Jurnal Techno Nusa Mandiri

SELECTION OF MUARA ABU BEACH SAFETY SYSTEM IN KUPANG CITY USING ANALYTICAL HIERARCHY PROCESS METHOD

Dian Johannis — 2025-03-26

Kupang City has a large coastal area, most of them live so close to the coastline that there is no longer a coastal buffer zone. One of the beaches close to the settlement is Muara Abu beach, which is located in Oesapa Barat Village, Kelapa Lima Sub-district, Kupang City. This research uses the Analytical Hierarchy Process (AHP) method with the following objectives are Establishing a coastal safety system at Muara Abu beach location based on the decision results of the AHP method used optimally and Analyze the coastal safety system using the AHP method. The criteria used in the selection of coastal safety systems are Waves (history, vulnerability, probability, and threat), Erosion (Shoreline change, scouring at the foot of the building, length of eroded beach), Abrasion (Width of abraded beach, length of abraded beach), Sedimentation (Length of closed estuary, percentage of estuary opening, and influence of sedimentation) and Environment (Sea water quality, coral reefs, mangroves). And the alternative system chosen is structural coastal protection, namely Seawall, Groin and Jetty. The results of calculations with the AHP method show the priority scale for securing Muara Abu Beach can be sorted as follows are Jetty is 46.53%, Seawall is 33.37% and Groin is 20.10% The selection of coastal safety systems using the AHP method provides objective results in determining the best alternative. Jetty is the main solution recommended to be implemented in Muara Abu Beach. Further research is recommended to examine the effectiveness of Jetty implementation in the long term.

ARCHITECTURAL DESIGN USING THE ZACHMAN FRAMEWORK AT MINING EQUIPMENT INDUSTRY

Francka Sakti Lee — 2025-03-14

The mining equipment industry requires the effective integration of Information Systems (IS) and Information Technology (IT) into its business processes to achieve a competitive advantage. This study focuses on Enterprise Architecture (EA) planning to align IS/IT implementation with the company's vision and mission. The Zachman Framework is utilized to map the organization’s systems comprehensively, considering six perspectives and addressing 5W+1H (What, Why, When, Where, Who, and How). The research methodology includes data collection through interviews with key stakeholders and observations of core and supporting business activities. These data are analyzed using the Value Chain to assess the current state of the organization. The findings reveal gaps in the existing business processes and the misalignment of IS/IT initiatives with the organization’s goals. Based on these analyses, the study develops an Enterprise Architecture design that proposes a structured approach to IS/IT implementation. The result of this research is a detailed proposal for the development of a tailored application to optimize business processes, improve operational efficiency, and ensure better alignment between IS/IT initiatives and organizational objectives. This study provides practical recommendations for the mining equipment industry to enhance its competitive edge through strategic IS/IT integration.

DESIGNING A WEB-BASED RESTAURANT RESERVATION INFORMATION SYSTEM WITH REQUIREMENT PROTOTYPING METHOD

Raymond Sutjiadi — 2025-03-14

The development of information technology is proliferating, along with the increasing human need for fast, precise, and accurate information. The role of information technology in supporting the business world will make it easier for business people to run their business. One of the business fields that can implement information technology is restaurants. Restaurant management is gradually changing from using conventional methods with manual recording to being more systematic through digital devices. With digital devices, restaurant managers can more efficiently record table reservations and food menu orders. On the consumer side, it is also easier because they can make reservations and food menus from anywhere via a computer or smartphone device connected to the internet. In this research, a web-based application will be created that is used as a means to record table reservations and order food menus with the case studies at Wisata Kampung Kemiri Jember. The design and creation of the website at Wisata Kampung Kemiri Jember uses the requirement prototyping software development method. For the testing process, the Black Box Testing method is used to test all features on the website that have been running according to their functions. To test the user experience, the User Acceptance Testing (UAT) method was used by distributing questionnaires. Through the implementation of this website-based table reservation and food ordering system, it is hoped that work efficiency can be improved to optimize customer satisfaction

DEVELOPMENT OF THE ODOO SYSTEM FOR THE EMPLOYEE PERFORMANCE APPRAISAL SYSTEM IN HRM MODULE

Reizki Jihan Melani — 2025-03-14

In 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.

