are also evaluated using Brute-force Time Estimation to calculate the estimated time required to crack the password. After both algorithms have been evaluated, the results are analyzed to find the correlation between the Zxcvbn score and the estimated brute force time. The results of the data analysis are then visualized in the form of graphs or diagrams to facilitate understanding and assessment of password security. This simulation estimates the time required to guess a password, depending on the level of password complexity. Although the simulation results show that long and complex passwords are more secure, the actual strength of the password is highly dependent on the tools used by the attacker. In addition, digital security is not only limited to passwords, but also depends on various loopholes that can be exploited, such as personal data leaks or software vulnerabilities. Therefore, a comprehensive security approach is essential to protect users from potential cyberattacks. This study aims to provide in-depth insights into the strength and vulnerability of passwords and the effectiveness of algorithms in assessing password security
DEVELOPMENT OF THE ODOO SYSTEM FOR THE EMPLOYEE PERFORMANCE APPRAISAL SYSTEM IN HRM MODULE
Full text linkIn organizations, such as companies, performance evaluation aims to assess, motivate, and improve employee performance. Human resource development is achieved by recognizing employees' potential. At PT.HM, there is currently no system for employee performance evaluation. The process is done manually by distributing Excel files for self-assessment, which are then forwarded for further evaluation. Performance evaluations are critical for measuring individual performance, serving as a basis for rewards and career paths. This research aims to develop an appraisal system in the Odoo HRM module using the NineBox Matrix, as PT.HM requires employee mapping across nine categories. The research includes four stages: problem identification, data collection, data analysis, and system design. The performance appraisal system will be integrated into the Odoo system already in use at the company for HRM. Data collection was done through direct observation at PT.HM. The system's development benefits HR Managers, Personal Managers, and employees by automating performance and competency assessments. It calculates scores based on predefined weights configured by HR Managers and provides a career path for employee promotions. The system is tested through black-box testing, yielding a 100% success rate, and User Acceptance Testing (UAT), also achieving a 100% success rate, as expected
COMPARISON OF ARIMA, LSTM, AND GRU MODELS FOR FORECASTING SALES OF HIT AEROSOL PRODUCTS
Full text linkA more accurate forecasting model, such as LSTM, can significantly enhance business efficiency by providing more reliable predictions of future sales, allowing for better inventory management, optimized production schedules, and more precise distribution planning. This leads to reduced costs, minimized stockouts, and improved customer satisfaction. This study evaluates the forecasting performance of ARIMA, Long Short-Term Memory (LSTM), and Gated Recurrent Unit (GRU) models using sales data from 2021 to 2023. The models are assessed based on Mean Square Error (MSE), Root Mean Square Error (RMSE), Mean Absolute Error (MAE), and Mean Absolute Percentage Error (MAPE). Results show that LSTM outperforms the other models with a MAPE of 10.76%, followed by ARIMA at 11.23% and GRU at 11.47%. These findings highlight the advantages of deep learning methods, particularly LSTM, in capturing complex patterns and trends in time series data. The study demonstrates the potential of these models to optimize sales forecasting, aiding decision-making processes in production and distribution planning
DEVELOPMENT OF INTEGRATED DIGITAL HR SYSTEM USING WATERFALL FOR LEAVE AND REPORT MANAGEMENT
Full text linkDigitalization in human resource management (HRM) is crucial for modern companies. Several previous studies have discussed HRM, but only a few have focused explicitly on developing leave applications and daily reports, especially regarding comprehensive data recapitulation. Until now, no research has explicitly designed an integrated HRM model incorporating these essential features. In response to this gap, this study presents the design and development of a digital HR management system named “CUTI DULU” to manage leave requests and daily reports. The system was developed Using the Waterfall SDLC model on the Laravel framework to streamline development. It incorporates role-based access control (RBAC) for user permissions and employs JSON Web Tokens (JWT) for secure authentication; data transmission and storage are protected by industry-standard encryption protocols. User Acceptance Testing (UAT) by IT experts and employees verified that the system met functional requirements. Results