Journal of Computer Networks, Architecture and High Performance Computing
Not a member yet
473 research outputs found
Sort by
Usability Assessment of a Waste Bank Customer Management Application Using the System Usability Scale (SUS)
Full text linkWaste Bank is a participatory solution for community-based waste management that provides positive economic and environmental impacts. At a waste bank, community members can deposit separated waste such as plastic, paper, cans, and bottles, as savings. The waste is weighed and assessed based on its type, then its value is converted into savings, similar to a conventional bank. To support the development of waste banks, effective and efficient management of customer data is essential, which can be facilitated through digital applications. This waste bank management application streamlines administrative processes, transaction tracking, and data management related to waste collection activities. The application offers several core features to support data recording and management activities, including customer data management, waste deposit logging, transaction tracking, and waste collection driver coordination. This study aims to evaluate the usability level of the prototype of the Bank Sampah Sakur Palembang customer data management application using the System Usability Scale (SUS) method. The evaluation was conducted with ten respondents who are potential users, consisting of administrative staff and customers. The analysis results show that the prototype received a SUS score of 87, which falls into the excellent and acceptable categories. These findings indicate that the application has a high-quality user interface, is easy to use, and has strong potential for further implementation to support the digital operations of waste bank. These results highlight the application's potential for supporting digital transformation in community-based environmental management systems
User Interface Analysis Using the Heuristic Evaluation Method in the Astra International Cooperative Application (KAI Apps)
Full text linkThis study aims to analyze the usability of the user interface in the Astra International Cooperative (KAI Apps) application using the Heuristic Evaluation method. A quantitative approach was applied through observation of the application and distribution of a Google Form-based questionnaire to 100 respondents selected using the Slovin formula from a population of 100,000 users. The research instrument consisted of 30 statements compiled based on Nielsen's ten Heuristic Evaluation principles, such as visibility of system status, consistency and standards, error prevention, and help and documentation. The data was analyzed using validity and reliability tests, as well as descriptive percentage analysis using SPSS software. The results showed that the Astra Cooperative application scored 86.78%, which is classified as very high, with nine out of ten usability principles rated as good by the majority of respondents. These findings indicate that the application is capable of providing a positive experience for users in accessing cooperative services digitally. However, weaknesses were still found in the aspects of help and documentation, which were considered unclear and not entirely relevant, so that development in the form of tutorials, FAQs, and interactive guides is needed to optimize the user experience
Analysis of the Effectiveness of the T² Hotelling Control Chart in Concrete Control
No full textIn the world of construction, concrete quality plays a very important role because it directly affects the strength and durability of building structures. The purpose of this research is to appraise and evaluate the efficiency of using the T² Hotelling control chart method in controlling concrete quality at PT. Wijaya Karya Beton Tbk by analyzing three main concrete quality parameters: slump, compressive strength, and tensile strength, based on data collected from January to February 2025. The methods employed include multivariate analysis approaches, such as correlation tests, multivariate normality tests, Johnson transformation to improve non-normally distributed data, and the application of generalized variance control charts and T² Hotelling control charts. The results of the study indicate a significant correlation between concrete quality variables; however, the initial data did not meet the assumption of multivariate normality, necessitating the Johnson transformation, which proved effective in improving data distribution and enabling the application of Hotelling's T² analysis. Based on the control charts, most observations remained inside the established control limits; however, some samples fell outside the boundaries, indicating process disturbances. Overall, this study concluded that the Hotelling T² method is effective in detecting process nonconformities at an early stage, thereby serving as a foundation for continuous improvement in concrete production quality and making a significant contribution to strengthening the quality control system in the national construction sector
Implementation Of Decision Tree Algorithms For Classification Of Respiratory Infectious Diseases
Full text linkAcute Respiratory Infection (ARI) is a common respiratory illness that frequently affects children, primarily caused by viruses such as rhinovirus or adenovirus. In Indonesia, a total of 200,000 ARI cases were recorded during the 2021–2023 period. This study aims to implement the Decision Tree algorithm to classify ARI cases. The dataset consists of 1,501 patient records obtained from UPT Puskesmas Bontang Barat for the 2024–2025 period. The research process includes the pre-processing stage, data splitting into training and testing sets using the 10-Fold Cross Validation technique. Subsequently, model evaluation is conducted using the Confusion Matrix to calculate the Accuracy, Precision, Recall, and F1-Score metrics. The results show that the Decision Tree algorithm is capable of performing classification with good performance, achieving an average accuracy of 81.75%, precision of 79.58%, recall of 81.75%, and an F1-score of 80.45%
The Design and Build a Web-Based Purchasing Information System using Agile Methods at Darma Store
No full textIncreased electronic media can help business efficiency in customer service and sales. The implementation of Business to Customer (B2C) focuses on operational improvements which include developing more effective marketing strategies providing more responsive and personalized customer service which aims to improve customer experience and strengthen long-term business relationships. Software implementations are designed to improve operational processes, optimize workflows and minimize time required. This research aims to design and build a web-based online ordering and purchasing information system at the Darma Building Store. The method used in this research is software development. Agile Software Development uses agile methods which are very efficient and convincing in recognizing changes and higher customer satisfaction. The programming language used is Hypertext Preprocessor (PHP) with the Laravel framework. This research hopes that a web-based online ordering and purchasing information system can help the Darma Building Store manage inventory, increase operational efficiency, and making it easier for customers to make purchases. This system has several online ordering features, purchase reports and sales reports. This system is expected to help stores manage inventory, increase operational efficiency, and make it easier for customers to make purchases