ARTIFICIAL LEARNING BASED ON KERNEL SVM FOR THE PREDICTION OF CARDIOVASCULAR DISEASE HYPERTENSION

Patient MUSUBAO SWAMBI — 2025-03-14

Hypertension, a critical risk factor for cardiovascular diseases, requires accurate early detection for effective management. This study examines the application of kernel-based Support Vector Machines (SVM) for predicting hypertension, utilizing advanced machine learning techniques to address the complex, non-linear relationships inherent in healthcare data. By employing various kernel functions, such as the radial basis function (RBF) and polynomial kernels, the study aims to enhance the model's ability to capture and interpret the nuanced patterns associated with hypertension risk. The research utilizes a diverse dataset that includes demographic, physiological, and lifestyle variables, applying kernel SVM to predict hypertension outcomes. Performance is evaluated through rigorous cross-validation, with metrics including accuracy, precision, recall, and F1-score. The findings indicate that kernel SVMs significantly outperform traditional linear models, offering superior prediction accuracy and robustness. This study highlights the potential of advanced machine learning methods in improving early detection and personalized risk assessment for hypertension, ultimately supporting more effective management strategies and better cardiovascular health outcomes.

PREDICTION OF HAJJ PILGRIMS' HEALTH RISK USING K-NN, DECISION TREE, CROSS VALIDATION, AND SMOTE

Widi Astuti — 2025-03-14

The background of this study is predicting the health risk levels of hajj pilgrims, which is a significant challenge in improving healthcare services during the pilgrimage. This research contributes by systematically evaluating several machine learning techniques and applying SMOTE to balance the dataset, as opposed to previous studies that relied on single-model classification approaches. The data analyzed includes 5,000 health records of pilgrims, covering various attributes such as age, gender, medical history, and disease diagnosis, sourced from the Siskohat database of the Directorate General of Hajj and Umrah Management. The results show that Cross-Validation (Logistic Regression) achieved the highest accuracy (87.9%) after applying SMOTE, outperforming Decision Tree (86.4%) and K-NN (83.1%). These findings highlight that SMOTE significantly enhances recall, ensuring better identification of high-risk patients. The implications of these results contribute to hajj health management by providing a robust predictive framework that improves early risk detection and medical resource allocation, while also demonstrating a novel approach to handling imbalanced healthcare datasets.

PERFORMANCE OF THE DELTA MODULATION SYSTEM WITH VARIOUS DELTA STEP SIZES

Djadjat Sudaradjat — 2025-03-14

Delta 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.

SENTIMENT ANALYSIS OF JAKLINGKO APP REVIEWS USING MACHINE LEARNING AND LSTM

Maghfiroh Maulani — 2025-03-17

Application-based transportation services have rapidly developed in recent years, with various studies indicating that service quality and user experience play a crucial role in the adoption of this technology. Previous research has analyzed user satisfaction with digital transportation applications, highlighting factors such as ease of use, service reliability, and the effectiveness of fare systems. This study aims to analyze user sentiment toward the JakLingko application to assess satisfaction levels and identify aspects that need improvement. Utilizing a dataset of 200 user reviews, this research applies data preprocessing techniques to clean and organize the information before performing sentiment classification. The machine learning models used include Naïve Bayes, Random Forest, Support Vector Machine, Logistic Regression, Decision Tree, and Long Short-Term Memory (LSTM), categorizing sentiment into positive, negative, and neutral. The analysis results indicate a dominance of negative sentiment in user reviews, reflecting a significant level of dissatisfaction with the application. This highlights major challenges in the implementation of transportation applications, potentially affecting public adoption and trust in the service. Therefore, besides providing insights into user perceptions, this study also proposes improvement strategies aimed at enhancing features and the overall user experience. Given the high proportion of negative sentiment, this research emphasizes the importance of improving the accuracy of sentiment analysis models to generate deeper and more precise insights. These findings can serve as a foundation for designing policies and strategies to improve application-based transportation services, ultimately enhancing service quality and expanding user adoption.

FEATURE SELECTION COMPARATIVE PERFORMANCE FOR UNSUPERVISED LEARNING ON CATEGORICAL DATASET

Rachmad Fitriyanto — 2025-03-17

In 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.

DIGITALIZATION OF HR AT ONIP: INFORMATION SYSTEMS URBANIZATION AND STRATEGIC ALIGNMENT AS KEY LEVERS

Evariste SINDANI — 2025-03-20

This article examines the digitalization of human resources (HR) at the Office National d’Identification de la Population (ONIP) in the Democratic Republic of Congo (DRC), emphasizing the pivotal role of information systems (IS) urbanization and strategic alignment as key levers. Using a qualitative methodology that combines semi-structured interviews with 15 stakeholders (HR managers, IT specialists, directors) and process analysis, we demonstrate the following outcomes: 40% reduction in HR processing time (from 7 to 4.2 days), 30% decrease in data entry errors through administrative task automation, 29% optimization of annual IT expenditures (from 120,000 to 85,000 USD), Increase in employee satisfaction scores from 58% to 82% (based on an internal survey of 200 employees). These results, derived from the implementation of a secure and modular HR information system (HRIS), underscore the efficacy of a structured approach in a fragile context. The article contributes to the literature on HR digital transformation in the African public sector by proposing a reproducible framework grounded in IS interoperability and collaborative governance.