showed that average leave request processing time fell from four days to about five hours, and administrative errors (e.g. duplicate entries or miscalculations) decreased by 80.95%. Survey responses indicated high satisfaction: 94% of IT experts and 92% of end users reported that the system met their needs. By automating leave and reporting workflows, the proposed system significantly improves administrative efficiency, data transparency, and HR process accuracy. While these results are promising, the current study is limited to a single organizational context, and its broader applicability remains to be validated. Future work should investigate its adaptability across diverse institutional settings to confirm its scalability and generalizability
PENGEMBANGAN SISTEM ROBOT PENJELAJAH BERBASIS MQTT MITIGASI BENCANA DENGAN DUKUNGAN IMAGE PROCESSING
Full text linkDisaster mitigation is a global challenge that requires innovation to enhance the effectiveness of emergency response, particularly in the rapid and safe detection of victims. Although much research focuses on optimizing individual components such as sensors or algorithms, a gap remains in the development of holistically integrated frameworks. This study develops and evaluates an integrated explorer robot system based on Message Queuing Telemetry Transport (MQTT) and artificial intelligence for real-time disaster victim detection. Using a Design Science Research approach, the system architecture integrates an explorer robot based on ESP32-CAM and GPS for data acquisition, a central server running the You Only Look Once (YOLO) algorithm for image analysis, and involves a human operator for critical decision validation. Experimental results show that the system can detect victims with an average accuracy of 87.3% across various simulated scenarios. Communication via the MQTT protocol proved to be highly reliable and efficient, with an average latency of 127 ms and a packet loss rate of only 2.3%, enabling swift coordination between components. This research successfully validates an effective and replicable end-to-end architectural model, thereby presenting a practical blueprint for the development of low-cost Search and Rescue (SAR) robotic system
PEMBUATAN WEBSITE SEBAGAI MEDIA PEMASARAN PT. KARYA PANCANG JAYA
Full text linkThe rapid advancement of digital technology has transformed the way companies promote their products and services, shifting from conventional methods to internet-based marketing strategies. The internet serves as an effective marketing medium to expand customer reach and strengthen business competitiveness through fast and broad information dissemination. PT. Karya Pancang Jaya is a construction service company specializing in pile foundation installation for various types of buildings. However, the company’s marketing activities have relied primarily on conventional approaches such as brochures, exhibitions, and customer referrals. To address this limitation, a community service program was carried out by lecturers from Universitas Atma Jaya Makassar through the development of a company website as a digital marketing medium. The program consisted of four stages—observation, preparation, implementation, and evaluation—conducted over a period of three months, from December 10, 2024, to February 12, 2025. The results indicate that the developed website has been successfully hosted and launched, featuring comprehensive information about the company profile, services, and completed projects. This website is expected to strengthen PT. Karya Pancang Jaya’s digital presence and improve its marketing effectiveness
PEMANFAATAN APLIKASI GEOLISTRIK UNTUK IDENTIFIKASI POTENSI AIR TANAH DI DAERAH HILLA
Full text linkHilla, located in Central Maluku Regency, boasts a gently sloping to steep topography. Extensive green plantations dominate the region. However, water resources, a primary need for the community and agricultural land, remain an unresolved challenge. This community service activity was conducted to assess the potential of groundwater in the Hilla area and provide a basis for effective management. Therefore, geophysical applications, specifically geoelectricity, were utilized to identify potential rock aquifers for groundwater storage. The potential aquifer, based on 2D resistivity cross-section data from geoelectrical readings, was identified at the second location, at a depth of 10-15 meters, and is thought to be formed by sedimentary limestone. This interpretation offers valuable insights for the Hilla community and local government to explore and utilize groundwater resources in the surrounding area. Another positive impact is that the Hilla area can meet its need for reliable and economical groundwater sources directly within its own region, without requiring supply from nearby areas or cities. This ensures that the local community's daily activities are effectively met