Regression Modeling of Zero-Inflated Negative Binomia (ZINB) in Pneumonia Cases in Toddlers in North Sumatra Province
Full text linkPneumonia is a lung infection that causes inflammation in the air sacs within the lungs. This disease is caused by microorganisms such as bacteria, viruses, fungi, or even inhaled substances. This study aims to identify significant factors influencing the incidence of pneumonia in children under five years old in North Sumatra Province in 2022. In this case, the dependent variable has an excessive number of zero values (excess Zero), leading to overdispersion. By using the Zero Inflated Negative Binomial (ZINB) regression method, significant factors affecting the incidence of pneumonia in children under five years old in North Sumatra Province were identified. The study found that the variable of the number of low birth weight babies (BBLR) (X5) significantly influences the incidence of the disease in North Sumatra Province in 2022. It can be seen from the significant variables affecting the occurrence of pneumonia in children under five, which are 0.0406% (X1), 0.00952% (X2), 0.006506% (X3), and 2.122% (X4)
Data Analysis of E-Journal Usage in UPM Library with K-Means Clustering Method
Full text linkThis study aims to evaluate the usage patterns of Emerald and WileyOnline Library e-journals from January to December 2023. By employing the K-Means clustering method, the data were classified to analyze usage characteristics and efficiency. The clustering results indicate that journals in clusters C1 and C2 have higher relevance compared to those in C3, based on download and access numbers. Evaluation using three metrics—average cost per e-journal, average cost per access, and appropriate content usage—revealed that e-journal usage at the UPM library is not yet efficient, with high average costs per access and content usage needing improvement. This study recommends strategies to enhance the efficiency of e-journal usage to better support academic activities and research at UPM
APPLICATION OF K-NEAREST NEIGHBOUR, RECURSIVE ELIMINATION AND ADASYN ALGORITHMS ON DERMATITIS DISEASE CLASSIFICATION DATA
Full text linkDermatitis is a common type of non-infectious skin disease frequently found in Indonesia. Its prevalence is influenced by several factors such as poor hygiene, environmental conditions, and climate change. Data from RSUD Jagakarsa recorded that from 1,066 skin disease cases between February 2023 and January 2024, approximately 62.2% were non-infectious, and 34.4% of those were classified as dermatitis. The diagnostic process for dermatitis is often challenging due to its symptom similarity with other skin conditions, leading to potential misclassification. Therefore, a more accurate and efficient classification approach is required to support medical professionals in identifying dermatitis cases effectively. This study proposes the use of a combination of machine learning methods: K-Nearest Neighbor (KNN) as the core classification algorithm, Recursive Feature Elimination (RFE) for feature selection, and Adaptive Synthetic Sampling (ADASYN) to handle class imbalance within the dataset. The data was sourced from UPTD Puskesmas Bontang Barat in 2024, consisting of 392 samples and 10 main features. Evaluation was conducted using a 10-fold cross-validation scheme. Results showed that the baseline KNN model achieved an average accuracy of 62.23%. With ADASYN applied, the accuracy improved to 63.56%, and further increased to 92.71% when combined with feature selection using RFE
Performance and Risk Assessment of Honeypots on IoT and VPS Using COBIT 2019 and Stress Test
Full text linkThe massive wave of digital transformation has increased the complexity of cyber threats, particularly targeting vital network services. Honeypots have emerged as an effective approach for detecting and analyzing attacks, yet platform selection and management strategies remain a challenge. This study analyzes the performance, management, and risks of two types of honeypots, Cowrie (medium interaction) and Heralding (low interaction), implemented in different computing environments, based on the COBIT 2019 framework (domains EDM03, APO12, and DSS05). Evaluation was conducted through experiments on SSH, Telnet, FTP, SMB, MySQL, and HTTP services, utilizing both isolated and multistage honeypot scenarios. The results show that both honeypot deployments effectively capture brute force and botnet attack patterns and enable accurate logging and validation of attack activities. The analysis of false positive rates and structured log validation processes produced more accurate and relevant attack data. This study is among the first to provide a holistic evaluation of Cowrie and Heralding honeypots with direct COBIT 2019 integration, presenting a novel perspective on governance-driven risk management in honeypot implementation. The application of the COBIT framework ensures that honeypot deployment is not only technically effective but also aligned with robust governance and risk management practices for information security. Strategic recommendations are provided regarding configuration optimization, platform selection, and COBIT-based governance integration to enhance organizational cybersecurity resilienc
Implementation of the K-Means Clustering Algorithm for Segmenting Employee Mental Health Profiles Based on Work Productivity Indicators
Full text linkThis study aims to identify mental health profile segmentation among employees based on work productivity indicators in the context of working from home (WFH) using the K-Means clustering algorithm. This study uniquely integrates mental health and productivity indicators into an unsupervised clustering framework. A cross-sectional method was conducted on 100 employee respondents with 10 main variables, analysed using K-Means with four optimal cluster evaluation methods. The results identified four distinct segments: Low WFH Adaptation (25%), High WFH Enthusiasts (30%), Mixed Preference (25%), and Office Preference (20%), with Silhouette Score validation of 0.623 and Davies-Bouldin Index of 0.967. The main findings reveal the paradox of High WFH Enthusiasts, who have the highest productivity (93%) but the highest mental health risk (1.90). This segmentation provides a practical framework for developing personalised mental health intervention strategies in employee management in the remote working era