IMPROVING AGRICULTURAL YIELDS IN THE DEMOCRATIC REPUBLIC OF CONGO USING MACHINE LEARNING ALGORITHMS

Rodolphe Nsimba Malumba — 2025-03-20

This article presents an analysis of agricultural yields in the Democratic Republic of Congo (DRC) using machine learning algorithms. The study is based on around 30,000 records covering several years of agricultural production. Each record includes variables such as seed type, climatic conditions (temperature, rainfall and humidity), soil characteristics (pH, nutrients), farming practices (fertilizer use, irrigation) and yields obtained. The data comes from a variety of sources, including METTELSAT, the World Meteorological Organization (WMO) and WorldClim for climate data, and the DRC Ministry of Agriculture and the FAO for soil and agricultural data. The algorithms evaluated include linear regression, random forest regression, Gradient Boosting Machines (GBM), Support Vector Machines (SVM), and Artificial Neural Networks (ANN). The performance of the algorithms is measured using metrics such as MSE, MAE, RMSE, R² Score and MAPE on three separate case studies (Farm A, Farm B and Farm C). The results show that artificial neural networks (ANNs) perform best, with MSE ranging from 600 to 850, MAE from 12 to 17, RMSE from 24.49 to 29.15, R² Score from 0.92 to 0.95, and MAPE from 8.5% to 10.7%. Next came GBM, random forest regression, SVM and finally linear regression. These results highlight the potential of machine learning algorithms to improve agricultural yield forecasts in the DRC.

OPTIMIZED FACEBOOK PROPHET FOR MPOX FORECASTING: ENHANCING PREDICTIVE ACCURACY WITH HYPERPARAMETER TUNING

Nur Alamsyah — 2025-03-25

MPOX (Monkeypox) has become a significant global health concern, requiring accurate forecasting for effective outbreak management. This study improves MPOX case prediction using Facebook Prophet with hyperparameter optimization. The dataset consists of global MPOX case records collected over time. Data preprocessing includes missing value imputation, normalization, and aggregation. Facebook Prophet is applied to forecast case trends, with model performance evaluated using Mean Squared Error (MSE) and Root Mean Squared Error (RMSE). A baseline Prophet model is first trained using default parameters. The model is then optimized by fine-tuning seasonality mode, changepoint prior scale, and growth model. The results show that hyperparameter tuning significantly enhances forecasting accuracy. The optimized model reduces MSE from 541,844.77 to 320,953.34 and RMSE from 736.10 to 566.53, demonstrating improved precision. The model also captures trend shifts and seasonal fluctuations more effectively. In conclusion, this study confirms that tuning Facebook Prophet improves epidemic forecasting, making it a reliable tool for MPOX monitoring. Future research should integrate external factors, such as vaccination rates and mobility data, to further refine predictions.

EARLY DETECTION OF ROT IN THAI PAPAYA (CARICA PAPAYA) USING THE K-NN METHOD

Agus Prayitno — 2025-03-26

Determining the category of a plant or fruit involves several criteria. One of the easiest methods to use is morphological criteria, which entails studying the external structure that can be directly observed. However, this approach cannot be regarded as a fixed standard since people's interpretations may vary. To address this, a system was developed to assess the ripeness of Thai papaya fruit, utilizing image processing and the K-Nearest Neighbor (KNN) method. This study analyzes a data set to detect rotten papaya fruit, which is expected to help consumers recognize papaya fruit that is purchased in a perfectly ripe condition, not ripe with certain parts that are rotting. The indicator used to determine the category is the color of the skin of Thai Papaya fruit with an ROI of 600 pixels x 300 pixels by finding the mean RGB value and then calculating it using the Euclidean distance formula. From the results of these calculations, it is expected to get a classification using K-Nearest Neighbor (KNN) to get an image pattern of the level of rottenness on the surface of the papaya. Therefore, by improving the RGB image eliminating noise in the papaya image, and using the K-NN classification of the image pattern obtained from the research results from the sampling data, an accuracy level of 80% was obtained with a range of mean R values: 130,671-169,630, mean G: 106,891-131,895, and mean B: 61,119-100,776 which came from 120 data.